paper-with-me

홈 › Papers

Stochastic Bias-Reduced Gradient Methods

2021-06-17 · NeurIPS 2021 12 · Hilal Asi, Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford

We develop a new primitive for stochastic optimization: a low-bias, low-cost estimator of the minimizer $x_\star$ of any Lipschitz strongly-convex function. In particular, we use a multilevel Monte-Carlo approach due to Blanchet and Glynn to turn any optimal stochastic gradient method into an estimator of $x_\star$ with bias $\delta$, variance $O(\log(1/\delta))$, and an expected sampling cost of $O(\log(1/\delta))$ stochastic gradient evaluations. As an immediate consequence, we obtain cheap and nearly unbiased gradient estimators for the Moreau-Yoshida envelope of any Lipschitz convex function, allowing us to perform dimension-free randomized smoothing. We demonstrate the potential of our estimator through four applications. First, we develop a method for minimizing the maximum of $N$ functions, improving on recent results and matching a lower bound up to logarithmic factors. Second and third, we recover state-of-the-art rates for projection-efficient and gradient-efficient optimization using simple algorithms with a transparent analysis. Finally, we show that an improved version of our estimator would yield a nearly linear-time, optimal-utility, differentially-private non-smooth stochastic optimization method.

📄 PDF Abstract BibTeX arXiv:2106.09481

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Randomised Splitting Methods and Stochastic Gradient Descent

2025-04-05 · Luke Shaw, Peter A. Whalley

We explore an explicit link between stochastic gradient descent using common batching strategies and splitting methods for ordinary differential equations. From this perspective, we introduce a new minibatching strategy …

Cocoercivity, Smoothness and Bias in Variance-Reduced Stochastic Gradient Methods

2019-03-21 · Martin Morin, Pontus Giselsson

With the purpose of examining biased updates in variance-reduced stochastic gradient methods, we introduce SVAG, a SAG/SAGA-like method with adjustable bias. SVAG is analyzed in a cocoercive root-finding setting, a setti…

Random Reshuffling for Stochastic Gradient Langevin Dynamics

2025-01-27 · Luke Shaw, Peter A. Whalley

We examine the use of different randomisation policies for stochastic gradient algorithms used in sampling, based on first-order (or overdamped) Langevin dynamics, the most popular of which is known as Stochastic Gradien…

Stochastic Variance-Reduced Policy Gradient

2018-06-14 · ICML 2018 7 · Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta 외

In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradien…

Reinforcement Learning

A Stochastic Gradient Method with Biased Estimation for Faster Nonconvex Optimization

2019-05-13 · Jia Bi, Steve R. Gunn

A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient…