Developing algorithms to differentiate between machine-generated texts and human-written texts has garnered substantial attention in recent years. Existing methods in this direction typically concern an offline setting where a dataset containing a mix of real and machine-generated texts is given upfront, and the task is to determine whether each sample in the dataset is from a large language model (LLM) or a human. However, in many practical scenarios, sources such as news websites, social media accounts, and online forums publish content in a streaming fashion. Therefore, in this online scenario, how to quickly and accurately determine whether the source is an LLM with strong statistical guarantees is crucial for these media or platforms to function effectively and prevent the spread of misinformation and other potential misuse of LLMs. To tackle the problem of online detection, we develop an algorithm based on the techniques of sequential hypothesis testing by betting that not only builds upon and complements existing offline detection techniques but also enjoys statistical guarantees, which include a controlled false positive rate and the expected time to correctly identify a source as an LLM. Experiments were conducted to demonstrate the effectiveness of our method.

Heavy Ball (HB) nowadays is one of the most popular momentum methods in non-convex optimization. It has been widely observed that incorporating the Heavy Ball dynamic in gradient-based methods accelerates the training process of modern machine learning models. However, the progress on establishing its theoretical foundation of acceleration is apparently far behind its empirical success. Existing provable acceleration results are of the quadratic or close-to-quadratic functions, as the current techniques of showing HB’s acceleration are limited to the case when the Hessian is fixed. In this work, we develop some new techniques that help show acceleration beyond quadratics, which is achieved by analyzing how the change of the Hessian at two consecutive time points affects the convergence speed. Based on our technical results, a class of Polyak-Lojasiewicz (PL) optimization problems for which provable acceleration can be achieved via HB is identified. Moreover, our analysis demonstrates a benefit of adaptively setting the momentum parameter.

Over-parametrization has become a popular technique in deep learning. It is observed that by over-parametrization, a larger neural network needs a fewer training iterations than a smaller one to achieve a certain level of performance — namely, over-parametrization leads to acceleration in optimization. However, despite that over-parametrization is widely used nowadays, little theory is available to explain the acceleration due to over-parametrization. In this paper, we propose understanding it by studying a simple problem first. Specifically, we consider the setting that there is a single teacher neuron with quadratic activation, where over-parametrization is realized by having multiple student neurons learn the data generated from the teacher neuron. We provably show that over-parametrization helps the iterate generated by gradient descent to enter the neighborhood of a global optimal solution that achieves zero testing error faster.

We propose a new variant of AMSGrad (Reddi et. al., 2018), a popular adaptive gradient based optimization algorithm widely used for training deep neural networks. Our algorithm adds prior knowledge about the sequence of consecutive mini-batch gradients and leverages its underlying structure making the gradients sequentially predictable. By exploiting the predictability process and ideas from optimistic online learning, the proposed algorithm can accelerate the convergence and increase its sample efficiency. After establishing a tighter upper bound under some convexity conditions on the regret, we offer a complimentary view of our algorithm which generalizes to the offline and stochastic nonconvex optimization settings. In the nonconvex case, we establish a non-asymptotic convergence bound independent of the initialization. We illustrate, via numerical experiments, the practical speedup on several deep learning models and benchmark datasets.

Incorporating a so-called “momentum” dynamic in gradient descent methods is widely used in neural net training as it has been broadly observed that, at least empirically, it often leads to significantly faster convergence. At the same time, there are very few theoretical guarantees in the literature to explain this apparent acceleration effect. Even for the classical strongly convex quadratic problems, several existing results only show Polyak’s momentum has an accelerated linear rate asymptotically. In this paper, we first revisit the quadratic problems and show a non-asymptotic accelerated linear rate of Polyak’s momentum. Then, we provably show that Polyak’s momentum achieves acceleration for training a one-layer wide ReLU network and a deep linear network, which are perhaps the two most popular canonical models for studying optimization and deep learning in the literature. Prior works (Du et al. 2019) and (Wu et al. 2019) showed that using vanilla gradient descent, and with an use of over-parameterization, the error decays as $(1- \Theta(\frac{1}{ \kappa’}))^t$ after $t$ iterations, where $\kappa’$ is the condition number of a Gram Matrix. Our result shows that with the appropriate choice of parameters Polyak’s momentum has a rate of $(1-\Theta(\frac{1}{\sqrt{\kappa’}}))^t$. For the deep linear network, prior work (Hu et al. 2020) showed that vanilla gradient descent has a rate of $(1-\Theta(\frac{1}{\kappa}))^t$, where $\kappa$ is the condition number of a data matrix. Our result shows an acceleration rate $(1- \Theta(\frac{1}{\sqrt{\kappa}}))^t$ is achievable by Polyak’s momentum. This work establishes that momentum does indeed speed up neural net training.

We revisit the Frank-Wolfe (FW) optimization under strongly convex constraint sets. We provide a faster convergence rate for FW without line search, showing that a previously overlooked variant of FW is indeed faster than the standard variant. With line search, we show that FW can converge to the global optimum, even for smooth functions that are not convex, but are quasi-convex and locally-Lipschitz. We also show that, for the general case of (smooth) non-convex functions, FW with line search converges with high probability to a stationary point at a rate of O(1/t), as long as the constraint set is strongly convex—one of the fastest convergence rates in non-convex optimization.

We study the problem of online linear optimization with sparsity constraints in the semi-bandit setting. It can be seen as a marriage between two well-known problems: the online linear optimization problem and the combinatorial bandit problem. For this problem, we provide an algorithm which is efficient and achieves a sublinear regret bound. Moreover, we extend our results to two generalized settings, one with delayed feedbacks and one with costs for receiving feedbacks. Finally, we conduct experiments which show the effectiveness of our methods in practice.

We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games. While standard regret bounds would lead to convergence rates on the order of $O(T^{-1/2})$, recent work \citep{RS13,SALS15} has established $O(1/T)$ rates by taking advantage of a particular class of optimistic prediction algorithms. In this work we go further, showing that for a particular class of games one achieves a $O(1/T^2)$ rate, and we show how this applies to the Frank-Wolfe method and recovers a similar bound \citep{D15}. We also show that such no-regret techniques can even achieve a linear rate, $O(\exp(-T))$, for equilibrium computation under additional curvature assumptions.

We consider the problem of minimizing a smooth convex function by reducing the optimization to computing the Nash equilibrium of a particular zero-sum convex-concave game. Zero-sum games can be solved using online learning dynamics, where a classical technique involves simulating two no-regret algorithms that play against each other and, after $T$ rounds, the average iterate is guaranteed to solve the original optimization problem with error decaying as $O(\log T/T)$. In this paper we show that the technique can be enhanced to a rate of $O(1/T^2)$ by extending recent work \cite{RS13,SALS15} that leverages \textit{optimistic learning} to speed up equilibrium computation. The resulting optimization algorithm derived from this analysis coincides \textit{exactly} with the well-known \NA \cite{N83a} method, and indeed the same story allows us to recover several variants of the Nesterov's algorithm via small tweaks. We are also able to establish the accelerated linear rate for a function which is both strongly-convex and smooth. This methodology unifies a number of different iterative optimization methods: we show that the \HB algorithm is precisely the non-optimistic variant of \NA, and recent prior work already established a similar perspective on \FW \cite{AW17,ALLW18}.

We consider the Frank-Wolfe (FW) method for constrained convex optimization, and we show that this classical technique can be interpreted from a different perspective: FW emerges as the computation of an equilibrium (saddle point) of a special convex-concave zero sum game. This saddle-point trick relies on the existence of no-regret online learning to both generate a sequence of iterates but also to provide a proof of convergence through vanishing regret. We show that our stated equivalence has several nice properties, as it exhibits a modularity that gives rise to various old and new algorithms. We explore a few such resulting methods, and provide experimental results to demonstrate correctness and efficiency.

Inspired by recent progress in parallel and distributed optimization, we propose parallel least-squares policy iteration (parallel LSPI) in this paper. LSPI is a policy iteration method to find an optimal policy for MDPs. As solving MDPs with large state space is challenging and time demanding, we propose a parallel variant of LSPI which is capable of leveraging multiple computational resources. Preliminary analysis of our proposed method shows that the sample complexity improved from O(1/√n) towards O(1/√Mn) for each worker, where n is the number of samples and M is the number of workers. Experiments show the advantages of parallel LSPI comparing to the standard non-parallel one.

This paper presents two strategies to speed up the alternating direction method of multipliers (ADMM) for distributed data. In the first method, inspired by stochastic gradient descent, each machine uses only a subset of its data at the first few iterations, speeding up those iterations. A key result is in proving that despite this approximation, our method enjoys the same convergence rate in terms of the number of iterations as the standard ADMM, and hence is faster overall. The second method also follows the idea of sampling a subset of the data to update the model before the communication of each round. It converts an objective to the approximated dual form and performs ADMM on the dual. The method turns out to be a distributed variant of the recently proposed SDCA-ADMM. Yet, compared to the straightforward distributed implementation of SDCA-ADMM, the proposed method enjoys less frequent communication between machines, better memory usage, and lighter computational demand. Experiments demonstrate the effectiveness of our two strategies.

This paper proposes a robust method to estimate the inverse covariance under noisy measurements. The method is based on the estimation of each column in the inverse covariance matrix independently via robust regression, which enables parallelization. Different from previous linear programming based methods that cannot guarantee a positive semi-definite covariance matrix, our method adjusts the learned matrix to satisfy this condition, which further facilitates the tasks of forecasting future values. Experiments on time series prediction and classification under noisy condition demonstrate the effectiveness of the approach.