English
Related papers

Related papers: Global linear convergence of entropy-regularized s…

200 papers

This paper investigates the limit behavior of Markov Decision Processes (MDPs) made of independent particles evolving in a common environment, when the number of particles goes to infinity. In the finite horizon case or with a discounted…

Probability · Mathematics 2009-06-10 Nicolas Gast , Bruno Gaujal

In reinforcement learning environments with state-dependent action validity, action masking consistently outperforms penalty-based handling of invalid actions, yet existing theory only shows that masking preserves the policy gradient…

Machine Learning · Computer Science 2026-03-11 Renos Zabounidis , Roy Siegelmann , Mohamad Qadri , Woojun Kim , Simon Stepputtis , Katia P. Sycara

Our work is motivated by a desire to study the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used for non-convex learning tasks such as training of neural networks. The key insight, already…

Probability · Mathematics 2020-12-15 Kaitong Hu , Zhenjie Ren , David Siska , Lukasz Szpruch

This paper considers the problem of minimizing the sum of a smooth function and the Schatten-$p$ norm of the matrix. Our contribution involves proposing accelerated iteratively reweighted nuclear norm methods designed for solving the…

Optimization and Control · Mathematics 2024-06-27 Hao Wang , Ye Wang , Xiangyu Yang

Decentralized optimization has become a fundamental tool for large-scale learning systems; however, most existing methods rely on the classical Lipschitz smoothness assumption, which is often violated in problems with rapidly varying…

Optimization and Control · Mathematics 2026-01-08 Yanan Bo , Yongqiang Wang

Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose…

Machine Learning · Computer Science 2020-10-19 Jingbin Liu , Xinyang Gu , Shuai Liu

Low-rank modeling has many important applications in computer vision and machine learning. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has demonstrated better empirical…

Machine Learning · Computer Science 2018-07-25 Quanming Yao , James T. Kwok , Taifeng Wang , Tie-Yan Liu

The $Q$-function is a central quantity in many Reinforcement Learning (RL) algorithms for which RL agents behave following a (soft)-greedy policy w.r.t. to $Q$. It is a powerful tool that allows action selection without a model of the…

Machine Learning · Computer Science 2022-06-01 Nino Vieillard , Marcin Andrychowicz , Anton Raichuk , Olivier Pietquin , Matthieu Geist

Cumulative entropy regularization introduces a regulatory signal to the reinforcement learning (RL) problem that encourages policies with high-entropy actions, which is equivalent to enforcing small deviations from a uniform reference…

Machine Learning · Computer Science 2019-09-16 Felix Leibfried , Jordi Grau-Moya

We consider infinite-horizon $\gamma$-discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy. We consider the algorithm Value Iteration and the sequence of policies $\pi_1,...,\pi_k$ it…

Artificial Intelligence · Computer Science 2012-04-02 Bruno Scherrer

Most prior results on differentially private stochastic gradient descent (DP-SGD) are derived under the simplistic assumption of uniform Lipschitzness, i.e., the per-sample gradients are uniformly bounded. We generalize uniform…

Machine Learning · Computer Science 2023-06-07 Rudrajit Das , Satyen Kale , Zheng Xu , Tong Zhang , Sujay Sanghavi

This work establishes a rigorous variational and gradient-based equivalence between the classical K-Means algorithm and differentiable Radial Basis Function (RBF) neural networks with smooth responsibilities. By reparameterizing the K-Means…

Machine Learning · Computer Science 2026-03-06 Felipe de Jesus Felix Arredondo , Alejandro Ucan-Puc , Carlos Astengo Noguez

In this paper we provide a rigorous convergence analysis for the renowned particle swarm optimization method by using tools from stochastic calculus and the analysis of partial differential equations. Based on a time-continuous formulation…

Numerical Analysis · Mathematics 2024-08-05 Hui Huang , Jinniao Qiu , Konstantin Riedl

The goal of this paper is to investigate new and simple convergence analysis of dynamic programming for linear quadratic regulator problem of discrete-time linear time-invariant systems. In particular, bounds on errors are given in terms of…

Optimization and Control · Mathematics 2021-06-18 Donghwan Lee

We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural networks with linear, ReLU or Leaky ReLU activation. We…

Machine Learning · Computer Science 2018-11-01 Simon S. Du , Wei Hu , Jason D. Lee

We consider the general polynomial optimization problem $P: f^*=\min \{f(x)\,:\,x\in K\}$ where $K$ is a compact basic semi-algebraic set. We first show that the standard Lagrangian relaxation yields a lower bound as close as desired to the…

Optimization and Control · Mathematics 2012-10-18 Jean Lasserre

Recently there is a large amount of work devoted to the study of Markov chain stochastic gradient methods (MC-SGMs) which mainly focus on their convergence analysis for solving minimization problems. In this paper, we provide a…

Machine Learning · Statistics 2022-09-19 Puyu Wang , Yunwen Lei , Yiming Ying , Ding-Xuan Zhou

We prove explicit bounds on the exponential rate of convergence for the momentum stochastic gradient descent scheme (MSGD) for arbitrary, fixed hyperparameters (learning rate, friction parameter) and its continuous-in-time counterpart in…

Optimization and Control · Mathematics 2024-11-07 Benjamin Gess , Sebastian Kassing

Despite its nonconvexity, policy optimization for the Linear Quadratic Regulator (LQR) admits a favorable structural property known as gradient dominance, which facilitates linear convergence of policy gradient methods to the globally…

Optimization and Control · Mathematics 2026-02-27 Yuto Watanabe , Yang Zheng

We study when low coordinate degree functions (LCDF) -- linear combinations of functions depending on small subsets of entries of a vector -- can hypothesis test between high-dimensional probability measures. These functions are a…

Statistics Theory · Mathematics 2024-03-13 Dmitriy Kunisky
‹ Prev 1 8 9 10 Next ›