English
Related papers

Related papers: Delightful Gradients Accelerate Corner Escape

200 papers

We study the regret of reinforcement learning from offline data generated by a fixed behavior policy in an infinite-horizon discounted Markov decision process (MDP). While existing analyses of common approaches, such as fitted $Q$-iteration…

Machine Learning · Computer Science 2023-07-13 Yichun Hu , Nathan Kallus , Masatoshi Uehara

Without randomization, escaping the saddle points of $f \colon \mathbb{R}^d \to \mathbb{R}$ requires at least $\Omega(d)$ pieces of information about $f$ (values, gradients, Hessian-vector products). With randomization, this can be reduced…

Optimization and Control · Mathematics 2026-03-17 Radu-Alexandru Dragomir , Xiaowen Jiang , Bonan Sun , Nicolas Boumal

While the Transformer architecture has achieved remarkable success across various domains, a thorough theoretical foundation explaining its optimization dynamics is yet to be fully developed. In this study, we aim to bridge this…

Machine Learning · Computer Science 2024-11-13 Bingqing Song , Boran Han , Shuai Zhang , Jie Ding , Mingyi Hong

We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and examine the last iterate convergence. By now, it is known that standard stepsize choices…

Optimization and Control · Mathematics 2026-04-16 Guy Kornowski , Ohad Shamir

Stochastic gradient descent (SGD) with mini-batching is a standard tool in large-scale optimization, yet its theoretical properties under heavy-tailed gradient noise remain largely unexplored. In this paper we study SGD with increasing…

Probability · Mathematics 2026-05-11 Bartosz Glowacki , Rafal Kulik , Philippe Soulier

We provide a detailed study on the implicit bias of gradient descent when optimizing loss functions with strictly monotone tails, such as the logistic loss, over separable datasets. We look at two basic questions: (a) what are the…

In this paper, we establish new convergence results for the quantized distributed gradient descent and suggest a novel strategy of choosing the stepsizes for the high-performance of the algorithm. Under the strongly convexity assumption on…

Optimization and Control · Mathematics 2023-07-03 Woocheol Choi , Myeong-Su Lee

Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety…

Machine Learning · Computer Science 2022-06-20 Matteo Papini , Matteo Pirotta , Marcello Restelli

We study a system with finitely many groups of multi-action bandit processes, each of which is a Markov decision process (MDP) with finite state and action spaces and potentially different transition matrices when taking different actions.…

Optimization and Control · Mathematics 2024-12-05 Jing Fu , Bill Moran , José Niño-Mora

We prove the familiar Lazy Online Gradient Descent algorithm is universal on polytope domains. That means it gets $O(1)$ pseudo-regret against i.i.d opponents, while simultaneously achieving the well-known $O(\sqrt N)$ worst-case regret…

Machine Learning · Computer Science 2022-09-01 Daron Anderson , Douglas Leith

Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Recently, Vaswani et al. [2021] introduced a policy gradient method that corresponds to mirror ascent…

Machine Learning · Computer Science 2025-06-02 Reza Asad , Reza Babanezhad , Issam Laradji , Nicolas Le Roux , Sharan Vaswani

This work shows that applying Gradient Descent (GD) with a fixed step size to minimize a (possibly nonconvex) quadratic function is equivalent to running the Power Method (PM) on the gradients. The connection between GD with a fixed step…

Optimization and Control · Mathematics 2022-11-03 Rachael Tappenden , Martin Takáč

Latent categorical variables are frequently found in deep learning architectures. They can model actions in discrete reinforcement-learning environments, represent categories in latent-variable models, or express relations in graph neural…

Machine Learning · Computer Science 2026-05-14 Alessandro Manenti , Cesare Alippi

As sequential learning algorithms are increasingly applied to real life, ensuring data privacy while maintaining their utilities emerges as a timely question. In this context, regret minimisation in stochastic bandits under…

Machine Learning · Statistics 2025-05-12 Achraf Azize , Yulian Wu , Junya Honda , Francesco Orabona , Shinji Ito , Debabrota Basu

Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep reinforcement learning (Deep RL), such optimization methods…

Machine Learning · Computer Science 2018-10-08 Peter Henderson , Joshua Romoff , Joelle Pineau

We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(2024) proposed the first best-of-both-worlds algorithm able…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but…

Machine Learning · Computer Science 2024-05-15 Qiuhao Wang , Chin Pang Ho , Marek Petrik

We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks better align with the attacker's goal: (1) tricking a model to assign higher probability to the target class than to any other class, while…

Machine Learning · Computer Science 2022-06-22 Weiran Lin , Keane Lucas , Lujo Bauer , Michael K. Reiter , Mahmood Sharif

We consider a policy gradient algorithm applied to a finite-arm bandit problem with Bernoulli rewards. We allow learning rates to depend on the current state of the algorithm, rather than use a deterministic time-decreasing learning rate.…

Machine Learning · Computer Science 2021-09-24 Denis Denisov , Neil Walton

Online minimization of an unknown convex function over the interval $[0,1]$ is considered under first-order stochastic bandit feedback, which returns a random realization of the gradient of the function at each query point. Without knowing…

Machine Learning · Statistics 2020-02-21 Sattar Vakili , Sudeep Salgia , Qing Zhao
‹ Prev 1 3 4 5 6 7 10 Next ›