Playing table tennis with a human player is a challenging robotic task due to its dynamic nature. Despite a number of researches being devoted to developing robotic table tennis systems, most of the works have demanding hardware requirements and ignore safety measures when generating the swing stoke. To address these issues, we propose a safe motion planning framework that fully pushes the robotic hardware performance limits to play table tennis. In particular, we propose a pipeline to generate manipulator joint trajectories with environmental safety constraints and scale the trajectories to satisfy joint movement limitations. We use three different agents to validate the planning algorithm with our handmade robot platform in both simulation and real-world environments.

The well-known Gumbel-Max Trick for sampling elements from a categorical distribution (or more generally a non-negative vector) and its variants have been widely used in areas such as machine learning and information retrieval. To sample a random element$i$in proportion to its positive weight$v_{i}$, the Gumbel-Max Trick first computes a Gumbel random variable$g_{i}$for each positive weight element$i$, and then samples the element$i$with the largest value of$g_{i}+\ln v_{i}$. Recently, applications including similarity estimation and weighted cardinality estimation require to generate$k$independent Gumbel-Max variables from high dimensional vectors. However, it is computationally expensive for a large$k$(e.g., hundreds or even thousands) when using the traditional Gumbel-Max Trick. To solve this problem, we propose a novel algorithm,FastGM, which reduces the time complexity from$O(kn^+)$to$O(k \ln k + n^+)$, where$n^+$is the number of positive elements in the vector of interest. FastGM stops the procedure of Gumbel random variables computing for many elements, especially for those with small weights. We perform experiments on a variety of real-world datasets and the experimental results demonstrate that FastGM is orders of magnitude faster than state-of-the-art methods without sacrificing accuracy or incurring additional expenses.

The REINFORCE algorithm \cite{williams1992simple} is popular in policy gradient (PG) for solving reinforcement learning (RL) problems. Meanwhile, the theoretical form of PG is from \cite{sutton1999policy}. Although both formulae prescribe PG, their precise connections are not yet illustrated. Recently, \citeauthor{nota2020policy} (\citeyear{nota2020policy}) have found that the ambiguity causes implementation errors. Motivated by the ambiguity and implementation incorrectness, we study PG from a perturbation perspective. In particular, we derive PG in a unified framework, precisely clarify the relation between PG implementation and theory, and echos back the findings by \citeauthor{nota2020policy}. Diving into factors contributing to empirical successes of the existing erroneous implementations, we find that small approximation error and the experience replay mechanism play critical roles.

Deep anomaly detection has become popular for its capability of handling complex data. However, training a deep detector is fragile to data contamination due to overfitting. In this work, we study the performance of the anomaly detectors under data contamination and construct a data-efficient countermeasure against data contamination. We show that training a deep anomaly detector induces an implicit kernel machine. We then derive an information-theoretic bound of performance degradation with respect to the data contamination ratio. To mitigate the degradation, we propose a contradicting training approach. Apart from learning normality on the contaminated dataset, our approach discourages learning an additional small auxiliary dataset of labeled anomalies. Our approach is much more affordable than constructing a completely clean training dataset. Experiments on public datasets show that our approach significantly improves anomaly detection in the presence of contamination and outperforms some recently proposed detectors.

Time-series is ubiquitous across applications, such as transportation, finance and healthcare. Time-series is often influenced by external factors, especially in the form of asynchronous events, making forecasting difficult. However, existing models are mainly designated for either synchronous time-series or asynchronous event sequence, and can hardly provide a synthetic way to capture the relation between them. We propose Variational Synergetic Multi-Horizon Network (VSMHN), a novel deep conditional generative model. To learn complex correlations across heterogeneous sequences, a tailored encoder is devised to combine the advances in deep point processes models and variational recurrent neural networks. In addition, an aligned time coding and an auxiliary transition scheme are carefully devised for batched training on unaligned sequences. Our model can be trained effectively using stochastic variational inference and generates probabilistic predictions with Monte-Carlo simulation. Furthermore, our model produces accurate, sharp and more realistic probabilistic forecasts. We also show that modeling asynchronous event sequences is crucial for multi-horizon time-series forecasting.

Flexible operation and maintenance (O&M) is critical for telecommunication (telecom) service providers due to the ever-growing communication networks. Currently, most O&M operations still rely on rule-based strategies, which only cover limited scenarios and are costly to extend for novel applications as expert knowledge is intensively involved. To build a more flexible O&M system, we propose a language model to extract useful representations out of massive network signaling messages and use the representations to perform downstream O&M tasks. Given that a vanilla language model is not directly applicable for the structured signaling messages, we develop an expert-knowledge-inspired statistical approach to preprocess the messages and a hierarchical network architecture to extract message relations among different levels. Moreover, network messages in the real world are often contaminated, which can mislead the language model to learn incorrect message patterns. To mitigate data contamination, we propose a reverse training method that prevents the language model from learning the contaminated data. We collected hundreds of thousands of signaling message flows to train the proposed signaling language model and applied the trained model to O&M tasks. Offline experiments show that our proposed language model captures various signaling protocols and the extracted representations enable us to achieve expert-level performance in network anomaly detection and service recognition. Our language model has been deployed online at Huawei and significantly improved O&M efficiency.

The restless multi-armed bandit (RMAB) problem is a generalization of the multi-armed bandit with non-stationary rewards. Its optimal solution is intractable due to exponentially large state and action spaces with respect to the number of arms. Existing approximation approaches, e.g., Whittle's index policy, have difficulty in capturing either temporal or spatial factors such as impacts from other arms. We propose considering both factors using the attention mechanism, which has achieved great success in deep learning. Our state-aware value function approximation solution comprises an attention-based value function approximator and a Bellman equation solver. The attention-based coordination module capture both spatial and temporal factors for arm coordination. The Bellman equation solver utilizes the decoupling structure of RMABs to acquire solutions with significantly reduced computation overheads. In particular, the time complexity of our approximation is linear in the number of arms. Finally, we illustrate the effectiveness and investigate the properties of our proposed method with numerical experiments.

Estimating set similarity and detecting highly similar sets are fundamental problems in areas such as databases and machine learning. MinHash is a well-known technique for approximating Jaccard similarity of sets and has been successfully used for many applications. Its two compressed versions, b-bit MinHash and Odd Sketch, can significantly reduce the memory usage of the MinHash, especially for estimating high similarities (i.e., similarities around 1). Although MinHash can be applied to static sets as well as streaming sets, of which elements are given in a streaming fashion, unfortunately, b-bit MinHash and Odd Sketch fail to deal with streaming data. To solve this problem, we previously designed a memory-efficient sketch method, MaxLogHash, to accurately estimate Jaccard similarities in streaming sets. Compared with MinHash, our method uses smaller sized registers (each register consists of less than 7 bits) to build a compact sketch for each set. In this paper, we further develop a faster method, MaxLogOPH++. Compared with MaxLogHash, MaxLogOPH++ reduces the time complexity for updating each coming element from O(k) with a small additional memory. We conduct experiments on a variety of datasets, and experimental results demonstrate the efficiency and effectiveness of our methods.

Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the massive amount of parameters in the network leads to expensive computational cost and low learning efficiency. The problem can be alleviated slightly by introducing one more narrow hidden layer to the network, but the sample size required to achieve a certain training error is still substantial. To address this challenge, we rearrange the weight matrices of a linear autoregressive network into a tensor form, and then make use of Tucker decomposition to represent low-rank structures. This leads to a novel compact autoregressive network, called Tucker AutoRegressive (TAR) net. Interestingly, the TAR net can be applied to sequences with long-range dependence since the dimension along the sequential order is reduced. Theoretical studies show that the TAR net improves the learning efficiency, and requires much fewer samples for model training. Experiments on synthetic and real-world datasets demonstrate the promising performance of the proposed compact network.

The LSTM network was proposed to overcome the difficulty in learning long-term dependence, and has made significant advancements in applications. With its success and drawbacks in mind, this paper raises the question - do RNN and LSTM have long memory? We answer it partially by proving that RNN and LSTM do not have long memory from a statistical perspective. A new definition for long memory networks is further introduced, and it requires the model weights to decay at a polynomial rate. To verify our theory, we convert RNN and LSTM into long memory networks by making a minimal modification, and their superiority is illustrated in modeling long-term dependence of various datasets.

The well-known Gumbel-Max Trick for sampling elements from a categorical distribution (or more generally a nonnegative vector) and its variants have been widely used in areas such as machine learning and information retrieval. To sample a random element i (or a Gumbel-Max variable i) in proportion to its positive weight vi, the Gumbel-Max Trick first computes a Gumbel random variable gi for each positive weight element i, and then samples the element i with the largest value of gi + ln vi. Recently, applications including similarity estimation and graph embedding require to generate k independent Gumbel-Max variables from high dimensional vectors. However, it is computationally expensive for a large k (e.g., hundreds or even thousands) when using the traditional Gumbel-Max Trick. To solve this problem, we propose a novel algorithm, FastGM, that reduces the time complexity from O(kn+) to O(kln k + n+), where n+ is the number of positive elements in the vector of interest. Instead of computing k independent Gumbel random variables directly, we find that there exists a technique to generate these variables in descending order. Using this technique, our method FastGM computes variables gi + ln vi for all positive elements i in descending order. As a result, FastGM significantly reduces the computation time because we can stop the procedure of Gumbel random variables computing for many elements especially for those with small weights. Experiments on a variety of real-world datasets show that FastGM is orders of magnitude faster than state-of-the-art methods without sacrificing accuracy and incurring additional expenses.

Many problems in science and engineering can be reduced to the recovery of an unknown large matrix from a small number of random linear measurements. Matrix factorization arguably is the most popular approach for low-rank matrix recovery. Many methods have been proposed using different loss functions, for example the most widely used L2loss, more robust choices such as L1and Huber loss, quantile and expectile loss for skewed data. All of them can be unified into the framework of M-estimation. In this paper, we present a general framework of low-rank matrix factorization based on M-estimation in statistics. The framework mainly involves two steps: firstly we apply Nesterov's smoothing technique to obtain an optimal smooth approximation for non-smooth loss function, such as L1and quantile loss; secondly we exploit an alternative updating scheme along with Nesterov's momentum method at each step to minimize the smoothed loss function. Strong theoretical convergence guarantee has been developed for the general framework, and extensive numerical experiments have been conducted to illustrate the performance of proposed algorithm.

Since the sure independence screening (SIS) method by Fan and Lv, many different variable screening methods have been proposed based on different measures under different models. However, most of these methods are designed for specific models. In practice, we often have very little information about the data generating process and different methods can result in very different sets of features. The heterogeneity presented here motivates us to combine various screening methods simultaneously. In this paper, we introduce a general ensemble-based framework to efficiently combine results from multiple variable screening methods. The consistency and sure screening property of proposed framework has been established. Extensive simulation studies confirm our intuition that the proposed ensemble-based method is more robust against model specification than using single variable screening method. The proposed ensemble-based method is used to predict attention deficit hyperactivity disorder (ADHD) status using brain function connectivity (FC).

Deep learning well demonstrates its potential in learning latent feature representations. Recent years have witnessed an increasing enthusiasm for regularizing deep neural networks by incorporating various side information, such as user-provided labels or pairwise constraints. However, the effectiveness and parameter sensitivity of such algorithms have been major obstacles for putting them into practice. The major contribution of our work is the exposition of a novel supervised deep learning algorithm, which distinguishes from two unique traits. First, it regularizes the network construction by utilizing similarity or dissimilarity constraints between data pairs, rather than sample-specific annotations. Such kind of side information is more flexible and greatly mitigates the workload of annotators. Secondly, unlike prior works, our proposed algorithm decouples the supervision information and intrinsic data structure. We design two heterogeneous networks, each of which encodes either supervision or unsupervised data structure respectively. Specifically, we term the supervision-oriented network as "auxiliary network" since it is principally used for facilitating the parameter learning of the other one and will be removed when handling out-of-sample data. The two networks are complementary to each other and bridged by enforcing the correlation of their parameters. We name the proposed algorithm SUpervision-Guided AutoencodeR (SUGAR). Comparing prior works on unsupervised deep networks and supervised learning, SUGAR better balances numerical tractability and the flexible utilization of supervision information. The classification performance on MNIST digits and eight benchmark datasets demonstrates that SUGAR can effectively improve the performance by using the auxiliary networks, on both shallow and deep architectures. Particularly, when multiple SUGARs are stacked, the performance is significantly boosted. On the selected benchmarks, ours achieve up to 11.35% relative accuracy improvement compared to the state-of-the-art models.

The expectation-maximization (EM) algorithm has been widely applied to the estimation of gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation.

Tracer kinetic modeling with dynamic positron emission tomography (PET) requires a plasma time-activity curve (PTAC) as an input function. Several image-derived input function (IDIF) methods that rely on drawing the region of interest (ROI) in large vascular structures have been proposed to overcome the problems caused by the invasive approach for obtaining the PTAC, especially for small-animal studies. However, the manual placement of ROIs for estimating IDIF is subjective and labor-intensive, making it an undesirable and unreliable process. In this paper, we propose a novel hybrid clustering method (HCM) that objectively delineates ROIs in dynamic PET images for the estimation of IDIFs, and demonstrate its application to the mouse PET studies acquired with [ (18)F]Fluoro-2-deoxy-2-D-glucose (FDG). We begin our HCM using k-means clustering for background removal. We then model the time-activity curves using polynomial regression mixture models in curve clustering for heart structure detection. The hierarchical clustering is finally applied for ROI refinements. The HCM achieved accurate ROI delineation in both computer simulations and experimental mouse studies. In the mouse studies, the predicted IDIF had a high correlation with the gold standard, the PTAC derived from the invasive blood samples. The results indicate that the proposed HCM has a great potential in ROI delineation for automatic estimation of IDIF in dynamic FDG-PET studies.