In this paper, we propose a class of faster double adaptive gradient methods to solve nonconvex finite-sum optimization problems possibly with nonsmooth regularization by simultaneously using adaptive learning rate and adaptive mini-batch size. Specifically, we first propose a double adaptive stochastic gradient method (i.e., 2AdaSGD), and prove that our 2AdaSGD obtains a low stochastic first-order oracle (SFO) complexity for finding a stationary solution under the population smoothness condition. Furthermore, we propose a variance reduced double adaptive stochastic gradient method (i.e., 2AdaSPIDER), and prove that our 2AdaSPIDER obtains an optimal SFO complexity under the average smoothness condition, which is lower than the SFO complexity of the existing double adaptive gradient algorithms. In particular, we introduce a new stochastic gradient mapping to adaptively adjust mini-batch size in our stochastic gradient methods. We conduct some numerical experiments to verify efficiency of our proposed methods.

Minimax optimization recently is widely applied in many machine learning tasks such as generative adversarial networks, robust learning and reinforcement learning. In the paper, we study a class of nonconvex-nonconcave minimax optimization with nonsmooth regularization, where the objective function is possibly nonconvex on primal variable $x$, and it is nonconcave and satisfies the Polyak-Lojasiewicz (PL) condition on dual variable $y$. Moreover, we propose a class of enhanced momentum-based gradient descent ascent methods (i.e., MSGDA and AdaMSGDA) to solve these stochastic nonconvex-PL minimax problems. In particular, our AdaMSGDA algorithm can use various adaptive learning rates in updating the variables $x$ and $y$ without relying on any specifical types. Theoretically, we prove that our methods have the best known sample complexity of $\tilde{O}(\epsilon^{-3})$ only requiring one sample at each loop in finding an $\epsilon$-stationary solution. Some numerical experiments on PL-game and Wasserstein-GAN demonstrate the efficiency of our proposed methods.

Bilevel optimization is widely applied in many machine learning tasks such as hyper-parameter learning and meta learning. Recently, many algorithms have been proposed to solve these bilevel optimization problems, which rely on the smoothness condition of objective functions of the bilevel optimization. In fact, some machine learning tasks such as learning language model do not satisfy the smoothness condition of objective functions. More recently, some methods have begun to study generalized smooth bilevel optimization. However, these proposed methods for generalized smooth bilevel optimization only focus on the (strongly) convex lower objective function. Meanwhile, these methods only consider the generalized-smooth upper-level objective, but still require the standard smooth lower-level objective in the bilevel optimization. To fill this gap, in the paper, thus we study the generalized-smooth bilevel optimization with the nonconvex lower-level objective function, where both upper-level and lower-level objectives are generalized-smooth. We propose an efficient single-loop Hessian/Jacobian-free penalty normalized gradient (i.e., PNGBiO) method. Moreover, we prove that our PNGBiO obtains a fast convergence rate of $O(\frac{1}{T^{1/4}})$ for finding a stationary solution, where $T$ denotes the iteration number. Meanwhile, we also propose a stochastic version of our PNGBiO (i.e., S-PNGBiO) method to solve stochastic bilevel problems, and prove that our S-PNGBiO has a fast convergence rate of $O(\frac{1}{T^{1/6}})$. Some experimental results on hyper-parameter learning and meta learning demonstrate efficiency of our proposed methods.

Hierarchical optimization is attracting significant attentions as it can be applied to a broad range of machine learning tasks. Recently, many algorithms are proposed to improve the theoretical results of minimax and bilevel optimizations. Among these works, a core issue that has not been well studies is to escape saddle point and find local minimum. In this paper, thus, we investigate the methods to achieve second-order optimality for nonconvex minimax and bilevel optimization. Specifically, we propose a new algorithm named PRGDA without the computation of second order derivative of the primal function. In nonconvex-strongly-concave minimax optimization, we prove that our algorithm can find a second-order stationary point with the gradient complexity that matches state-of-the-art result to find first-order stationary point. To our best knowledge, PRGDA is the first stochastic algorithm that is guaranteed to obtain the second-order stationary point for nonconvex minimax problems. In nonconvex-strongly-convex bilevel optimization, our method also achieves better gradient complexity to find local minimum. Finally, we conduct two numerical experiments to validate the performance of our new method.

Federated learning is a popular distributed and privacy-preserving learning paradigm in machine learning. Recently, some federated learning algorithms have been proposed to solve the distributed minimax problems. However, these federated minimax algorithms still suffer from high gradient or communication complexity. Meanwhile, few algorithm focuses on using adaptive learning rate to accelerate these algorithms. To fill this gap, in the paper, we study a class of nonconvex minimax optimization, and propose an efficient adaptive federated minimax optimization algorithm (i.e., AdaFGDA) to solve these distributed minimax problems. Specifically, our AdaFGDA builds on the momentum-based variance reduced and local-SGD techniques, and it can flexibly incorporate various adaptive learning rates by using the unified adaptive matrices. Theoretically, we provide a solid convergence analysis framework for our AdaFGDA algorithm under non-i.i.d. setting. Moreover, we prove our AdaFGDA algorithm obtains a lower gradient (i.e., stochastic first-order oracle, SFO) complexity of $\tilde{O}(\epsilon^{-3})$ with lower communication complexity of $\tilde{O}(\epsilon^{-2})$ in finding $\epsilon$-stationary point of the nonconvex minimax problems. Experimentally, we conduct some experiments on the deep AUC maximization and robust neural network training tasks to verify efficiency of our algorithms.

Most existing dynamic or runtime channel pruning meth-ods have to store all weights to achieve efficient inference, which brings extra storage costs. Static pruning methods can reduce storage costs directly, but their performance is limited by using a fixed sub-network to approximate the orig-inal model. Most existing pruning works suffer from these drawbacks because they were designed to only conduct ei-ther static or dynamic pruning. In this paper, we propose a novel method to solve both efficiency and storage challenges via simultaneously conducting dynamic and static channel pruning for convolutional neural networks. We propose a new bi-level optimization based model to naturally integrate the static and dynamic channel pruning. By doing so, our method enjoys benefits from both sides, and the disadvan-tages of dynamic and static pruning are reduced. After pruning, we permanently remove redundant parameters and then finetune the model with dynamic flexibility. Experimental results on CIFAR-10 and ImageNet datasets suggest that our method can achieve state-of-the-art performance compared to existing dynamic and static channel pruning methods.

Federated learning (FL) is an emerging learning paradigm where a set of distributed clients learns a task under the coordination of a server. The FedAvg algorithm is one of the most widely used methods in FL. In FedAvg, the learning rate is a constant rather than changing adaptively. Adaptive gradient methods have demonstrated superior performance over the constant learning rate schedules in non-distributed settings, and they have recently been adapted to FL. However, the majority of these methods are designed for unconstrained settings. Meanwhile, many crucial FL applications, like disease diagnosis and biomarker identification, often rely on constrained formulations such as Lasso and group Lasso. It remains an open question as to whether adaptive gradient methods can be effectively applied to FL problems with constrains. In this work, we introduce \textbf{FedDA}, a novel adaptive gradient framework for FL. This framework utilizes a restarted dual averaging technique and is compatible with a range of gradient estimation methods and adaptive learning rate schedules. Specifically, an instantiation of our framework FedDA-MVR achieves sample complexity $\tilde{O}(K^{-1}\epsilon^{-1.5})$ and communication complexity $\tilde{O}(K^{-0.25}\epsilon^{-1.25})$ for finding a stationary point $\epsilon$ in the constrained setting with $K$ be the number of clients. We conduct experiments over both constrained and unconstrained tasks to confirm the effectiveness of our approach.

Bilevel optimization is widely applied in many machine learning tasks such as hyper-parameter learning, meta learning and reinforcement learning. Although many algorithms recently have been developed to solve the bilevel optimization problems, they generally rely on the (strongly) convex lower-level problems. More recently, some methods have been proposed to solve the nonconvex-PL bilevel optimization problems, where their upper-level problems are possibly nonconvex, and their lower-level problems are also possibly nonconvex while satisfying Polyak-Łojasiewicz (PL) condition. However, these methods still have a high convergence complexity or a high computation complexity such as requiring compute expensive Hessian/Jacobian matrices and its inverses. In the paper, thus, we propose an efficient Hessian/Jacobian-free method (i.e., HJFBiO) with the optimal convergence complexity to solve the nonconvex-PL bilevel problems. Theoretically, under some mild conditions, we prove that our HJFBiO method obtains an optimal convergence rate of $O(\frac{1}{T})$, where $T$ denotes the number of iterations, and has an optimal gradient complexity of $O(\epsilon^{-1})$ in finding an $\epsilon$-stationary solution. We conduct some numerical experiments on the bilevel PL game and hyper-representation learning task to demonstrate efficiency of our proposed method.

Decentralized learning recently has received increasing attention in machine learning due to its advantages in implementation simplicity and system robustness, data privacy. Meanwhile, the adaptive gradient methods show superior performances in many machine learning tasks such as training neural networks. Although some works focus on studying decentralized optimization algorithms with adaptive learning rates, these adaptive decentralized algorithms still suffer from high sample complexity. To fill these gaps, we propose a class of faster adaptive decentralized algorithms (i.e., AdaMDOS and AdaMDOF) for distributed nonconvex stochastic and finite-sum optimization, respectively. Moreover, we provide a solid convergence analysis framework for our methods. In particular, we prove that our AdaMDOS obtains a near-optimal sample complexity of $\tilde{O}(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution of nonconvex stochastic optimization. Meanwhile, our AdaMDOF obtains a near-optimal sample complexity of $O(\sqrt{n}\epsilon^{-2})$ for finding an $\epsilon$-stationary solution of for nonconvex finite-sum optimization, where $n$ denotes the sample size. To the best of our knowledge, our AdaMDOF algorithm is the first adaptive decentralized algorithm for nonconvex finite-sum optimization. Some experimental results demonstrate efficiency of our algorithms.

Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, the federated learning in practice still faces numerous challenges, such as the large training iterations to converge since the sizes of models and datasets keep increasing, and the lack of adaptivity by SGD-based model updates. Meanwhile, the study of adaptive methods in federated learning is scarce and existing works either lack a complete theoretical convergence guarantee or have slow sample complexity. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on the momentum-based variance reduced technique in cross-silo FL. We first explore how to design the adaptive algorithm in the FL setting. By providing a counter-example, we prove that a simple combination of FL and adaptive methods could lead to divergence. More importantly, we provide a convergence analysis for our method and prove that our algorithm is the first adaptive FL algorithm to reach the best-known samples O(epsilon(-3)) and O(epsilon(-2)) communication rounds to find an epsilon-stationary point without large batches. The experimental results on the language modeling task and image classification task with heterogeneous data demonstrate the efficiency of our algorithms.

In the paper, we propose a class of faster adaptive Gradient Descent Ascent (GDA) methods for solving the nonconvex-strongly-concave minimax problems by using the unified adaptive matrices, which include almost all existing coordinate-wise and global adaptive learning rates. In particular, we provide an effective convergence analysis framework for our adaptive GDA methods. Specifically, we propose a fast Adaptive Gradient Descent Ascent (AdaGDA) method based on the basic momentum technique, which reaches a lower gradient complexity of $\tilde{O}(\kappa^4\epsilon^{-4})$ for finding an $\epsilon$-stationary point without large batches, which improves the existing results of the adaptive GDA methods by a factor of $O(\sqrt{\kappa})$. Moreover, we propose an accelerated version of AdaGDA (VR-AdaGDA) method based on the momentum-based variance reduced technique, which achieves a lower gradient complexity of $\tilde{O}(\kappa^{4.5}\epsilon^{-3})$ for finding an $\epsilon$-stationary point without large batches, which improves the existing results of the adaptive GDA methods by a factor of $O(\epsilon^{-1})$. Moreover, we prove that our VR-AdaGDA method can reach the best known gradient complexity of $\tilde{O}(\kappa^{3}\epsilon^{-3})$ with the mini-batch size $O(\kappa^3)$. The experiments on policy evaluation and fair classifier learning tasks are conducted to verify the efficiency of our new algorithms.

In this paper, we propose a novel channel pruning method to reduce the computational and storage costs of Convolutional Neural Networks (CNNs). Many existing one-shot pruning methods directly remove redundant structures, which brings a huge gap between the model before and after network pruning. This gap will no doubt result in performance loss for network pruning. To mitigate this gap, we first learn a target sub-network during the model training process, and then we use this sub-network to guide the learning of model weights through partial regularization. The target sub-network is learned and produced by using an architecture generator, and it can be optimized efficiently. In addition, we also derive the proximal gradient for our proposed partial regularization to facilitate the structural alignment process. With these designs, the gap between the pruned model and the sub-network is reduced, thus improving the pruning performance. Empirical results also suggest that the sub-network found by our method has a much higher performance than the one-shot pruning setting. Extensive experiments show that our method can achieve state-of-the-art performances on CIFAR-10 and ImageNet with ResNets and MobileNet-V2.

Bilevel Optimization has witnessed notable progress recently with new emerging efficient algorithms. However, its application in the Federated Learning setting remains relatively underexplored, and the impact of Federated Learning's inherent challenges on the convergence of bilevel algorithms remain obscure. In this work, we investigate Federated Bilevel Optimization problems and propose a communication-efficient algorithm, named FedBiOAcc. The algorithm leverages an efficient estimation of the hyper-gradient in the distributed setting and utilizes the momentum-based variance-reduction acceleration. Remarkably, FedBiOAcc achieves a communication complexity $O(\epsilon^{-1})$, a sample complexity $O(\epsilon^{-1.5})$ and the linear speed up with respect to the number of clients. We also analyze a special case of the Federated Bilevel Optimization problems, where lower level problems are locally managed by clients. We prove that FedBiOAcc-Local, a modified version of FedBiOAcc, converges at the same rate for this type of problems. Finally, we validate the proposed algorithms through two real-world tasks: Federated Data-cleaning and Federated Hyper-representation Learning. Empirical results show superior performance of our algorithms.

In the paper, we study a class of useful minimax problems on Riemanian manifolds and propose a class of effective Riemanian gradient-based methods to solve these minimax problems. Specifically, we propose an effective Riemannian gradient descent ascent (RGDA) algorithm for the deterministic minimax optimization. Moreover, we prove that our RGDA has a sample complexity of$O(\kappa ^{2}\epsilon ^{-2})$for finding an$\epsilon$-stationary solution of the Geodesically-Nonconvex Strongly-Concave (GNSC) minimax problems, where$\kappa$denotes the condition number. At the same time, we present an effective Riemannian stochastic gradient descent ascent (RSGDA) algorithm for the stochastic minimax optimization, which has a sample complexity of$O(\kappa ^{4}\epsilon ^{-4})$for finding an$\epsilon$-stationary solution. To further reduce the sample complexity, we propose an accelerated Riemannian stochastic gradient descent ascent (Acc-RSGDA) algorithm based on the momentum-based variance-reduced technique. We prove that our Acc-RSGDA algorithm achieves a lower sample complexity of$\tilde{O}(\kappa ^{4}\epsilon ^{-3})$in searching for an$\epsilon$-stationary solution of the GNSC minimax problems. Extensive experimental results on the robust distributional optimization and robust Deep Neural Networks (DNNs) training over Stiefel manifold demonstrate efficiency of our algorithms.

Standard deep learning models have been mainly designed for balanced data mining tasks and use accuracy to evaluate the classifier. However, in many real-world applications, the distribution of data is skewed. If the standard models, which are designed to optimize the accuracy, are applied to the imbalanced data, the prediction performance could be poor because the model bias towards the majority class. To address the imbalanced data mining problem, areas under precision-recall curves (AUPRC) was proposed as a good measure to evaluate the performance of prediction models on imbalanced data sets, and shows excellent capability in identifying the models with high predictive power. To improve the performance of models, researchers recently design methods to directly optimize AUPRC for imbalanced data mining. However, these approaches suffer from a high iteration complexity and efficient methods are desired. In this paper, we propose a faster stochastic method (i.e., ROAP) for maximizing the AURPC based on the momentum-based variance reduced technique. Our new method is based on the maximization of non-parametric averaged precision (AP), which is a popular unbiased point estimator of AUPRC, and the optimization objective in this paper can be converted into a sum of dependent compositional functions, where the inner functions rely on random variables of both inner and outer levels. Compared to previous methods, our ROAP algorithm can achieve a lower iteration complexity of $O(\epsilon^{-3})$ for finding an ϵ-stationary solution. Furthermore, we extend our method to an adaptive version (i.e., AROAP) with the same iteration complexity of $O(\epsilon^{-3})$. To the best of our knowledge, this paper is the first work showing that the variance reduction method can be incorporated into maximizing the AURPC for efficient data mining on imbalanced datasets. Finally, we conduct extensive experiments on various imbalanced data sets with different models to demonstrate the efficiency of our new algorithms.

Distributed data mining is an emerging research topic to effectively and efficiently address hard data mining tasks using big data, which are partitioned and computed on different worker nodes, instead of one centralized server. Nevertheless, distributed learning methods often suffer from the communication bottleneck when the network bandwidth is limited or the size of model is large. To solve this critical issue, many gradient compression methods have been proposed recently to reduce the communication cost for multiple optimization algorithms. However, the current applications of gradient compression to adaptive gradient method, which is widely adopted because of its excellent performance to train DNNs, do not achieve the same ideal compression rate or convergence rate as Sketched-SGD. To address this limitation, in this paper, we propose a class of novel distributed Adam-type algorithms (i.e., SketchedAMSGrad) utilizing sketching, which is a promising compression technique that reduces the communication cost from O(d) to $O(\log(d))$ where d is the parameter dimension. In our theoretical analysis, we prove that our new algorithm achieves a fast convergence rate of $O\left(\frac{1}{\sqrt{nT}}+\frac{1}{\left(k/d\right)^{2}T}\right)$ with the communication cost of $O(k\log(d))$ at each iteration. Compared with single-machine AMSGrad, our algorithm can achieve the linear speedup with respect to the number of workers n. The experimental result of training distributed DNN validates the performance of our algorithms.

Bilevel optimization has been recently used in many machine learning problems such as hyperparameter optimization, policy optimization, and meta learning. Although many bilevel optimization methods have been proposed, they still suffer from the high computational complexities and do not consider the more general bilevel problems with nonsmooth regularization. In the paper, thus, we propose a class of enhanced bilevel optimization methods with using Bregman distance to solve bilevel optimization problems, where the outer subproblem is nonconvex and possibly nonsmooth, and the inner subproblem is strongly convex. Specifically, we propose a bilevel optimization method based on Bregman distance (BiO-BreD) to solve deterministic bilevel problems, which achieves a lower computational complexity than the best known results. Meanwhile, we also propose a stochastic bilevel optimization method (SBiO-BreD) to solve stochastic bilevel problems based on stochastic approximated gradients and Bregman distance. Moreover, we further propose an accelerated version of SBiO-BreD method (ASBiO-BreD) using the variance-reduced technique, which can achieve a lower computational complexity than the best known computational complexities with respect to condition number $\kappa$ and target accuracy $\epsilon$ for finding an $\epsilon$-stationary point. We conduct data hyper-cleaning task and hyper-representation learning task to demonstrate that our new algorithms outperform related bilevel optimization approaches.

In the paper, we propose a class of accelerated zeroth-order and first-order momentum methods for both nonconvex mini-optimization and minimax-optimization. Specifically, we propose a new accelerated zeroth-order momentum (Acc-ZOM) method for black-box mini-optimization where only function values can be obtained. Moreover, we prove that our Acc-ZOM method achieves a lower query complexity of $\tilde{O}(d^{3/4}\epsilon^{-3})$ for finding an $\epsilon$-stationary point, which improves the best known result by a factor of $O(d^{1/4})$ where $d$ denotes the variable dimension. In particular, our Acc-ZOM does not need large batches required in the existing zeroth-order stochastic algorithms. Meanwhile, we propose an accelerated zeroth-order momentum descent ascent (Acc-ZOMDA) method for black-box minimax optimization, where only function values can be obtained. Our Acc-ZOMDA obtains a low query complexity of $\tilde{O}((d_1+d_2)^{3/4}\kappa_y^{4.5}\epsilon^{-3})$ without requiring large batches for finding an $\epsilon$-stationary point, where $d_1$ and $d_2$ denote variable dimensions and $\kappa_y$ is condition number. Moreover, we propose an accelerated first-order momentum descent ascent (Acc-MDA) method for minimax optimization, whose explicit gradients are accessible. Our Acc-MDA achieves a low gradient complexity of $\tilde{O}(\kappa_y^{4.5}\epsilon^{-3})$ without requiring large batches for finding an $\epsilon$-stationary point. In particular, our Acc-MDA can obtain a lower gradient complexity of $\tilde{O}(\kappa_y^{2.5}\epsilon^{-3})$ with a batch size $O(\kappa_y^4)$, which improves the best known result by a factor of $O(\kappa_y^{1/2})$. Extensive experimental results on black-box adversarial attack to deep neural networks and poisoning attack to logistic regression demonstrate efficiency of our algorithms.

Stochastic optimization methods have become a class of popular optimization tools in machine learning. Especially, stochastic gradient descent (SGD) has been widely used for machine learning problems, such as training neural networks, due to low per-iteration computational complexity. In fact, the Newton or quasi-newton (QN) methods leveraging the second-order information are able to achieve a better solution than the first-order methods. Thus, stochastic QN (SQN) methods have been developed to achieve a better solution efficiently than the stochastic first-order methods by utilizing approximate second-order information. However, the existing SQN methods still do not reach the best known stochastic first-order oracle (SFO) complexity. To fill this gap, we propose a novel faster stochastic QN method (SpiderSQN) based on the variance reduced technique of SIPDER. We prove that our SpiderSQN method reaches the best known SFO complexity of$\mathcal {O}(n+n^{1/2}\epsilon ^{-2})$in the finite-sum setting to obtain an$\epsilon $-first-order stationary point. To further improve its practical performance, we incorporate SpiderSQN with different momentum schemes. Moreover, the proposed algorithms are generalized to the online setting, and the corresponding SFO complexity of$\mathcal {O}(\epsilon ^{-3})$is developed, which also matches the existing best result. Extensive experiments on benchmark data sets demonstrate that our new algorithms outperform state-of-the-art approaches for nonconvex optimization.

Recently decentralized optimization attracts much attention in machine learning because it is more communication-efficient than the centralized fashion. Quantization is a promising method to reduce the communication cost via cutting down the budget of each single communication using the gradient compression. To further improve the communication efficiency, more recently, some quantized decentralized algorithms have been studied. However, the quantized decentralized algorithm for nonconvex constrained machine learning problems is still limited. Frank-Wolfe (a.k.a., conditional gradient or projection-free) method is very efficient to solve many constrained optimization tasks, such as low-rank or sparsity-constrained models training. In this paper, to fill the gap of decentralized quantized constrained optimization, we propose a novel communication-efficient Decentralized Quantized Stochastic Frank-Wolfe (DQSFW) algorithm for non-convex constrained learning models. We first design a new counterexample to show that the vanilla decentralized quantized stochastic Frank-Wolfe algorithm usually diverges. Thus, we propose DQSFW algorithm with the gradient tracking technique to guarantee the method will converge to the stationary point of non-convex optimization safely. In our theoretical analysis, we prove that to achieve the stationary point our DQSFW algorithm achieves the same gradient complexity as the standard stochastic Frank-Wolfe and centralized Frank-Wolfe algorithms, but has much less communication cost. Experiments on matrix completion and model compression applications demonstrate the efficiency of our new algorithm.

Channel pruning is a class of powerful methods for model compression. When pruning a neural network, it's ideal to obtain a sub-network with higher accuracy. However, a sub-network does not necessarily have high accuracy with low classification loss (loss-metric mismatch). In the paper, we first consider the loss-metric mismatch problem for pruning and propose a novel channel pruning method for Convolutional Neural Networks (CNNs) by directly maximizing the performance (i.e., accuracy) of sub-networks. Specifically, we train a stand-alone neural network to predict sub-networks' performance and then maximize the output of the network as a proxy of accuracy to guide pruning. Training such a performance prediction network efficiently is not an easy task, and it may potentially suffer from the problem of catastrophic forgetting and the imbalance distribution of sub-networks. To deal with this challenge, we introduce a corresponding episodic memory to update and collect sub-networks during the pruning process. In the experiment section, we further demonstrate that the gradients from the performance prediction network and the classification loss have different directions. Extensive experimental results show that the proposed method can achieve state-of-the-art performance with ResNet, MobileNetV2, and ShuffleNetV2+ on ImageNet and CIFAR-10.

In the paper, we study the underdamped Langevin diffusion (ULD) with strongly-convex potential consisting of finite summation of $N$ smooth components, and propose an efficient discretization method, which requires $O(N+d^\frac{1}{3}N^\frac{2}{3}/\varepsilon^\frac{2}{3})$ gradient evaluations to achieve $\varepsilon$-error (in $\sqrt{\mathbb{E}{\lVert{\cdot}\rVert_2^2}}$ distance) for approximating $d$-dimensional ULD. Moreover, we prove a lower bound of gradient complexity as $\Omega(N+d^\frac{1}{3}N^\frac{2}{3}/\varepsilon^\frac{2}{3})$, which indicates that our method is optimal in dependence of $N$, $\varepsilon$, and $d$. In particular, we apply our method to sample the strongly-log-concave distribution and obtain gradient complexity better than all existing gradient based sampling algorithms. Experimental results on both synthetic and real-world data show that our new method consistently outperforms the existing ULD approaches.

Adaptive gradient methods have shown excellent performances for solving many machine learning problems. Although multiple adaptive gradient methods were recently studied, they mainly focus on either empirical or theoretical aspects and also only work for specific problems by using some specific adaptive learning rates. Thus, it is desired to design a universal framework for practical algorithms of adaptive gradients with theoretical guarantee to solve general problems. To fill this gap, we propose a faster and universal framework of adaptive gradients (i.e., SUPER-ADAM) by introducing a universal adaptive matrix that includes most existing adaptive gradient forms. Moreover, our framework can flexibly integrate the momentum and variance reduced techniques. In particular, our novel framework provides the convergence analysis support for adaptive gradient methods under the nonconvex setting. In theoretical analysis, we prove that our SUPER-ADAM algorithm can achieve the best known gradient (i.e., stochastic first-order oracle (SFO)) complexity of $\tilde{O}(\epsilon^{-3})$ for finding an $\epsilon$-stationary point of nonconvex optimization, which matches the lower bound for stochastic smooth nonconvex optimization. In numerical experiments, we employ various deep learning tasks to validate that our algorithm consistently outperforms the existing adaptive algorithms. Code is available at https://github.com/LIJUNYI95/SuperAdam

In the paper, we propose a class of efficient mirror descent ascent methods to solve the nonsmooth nonconvex-strongly-concave minimax problems by using dynamic mirror functions, and introduce a convergence analysis framework to conduct rigorous theoretical analysis for our mirror descent ascent methods. For our stochastic algorithms, we first prove that the mini-batch stochastic mirror descent ascent (SMDA) method obtains a gradient complexity of $O(\kappa^3\epsilon^{-4})$ for finding an $\epsilon$-stationary point, where $\kappa$ denotes the condition number. Further, we propose an accelerated stochastic mirror descent ascent (VR-SMDA) method based on the variance reduced technique. We prove that our VR-SMDA method achieves a lower gradient complexity of $O(\kappa^3\epsilon^{-3})$. For our deterministic algorithm, we prove that our deterministic mirror descent ascent (MDA) achieves a lower gradient complexity of $O(\sqrt{\kappa}\epsilon^{-2})$ under mild conditions, which matches the best known complexity in solving smooth nonconvex-strongly-concave minimax optimization. We conduct the experiments on fair classifier and robust neural network training tasks to demonstrate the efficiency of our new algorithms.

In this paper, we study the nonconvex-strongly-concave minimax optimization problem on decentralized setting. The minimax problems are attracting increasing attentions because of their popular practical applications such as policy evaluation and adversarial training. As training data become larger, distributed training has been broadly adopted in machine learning tasks. Recent research works show that the decentralized distributed data-parallel training techniques are specially promising, because they can achieve the efficient communications and avoid the bottleneck problem on the central node or the latency of low bandwidth network. However, the decentralized minimax problems were seldom studied in literature and the existing methods suffer from very high gradient complexity. To address this challenge, we propose a new faster decentralized algorithm, named as DM-HSGD, for nonconvex minimax problems by using the variance reduced technique of hybrid stochastic gradient descent. We prove that our DM-HSGD algorithm achieves stochastic first-order oracle (SFO) complexity of $O(\kappa^3 \epsilon^{-3})$ for decentralized stochastic nonconvex-strongly-concave problem to search an $\epsilon$-stationary point, which improves the exiting best theoretical results. Moreover, we also prove that our algorithm achieves linear speedup with respect to the number of workers. Our experiments on decentralized settings show the superior performance of our new algorithm.

In this paper, we target to address the problem of compression and acceleration of Convolutional Neural Networks (CNNs). Specifically, we propose a novel structural pruning method to obtain a compact CNN with strong discriminative power. To find such networks, we propose an efficient discrete optimization method to directly optimize channel-wise differentiable discrete gate under resource constraint while freezing all the other model parameters. Although directly optimizing discrete variables is a complex non-smooth, non-convex and NP-hard problem, our optimization method can circumvent these difficulties by using the straight-through estimator. Thus, our method is able to ensure that the sub-network discovered within the training process reflects the true sub-network. We further extend the discrete gate to its stochastic version in order to thoroughly explore the potential sub-networks. Unlike many previous methods requiring per-layer hyper-parameters, we only require one hyper-parameter to control FLOPs budget. Moreover, our method is globally discrimination-aware due to the discrete setting. The experimental results on CIFAR-10 and ImageNet show that our method is competitive with state-of-the-art methods.

In the paper, we propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning, which use adaptive learning rates and do not require any large batches. Specifically, we propose a fast important-sampling momentum-based policy gradient (IS-MBPG) method based on a new momentum-based variance reduced technique and the importance sampling technique. We also propose a fast Hessian-aided momentum-based policy gradient (HA-MBPG) method based on the momentum-based variance reduced technique and the Hessian-aided technique. Moreover, we prove that both the IS-MBPG and HA-MBPG methods reach the best known sample complexity of $O(\epsilon^{-3})$ for finding an $\epsilon$-stationary point of the nonconcave performance function, which only require one trajectory at each iteration. In particular, we present a non-adaptive version of IS-MBPG method, i.e., IS-MBPG*, which also reaches the best known sample complexity of $O(\epsilon^{-3})$ without any large batches. In the experiments, we apply four benchmark tasks to demonstrate the effectiveness of our algorithms.

In the paper, we propose a class of accelerated stochastic gradient-free and projection-free (a.k.a., zeroth-order Frank-Wolfe) methods to solve the constrained stochastic and finite-sum nonconvex optimization. Specifically, we propose an accelerated stochastic zeroth-order Frank-Wolfe (Acc-SZOFW) method based on the variance reduced technique of SPIDER/SpiderBoost and a novel momentum accelerated technique. Moreover, under some mild conditions, we prove that the Acc-SZOFW has the function query complexity of $O(d\sqrt{n}\epsilon^{-2})$ for finding an $\epsilon$-stationary point in the finite-sum problem, which improves the exiting best result by a factor of $O(\sqrt{n}\epsilon^{-2})$, and has the function query complexity of $O(d\epsilon^{-3})$ in the stochastic problem, which improves the exiting best result by a factor of $O(\epsilon^{-1})$. To relax the large batches required in the Acc-SZOFW, we further propose a novel accelerated stochastic zeroth-order Frank-Wolfe (Acc-SZOFW*) based on a new variance reduced technique of STORM, which still reaches the function query complexity of $O(d\epsilon^{-3})$ in the stochastic problem without relying on any large batches. In particular, we present an accelerated framework of the Frank-Wolfe methods based on the proposed momentum accelerated technique. The extensive experimental results on black-box adversarial attack and robust black-box classification demonstrate the efficiency of our algorithms.

Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems such as the bandit model and the black-box learning problem, proximal gradient method could fail because the explicit gradients of these problems are difficult or infeasible to obtain. The gradient-free (zeroth-order) method can address these problems because only the objective function values are required in the optimization. Recently, the first zeroth-order proximal stochastic algorithm was proposed to solve the nonconvex nonsmooth problems. However, its convergence rate is O(1/√T) for the nonconvex problems, which is significantly slower than the best convergence rate O(T1) of the zerothorder stochastic algorithm, where T is the iteration number. To fill this gap, in the paper, we propose a class of faster zeroth-order proximal stochastic methods with the variance reduction techniques of SVRG and SAGA, which are denoted as ZO-ProxSVRG and ZO-ProxSAGA, respectively. In theoretical analysis, we address the main challenge that an unbiased estimate of the true gradient does not hold in the zerothorder case, which was required in previous theoretical analysis of both SVRG and SAGA. Moreover, we prove that both ZO-ProxSVRG and ZO-ProxSAGA algorithms have O(T1) convergence rates. Finally, the experimental results verify that our algorithms have a faster convergence rate than the existing zeroth-order proximal stochastic algorithm.

In this paper, we propose a faster stochastic alternating direction method of multipliers (ADMM) for nonconvex optimization by using a new stochastic path-integrated differential estimator (SPIDER), called as SPIDER-ADMM. Moreover, we prove that the SPIDER-ADMM achieves a record-breaking incremental first-order oracle (IFO) complexity for finding an $\epsilon$-approximate solution. As one of major contribution of this paper, we provide a new theoretical analysis framework for nonconvex stochastic ADMM methods with providing the optimal IFO complexity. Based on this new analysis framework, we study the unsolved optimal IFO complexity of the existing non-convex SVRG-ADMM and SAGA-ADMM methods, and prove their the optimal IFO complexity. Thus, the SPIDER-ADMM improves the existing stochastic ADMM methods. Moreover, we extend SPIDER-ADMM to the online setting, and propose a faster online SPIDER-ADMM. Our theoretical analysis also derives the IFO complexity of the online SPIDER-ADMM. Finally, the experimental results on benchmark datasets validate that the proposed algorithms have faster convergence rate than the existing ADMM algorithms for nonconvex optimization.

Alternating direction method of multipliers (ADMM) is a popular optimization tool for the composite and constrained problems in machine learning. However, in many machine learning problems such as black-box learning and bandit feedback, ADMM could fail because the explicit gradients of these problems are difficult or even infeasible to obtain. Zeroth-order (gradient-free) methods can effectively solve these problems due to that the objective function values are only required in the optimization. Recently, though there exist a few zeroth-order ADMM methods, they build on the convexity of objective function. Clearly, these existing zeroth-order methods are limited in many applications. In the paper, thus, we propose a class of fast zeroth-order stochastic ADMM methods (\emph{i.e.}, ZO-SVRG-ADMM and ZO-SAGA-ADMM) for solving nonconvex problems with multiple nonsmooth penalties, based on the coordinate smoothing gradient estimator. Moreover, we prove that both the ZO-SVRG-ADMM and ZO-SAGA-ADMM have convergence rate of $O(1/T)$, where $T$ denotes the number of iterations. In particular, our methods not only reach the best convergence rate of $O(1/T)$ for the nonconvex optimization, but also are able to effectively solve many complex machine learning problems with multiple regularized penalties and constraints. Finally, we conduct the experiments of black-box binary classification and structured adversarial attack on black-box deep neural network to validate the efficiency of our algorithms.

In the paper, we propose a class of dynamic conditional Gaussian graphical models (DCGGMs) based on a set of nonidentical distribution observations, which changes smoothly with time or condition. Specifically, the DCGGMs model the dynamic output network influenced by conditioning input variables, which are encoded by a set of varying parameters. Moreover, we propose a joint smooth graphical Lasso to estimate the DCGGMs, which combines kernel smoother with sparse group Lasso penalty. At the same time, we design an efficient accelerated proximal gradient algorithm to solve this estimator. Theoretically, we establish the asymptotic properties of our model on consistency and sparsistency under the high-dimensional settings. In particular, we highlight a class of consistency theory for dynamic graphical models, in which the sample size can be seen as n4/5for estimating a local graphical model when the bandwidth parameter h of kernel smoother is chosen as h = n-1/5for describing the dynamic. Finally, the extensive numerical experiments on both synthetic and real datasets are provided to support the effectiveness of the proposed method.

In this paper, we propose a joint conditional graphical Lasso to learn multiple conditional Gaussian graphical models, also known as Gaussian conditional random fields, with some similar structures. Our model builds on the maximum likelihood method with the convex sparse group Lasso penalty. Moreover, our model is able to model multiple multivariate linear regressions with unknown noise covariances via a convex formulation. In addition, we develop an efficient approximated Newton's method for optimizing our model. Theoretically, we establish the asymptotic properties of our model on consistency and sparsistency under the high-dimensional settings. Finally, extensive numerical results on simulations and real data sets demonstrate that our method outperforms the compared methods on structure recovery and structured output prediction. To the best of our knowledge, the joint learning of multiple multivariate regressions with unknown covariance is first studied.

We consider joint learning of multiple sparse matrix Gaussian graphical models and propose the joint matrix graphical Lasso to discover the conditional independence structures among rows (columns) in the matrix variable under distinct conditions. The proposed approach borrows strength across the different graphical models and is based on the maximum likelihood with penalized row and column precision matrices, respectively. In particular, our model is more parsimonious and flexible than the joint vector graphical models. Furthermore, we establish the asymptotic properties of our model on consistency and sparsistency. And the asymptotic analysis shows that our model enjoys a better convergence rate than the joint vector graphical models. Extensive simulation experiments demonstrate that our methods outperform state-of-the-art methods in identifying graphical structures and estimating precision matrices. Moreover, the effectiveness of our methods is also illustrated via a real data set analysis. Sparsistency is shorthand for consistency of the sparsity pattern of the parameters.