English
Related papers

Related papers: Sample Complexity of Policy Gradient for Log-Growt…

200 papers

Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the…

Machine Learning · Computer Science 2023-06-06 Amirhossein Reisizadeh , Haochuan Li , Subhro Das , Ali Jadbabaie

Gradient clipping is a popular modification to standard (stochastic) gradient descent, at every iteration limiting the gradient norm to a certain value $c >0$. It is widely used for example for stabilizing the training of deep learning…

Machine Learning · Computer Science 2023-11-10 Anastasia Koloskova , Hadrien Hendrikx , Sebastian U. Stich

Stochastic optimization lies at the core of most statistical learning models. The recent great development of stochastic algorithmic tools focused significantly onto proximal gradient iterations, in order to find an efficient approach for…

Machine Learning · Computer Science 2020-03-31 Andrei Patrascu , Ciprian Paduraru , Paul Irofti

Multi-task reinforcement learning (RL) aims to find a single policy that effectively solves multiple tasks at the same time. This paper presents a constrained formulation for multi-task RL where the goal is to maximize the average…

Optimization and Control · Mathematics 2024-05-07 Sihan Zeng , Thinh T. Doan , Justin Romberg

The population recovery problem is a basic problem in noisy unsupervised learning that has attracted significant research attention in recent years [WY12,DRWY12, MS13, BIMP13, LZ15,DST16]. A number of different variants of this problem have…

Data Structures and Algorithms · Computer Science 2017-03-07 Anindya De , Ryan O'Donnell , Rocco Servedio

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

This paper studies an infinite horizon optimal control problem for discrete-time linear system and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. In this general…

Optimization and Control · Mathematics 2024-03-04 Deyue Li

Control of continuous time dynamics with multiplicative noise is a classic topic in stochastic optimal control. This work addresses the problem of designing infinite horizon optimal controls with stability guarantees for \textit{a single…

Optimization and Control · Mathematics 2020-10-02 Kaivalya Bakshi , Evangelos A. Theodorou , Piyush Grover

We study the algorithmic thresholds for principal component analysis of Gaussian $k$-tensors with a planted rank-one spike, via Langevin dynamics and gradient descent. In order to efficiently recover the spike from natural initializations,…

Probability · Mathematics 2023-06-23 Gerard Ben Arous , Reza Gheissari , Aukosh Jagannath

This paper is concerned with the problem of Model Predictive Control and Rolling Horizon Control of discrete-time systems subject to possibly unbounded random noise inputs, while satisfying hard bounds on the control inputs. We use a…

Optimization and Control · Mathematics 2010-09-08 Peter Hokayem , Debasish Chatterjee , John Lygeros

Improving the sample efficiency in reinforcement learning has been a long-standing research problem. In this work, we aim to reduce the sample complexity of existing policy gradient methods. We propose a novel policy gradient algorithm…

Machine Learning · Computer Science 2021-08-03 Pan Xu , Felicia Gao , Quanquan Gu

Second-order information -- such as curvature or data covariance -- is critical for optimisation, diagnostics, and robustness. However, in many modern settings, only the gradients are observable. We show that the gradients alone can reveal…

Machine Learning · Computer Science 2026-04-08 Arash Jamshidi , Katsiaryna Haitsiukevich , Kai Puolamäki

We investigate the problem of best-policy identification in discounted Markov Decision Processes (MDPs) when the learner has access to a generative model. The objective is to devise a learning algorithm returning the best policy as early as…

Machine Learning · Statistics 2021-05-11 Aymen Al Marjani , Alexandre Proutiere

We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponential horizon dependence between lower and upper bounds on the…

Machine Learning · Computer Science 2026-05-14 Amer Essakine , Claire Vernade

We consider a distributionally robust stochastic optimization problem and formulate it as a stochastic two-level composition optimization problem with the use of the mean--semideviation risk measure. In this setting, we consider a single…

Optimization and Control · Mathematics 2023-06-12 Landi Zhu , Mert Gürbüzbalaban , Andrzej Ruszczyński

We analyze the performance of policy gradient in multitask linear quadratic regulation (LQR), where the system and cost parameters differ across tasks. The main goal of multitask LQR is to find a controller with satisfactory performance on…

Systems and Control · Electrical Eng. & Systems 2025-09-24 Charis Stamouli , Leonardo F. Toso , Anastasios Tsiamis , George J. Pappas , James Anderson

This work provides the first finite-time convergence guarantees for linearly constrained stochastic bilevel optimization using only first-order methods, requiring solely gradient information without any Hessian computations or second-order…

Optimization and Control · Mathematics 2025-11-18 Cac Phan , Kai Wang

We derive approximation bounds for learning single neuron models using thresholded gradient descent when both the labels and the covariates are possibly corrupted adversarially. We assume the data follows the model $y =…

Machine Learning · Statistics 2024-09-06 Arvind Rathnashyam , Alex Gittens

The aim of the present paper is to provide necessary and sufficient conditions to maintain a stochastic coupled system, with porous media components and gradient-type noise in a prescribed set of constraints by using internal controls. This…

Analysis of PDEs · Mathematics 2022-02-08 Ioana Ciotir , Dan Goreac , Ionut Munteanu

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg