English
Related papers

Related papers: Delightful Gradients Accelerate Corner Escape

200 papers

Attention mechanisms have revolutionized several domains of artificial intelligence, such as natural language processing and computer vision, by enabling models to selectively focus on relevant parts of the input data. While recent work has…

Machine Learning · Computer Science 2026-02-03 Addison Kristanto Julistiono , Davoud Ataee Tarzanagh , Navid Azizan

We study the problem of policy optimization for infinite-horizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms. We concentrate on the training dynamics…

Machine Learning · Computer Science 2020-10-23 Andrea Agazzi , Jianfeng Lu

This paper studies the convergence properties of a family of Relaxed $\ell$-Minimal Gradient Descent methods for quadratic optimization; the family includes the omnipresent Steepest Descent method, as well as the Minimal Gradient method.…

Optimization and Control · Mathematics 2024-05-01 Liam MacDonald , Rua Murray , Rachael Tappenden

In this paper, we give a sharp analysis for Stochastic Gradient Descent (SGD) and prove that SGD is able to efficiently escape from saddle points and find an $(\epsilon, O(\epsilon^{0.5}))$-approximate second-order stationary point in…

Optimization and Control · Mathematics 2019-06-05 Cong Fang , Zhouchen Lin , Tong Zhang

Projected subgradient descent (PSD) has gained popularity for solving robust Markov decision processes (RMDPs) because it applies to a broader class of uncertainty sets than traditional dynamic programming. Existing work claims that RMDPs…

Optimization and Control · Mathematics 2026-04-24 Toshinori Kitamura , Arnob Ghosh , Alex Ayoub , Thang D. Chu , Csaba Szepesvári

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

Machine Learning · Statistics 2022-10-18 Jiayuan Ye , Reza Shokri

We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider log-linear softmax policies with linear function…

Machine Learning · Computer Science 2026-05-26 Ziyue Chen , David Šiška , Lukasz Szpruch

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

We study stochastic convex optimization (SCO) with heavy-tailed gradients under pure $\varepsilon$-differential privacy (DP). Instead of assuming a bound on the worst-case Lipschitz parameter of the loss, we assume only a bounded $k$-th…

Machine Learning · Computer Science 2026-05-06 Andrew Lowy

We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit). Under this type of feedback, the agent observes only the total loss incurred over the entire…

Machine Learning · Computer Science 2025-02-07 Tal Lancewicki , Yishay Mansour

Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models, from regression to neural networks. Given the recent practical focus on…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-06-25 Dan Alistarh , Christopher De Sa , Nikola Konstantinov

Last-iterate convergence of learning dynamics in games has attracted significant recent attention. In two-player zero-sum games with bandit feedback, where only the loss of the selected action pair is observed, Fiegel et al. (2025) show a…

Machine Learning · Computer Science 2026-05-12 Soumita Hait , Ping Li , Haipeng Luo , Mengxiao Zhang

This paper shows that the implicit bias of gradient descent on linearly separable data is exactly characterized by the optimal solution of a dual optimization problem given by a smoothed margin, even for general losses. This is in contrast…

Machine Learning · Computer Science 2020-11-13 Ziwei Ji , Matus Telgarsky

Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization. A number of works have uncovered that gradient noise plays a critical role in the ability of gradient descent…

Optimization and Control · Mathematics 2019-08-21 Stefan Vlaski , Ali H. Sayed

This paper presents a constrained policy gradient algorithm. We introduce constraints for safe learning with the following steps. First, learning is slowed down (lazy learning) so that the episodic policy change can be computed with the…

Machine Learning · Computer Science 2022-01-24 Balázs Varga , Balázs Kulcsár , Morteza Haghir Chehreghani

The non-asymptotic analysis of Stochastic Gradient Descent (SGD) typically yields bounds that decompose into a bias term and a variance term. In this work, we focus on the bias component and study the extent to which SGD can match the…

Optimization and Control · Mathematics 2026-02-02 Daniel Cortild , Lucas Ketels , Juan Peypouquet , Guillaume Garrigos

Gradient Descent Ascent (GDA) methods for min-max optimization problems typically produce oscillatory behavior that can lead to instability, e.g., in bilinear settings. To address this problem, we introduce a dissipation term into the GDA…

Optimization and Control · Mathematics 2024-03-15 Tianqi Zheng , Nicolas Loizou , Pengcheng You , Enrique Mallada

A rich body of prior work has highlighted the existence of communication bottlenecks in synchronous data-parallel training. To alleviate these bottlenecks, a long line of recent work proposes gradient and model compression methods. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-07-01 Saurabh Agarwal , Hongyi Wang , Shivaram Venkataraman , Dimitris Papailiopoulos

$L_0$-smoothness, which has been pivotal to advancing decentralized optimization theory, is often fairly restrictive for modern tasks like deep learning. The recent advent of relaxed $(L_0,L_1)$-smoothness condition enables improved…

Optimization and Control · Mathematics 2025-08-13 Zhanhong Jiang , Aditya Balu , Soumik Sarkar

In this paper, we consider continuous-time stochastic optimal control problems where the cost is evaluated through a coherent risk measure. We provide an explicit gradient descent-ascent algorithm which applies to problems subject to…

Optimization and Control · Mathematics 2023-06-23 Gabriel Velho , Jean Auriol , Riccardo Bonalli