English
Related papers

Related papers: Policy Gradient with Second Order Momentum

200 papers

Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such as the curvature can help de-sensitize common…

Machine Learning · Computer Science 2020-11-11 Ricky T. Q. Chen , Dami Choi , Lukas Balles , David Duvenaud , Philipp Hennig

Model predictive control can optimally deal with nonlinear systems under consideration of constraints. The control performance depends on the model accuracy and the prediction horizon. Recent advances propose to use reinforcement learning…

Machine Learning · Computer Science 2024-11-01 Dean Brandner , Sergio Lucia

Recently a majorization method for optimizing partition functions of log-linear models was proposed alongside a novel quadratic variational upper-bound. In the batch setting, it outperformed state-of-the-art first- and second-order…

Machine Learning · Computer Science 2013-09-24 Anna Choromanska , Tony Jebara

Gradient dominance property is a condition weaker than strong convexity, yet sufficiently ensures global convergence even in non-convex optimization. This property finds wide applications in machine learning, reinforcement learning (RL),…

Optimization and Control · Mathematics 2024-05-30 Jiyuan Tan , Chenyu Xue , Chuwen Zhang , Qi Deng , Dongdong Ge , Yinyu Ye

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Machine Learning · Computer Science 2026-05-15 Matias Alvo , Daniel Russo , Yash Kanoria

Gradient based optimization algorithms deployed in Machine Learning (ML) applications are often analyzed and compared by their convergence rates or regret bounds. While these rates and bounds convey valuable information they don't always…

Machine Learning · Computer Science 2025-02-04 Travis E. Gibson , Sawal Acharya , Anjali Parashar , Joseph E. Gaudio , Anurdha M. Annaswamy

In this work, we develop new optimization algorithms that use approximate second-order information combined with the gradient regularization technique to achieve fast global convergence rates for both convex and non-convex objectives. The…

Optimization and Control · Mathematics 2025-06-17 Andrei Semenov , Martin Jaggi , Nikita Doikov

Gradient descent is the primary workhorse for optimizing large-scale problems in machine learning. However, its performance is highly sensitive to the choice of the learning rate. A key limitation of gradient descent is its lack of natural…

Optimization and Control · Mathematics 2025-07-15 Oscar Smee , Fred Roosta , Stephen J. Wright

We present an algorithm for minimizing a sum of functions that combines the computational efficiency of stochastic gradient descent (SGD) with the second order curvature information leveraged by quasi-Newton methods. We unify these…

Machine Learning · Computer Science 2014-12-02 Jascha Sohl-Dickstein , Ben Poole , Surya Ganguli

We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well. This is accomplished by…

Machine Learning · Statistics 2017-03-30 Kai Fan , Ziteng Wang , Jeff Beck , James Kwok , Katherine Heller

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Machine Learning · Computer Science 2022-05-17 Yue Wang , Shaofeng Zou

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update…

Machine Learning · Computer Science 2024-05-02 Mrinmay Sen , A. K. Qin , Gayathri C , Raghu Kishore N , Yen-Wei Chen , Balasubramanian Raman

Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead. This can be viewed as a hardware limitation (imposed by…

Machine Learning · Computer Science 2024-05-24 Kaelan Donatella , Samuel Duffield , Maxwell Aifer , Denis Melanson , Gavin Crooks , Patrick J. Coles

In this paper, we propose new structured second-order methods and structured adaptive-gradient methods obtained by performing natural-gradient descent on structured parameter spaces. Natural-gradient descent is an attractive approach to…

Machine Learning · Statistics 2022-02-22 Wu Lin , Frank Nielsen , Mohammad Emtiyaz Khan , Mark Schmidt

Recently, foundation models such as OpenAI's O1 and O3, along with DeepSeek's R1, have demonstrated strong reasoning capacities and problem-solving skills acquired through large-scale reinforcement learning (RL), with wide applications in…

Machine Learning · Computer Science 2025-04-29 Tianbing Xu

Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the…

Optimization and Control · Mathematics 2016-02-29 Farbod Roosta-Khorasani , Michael W. Mahoney

We present a new accelerated stochastic second-order method that is robust to both gradient and Hessian inexactness, which occurs typically in machine learning. We establish theoretical lower bounds and prove that our algorithm achieves…

Optimization and Control · Mathematics 2024-05-28 Artem Agafonov , Dmitry Kamzolov , Alexander Gasnikov , Ali Kavis , Kimon Antonakopoulos , Volkan Cevher , Martin Takáč

We combine two advanced ideas widely used in optimization for machine learning: shuffling strategy and momentum technique to develop a novel shuffling gradient-based method with momentum, coined Shuffling Momentum Gradient (SMG), for…

Optimization and Control · Mathematics 2021-06-10 Trang H. Tran , Lam M. Nguyen , Quoc Tran-Dinh

We consider minimization of a smooth nonconvex function with inexact oracle access to gradient and Hessian (without assuming access to the function value) to achieve approximate second-order optimality. A novel feature of our method is that…

Optimization and Control · Mathematics 2024-03-27 Shuyao Li , Stephen J. Wright

Recent studies of gradient descent with large step sizes have shown that there is often a regime with an initial increase in the largest eigenvalue of the loss Hessian (progressive sharpening), followed by a stabilization of the eigenvalue…

Machine Learning · Computer Science 2022-10-11 Atish Agarwala , Fabian Pedregosa , Jeffrey Pennington