This paper studies stochastic control problems with the action space taken to be the space of measures, regularized by the relative entropy. We identify suitable metric space on which we construct a gradient flow for the measure-valued control process along which the cost functional is guaranteed to decrease. It is shown that any invariant measure of this gradient flow satisfies the Pontryagin optimality principle. If the problem we work with is sufficiently convex, the gradient flow converges exponentially fast. Furthermore, the optimal measure-valued control admits Bayesian interpretation which means that one can incorporate prior knowledge when solving stochastic control problem. This work is motivated by a desire to extend the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used in the reinforcement learning community to solve control problems.

Federated learning (FL), which has gained increasing attention recently, enables distributed devices to train a common machine learning (ML) model for intelligent inference cooperatively without data sharing. However, problems in practical networks, such as non-independent-and-identically-distributed (non-iid) raw data and limited bandwidth, give rise to slow and unstable convergence of the FL training process. To address these issues, we propose a new FL method that can significantly mitigate statistical heterogeneity through the depersonalization mechanism. Particularly, we decouple the global and local optimization objectives by alternating stochastic gradient descent, thus reducing the accumulated variance in local update phases to accelerate the FL convergence. Then we analyze the proposed method detailedly to show the proposed method converging at a sublinear speed in the general non-convex setting. Finally, numerical results are conducted with experiments on public datasets to verify the effectiveness of our proposed method.

Sampling from a high-dimensional distribution is a fundamental task in statistics, engineering, and the sciences. A canonical approach is the Langevin Algorithm, i.e., the Markov chain for the discretized Langevin Diffusion. This is the sampling analog of Gradient Descent. Despite being studied for several decades in multiple communities, tight mixing bounds for this algorithm remain unresolved even in the seemingly simple setting of log-concave distributions over a bounded domain. This paper completely characterizes the mixing time of the Langevin Algorithm to its stationary distribution in this setting (and others). This mixing result can be combined with any bound on the discretization bias in order to sample from the stationary distribution of the continuous Langevin Diffusion. In this way, we disentangle the study of the mixing and bias of the Langevin Algorithm. Our key insight is to introduce a technique from the differential privacy literature to the sampling literature. This technique, called Privacy Amplification by Iteration, uses as a potential a variant of R\'enyi divergence that is made geometrically aware via Optimal Transport smoothing. This gives a short, simple proof of optimal mixing bounds and has several additional appealing properties. First, our approach removes all unnecessary assumptions required by other sampling analyses. Second, our approach unifies many settings: it extends unchanged if the Langevin Algorithm uses projections, stochastic mini-batch gradients, or strongly convex potentials (whereby our mixing time improves exponentially). Third, our approach exploits convexity only through the contractivity of a gradient step -- reminiscent of how convexity is used in textbook proofs of Gradient Descent. In this way, we offer a new approach towards further unifying the analyses of optimization and sampling algorithms.

We propose Adaptive Compressed Gradient Descent (AdaCGD) - a novel optimization algorithm for communication-efficient training of supervised machine learning models with adaptive compression level. Our approach is inspired by the recently proposed three point compressor (3PC) framework of Richtarik et al. (2022), which includes error feedback (EF21), lazily aggregated gradient (LAG), and their combination as special cases, and offers the current state-of-the-art rates for these methods under weak assumptions. While the above mechanisms offer a fixed compression level, or adapt between two extremes only, our proposal is to perform a much finer adaptation. In particular, we allow the user to choose any number of arbitrarily chosen contractive compression mechanisms, such as Top-K sparsification with a user-defined selection of sparsification levels K, or quantization with a user-defined selection of quantization levels, or their combination. AdaCGD chooses the appropriate compressor and compression level adaptively during the optimization process. Besides i) proposing a theoretically-grounded multi-adaptive communication compression mechanism, we further ii) extend the 3PC framework to bidirectional compression, i.e., we allow the server to compress as well, and iii) provide sharp convergence bounds in the strongly convex, convex and nonconvex settings. The convex regime results are new even for several key special cases of our general mechanism, including 3PC and EF21. In all regimes, our rates are superior compared to all existing adaptive compression methods.

In non-private stochastic convex optimization, stochastic gradient methods converge much faster on interpolation problems -- problems where there exists a solution that simultaneously minimizes all of the sample losses -- than on non-interpolating ones; we show that generally similar improvements are impossible in the private setting. However, when the functions exhibit quadratic growth around the optimum, we show (near) exponential improvements in the private sample complexity. In particular, we propose an adaptive algorithm that improves the sample complexity to achieve expected error $\alpha$ from $\frac{d}{\varepsilon \sqrt{\alpha}}$ to $\frac{1}{\alpha^\rho} + \frac{d}{\varepsilon} \log\left(\frac{1}{\alpha}\right)$ for any fixed $\rho >0$, while retaining the standard minimax-optimal sample complexity for non-interpolation problems. We prove a lower bound that shows the dimension-dependent term is tight. Furthermore, we provide a superefficiency result which demonstrates the necessity of the polynomial term for adaptive algorithms: any algorithm that has a polylogarithmic sample complexity for interpolation problems cannot achieve the minimax-optimal rates for the family of non-interpolation problems.

The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its success is still missing. This article presents, for orthogonal input vectors, a precise description of the gradient flow dynamics of training one-hidden layer ReLU neural networks for the mean squared error at small initialisation. In this setting, despite non-convexity, we show that the gradient flow converges to zero loss and characterise its implicit bias towards minimum variation norm. Furthermore, some interesting phenomena are highlighted: a quantitative description of the initial alignment phenomenon and a proof that the process follows a specific saddle to saddle dynamics.

Adaptive gradient methods have shown their ability to adjust the stepsizes on the fly in a parameter-agnostic manner, and empirically achieve faster convergence for solving minimization problems. When it comes to nonconvex minimax optimization, however, current convergence analyses of gradient descent ascent (GDA) combined with adaptive stepsizes require careful tuning of hyper-parameters and the knowledge of problem-dependent parameters. Such a discrepancy arises from the primal-dual nature of minimax problems and the necessity of delicate time-scale separation between the primal and dual updates in attaining convergence. In this work, we propose a single-loop adaptive GDA algorithm called TiAda for nonconvex minimax optimization that automatically adapts to the time-scale separation. Our algorithm is fully parameter-agnostic and can achieve near-optimal complexities simultaneously in deterministic and stochastic settings of nonconvex-strongly-concave minimax problems. The effectiveness of the proposed method is further justified numerically for a number of machine learning applications.

We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and the substitution between two close subtokens has a similar effect to the character modification. Our method mainly contains three steps. First, a gradient-based method is adopted to find the most vulnerable words in the sentence. Then we split the selected words into subtokens to replace the origin tokenization result from the transformer tokenizer. Finally, we utilize an adversarial loss to guide the substitution of attachable subtokens in which the Gumbel-softmax trick is introduced to ensure gradient propagation. Meanwhile, we introduce the visual and length constraint in the optimization process to achieve minimum character modifications. Extensive experiments on both sentence-level and token-level tasks demonstrate that our method could outperform the previous attack methods in terms of success rate and edit distance. Furthermore, human evaluation verifies our adversarial examples could preserve their origin labels.

We consider linear prediction with a convex Lipschitz loss, or more generally, stochastic convex optimization problems of generalized linear form, i.e.~where each instantaneous loss is a scalar convex function of a linear function. We show that in this setting, early stopped Gradient Descent (GD), without any explicit regularization or projection, ensures excess error at most $\epsilon$ (compared to the best possible with unit Euclidean norm) with an optimal, up to logarithmic factors, sample complexity of $\tilde{O}(1/\epsilon^2)$ and only $\tilde{O}(1/\epsilon^2)$ iterations. This contrasts with general stochastic convex optimization, where $\Omega(1/\epsilon^4)$ iterations are needed Amir et al. [2021b]. The lower iteration complexity is ensured by leveraging uniform convergence rather than stability. But instead of uniform convergence in a norm ball, which we show can guarantee suboptimal learning using $\Theta(1/\epsilon^4)$ samples, we rely on uniform convergence in a distribution-dependent ball.

Neural network quantum states (NQS), incorporating with variational Monte Carlo (VMC) method, are shown to be a promising way to investigate quantum many-body physics. Whereas vanilla VMC methods perform one gradient update per sample, we introduce a novel objective function with proximal optimization (PO) that enables multiple updates via reusing the mismatched samples. Our VMC-PO method keeps the advantage of the previous importance sampling gradient optimization algorithm [L. Yang, {\it et al}, Phys. Rev. Research {\bf 2}, 012039(R)(2020)] that efficiently uses sampled states. PO mitigates the numerical instabilities during network updates, which is similar to stochastic reconfiguration (SR) methods, but achieves an alternative and simpler implement with lower computational complexity. We investigate the performance of our VMC-PO algorithm for ground-state searching with a 1-dimensional transverse-field Ising model and 2-dimensional Heisenberg antiferromagnet on a square lattice, and demonstrate that the reached ground-state energies are comparable to state-of-the-art results.