English
Related papers

Related papers: Geometry and convergence of natural policy gradien…

200 papers

Noisy particle gradient descent (NPGD) is an algorithm to minimize convex functions over the space of measures that include an entropy term. In the many-particle limit, this algorithm is described by a Mean-Field Langevin dynamics - a…

Optimization and Control · Mathematics 2022-08-12 Lénaïc Chizat

In this work, we study $\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs) and introduce a framework called dynamic policy gradient (DynPG). The framework directly integrates dynamic programming with (any) policy…

Machine Learning · Computer Science 2024-11-08 Sara Klein , Xiangyuan Zhang , Tamer Başar , Simon Weissmann , Leif Döring

The proximal stochastic gradient method (PSGD) is one of the state-of-the-art approaches for stochastic composite-type problems. In contrast to its deterministic counterpart, PSGD has been found to have difficulties with the correct…

Optimization and Control · Mathematics 2026-03-04 Junwen Qiu , Li Jiang , Andre Milzarek

Many statistical $M$-estimators are based on convex optimization problems formed by the combination of a data-dependent loss function with a norm-based regularizer. We analyze the convergence rates of projected gradient and composite…

Machine Learning · Statistics 2012-07-26 Alekh Agarwal , Sahand N. Negahban , Martin J. Wainwright

We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP). Despite the popularity of Lagrangian-based policy search methods used in practice, the oscillation…

Optimization and Control · Mathematics 2024-01-18 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Alejandro Ribeiro

Projected gradient methods are widely used for constrained optimization. A key application is for partial differential equations (PDEs), where the objective functional represents physical energy and the linear constraints enforce…

Optimization and Control · Mathematics 2025-06-05 Ruchi Guo , Jun Zou

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…

Machine Learning · Computer Science 2017-05-23 Gergely Neu , Anders Jonsson , Vicenç Gómez

Nonconvex optimization underlies many modern machine learning and control tasks, where saddle points pose the dominant obstacle to reliable convergence in high-dimensional settings. Escaping these saddle points deterministically using…

Optimization and Control · Mathematics 2026-05-13 Liraz Mudrik , Isaac Kaminer , Sean Kragelund , Abram H. Clark

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

Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central…

Optimization and Control · Mathematics 2022-11-01 Runyu Zhang , Jincheng Mei , Bo Dai , Dale Schuurmans , Na Li

Motivated by a constrained minimization problem, it is studied the gradient flows with respect to Hessian Riemannian metrics induced by convex functions of Legendre type. The first result characterizes Hessian Riemannian structures on…

Optimization and Control · Mathematics 2018-11-27 Felipe Alvarez , Jérôme Bolte , Olivier Brahic

A novel optimization approach is proposed for application to policy gradient methods and evolution strategies for reinforcement learning (RL). The procedure uses a computationally efficient Wasserstein natural gradient (WNG) descent that…

Machine Learning · Computer Science 2021-03-19 Ted Moskovitz , Michael Arbel , Ferenc Huszar , Arthur Gretton

Policy gradient (PG) methods are popular and efficient for large-scale reinforcement learning due to their relative stability and incremental nature. In recent years, the empirical success of PG methods has led to the development of a…

Machine Learning · Computer Science 2022-05-24 Yuhao Ding , Junzi Zhang , Javad Lavaei

The Gromov-Wasserstein (GW) distance quantifies discrepancy between metric measure spaces and provides a natural framework for aligning heterogeneous datasets. Alas, as exact computation of GW alignment is NP hard, entropic regularization…

Optimization and Control · Mathematics 2024-01-11 Gabriel Rioux , Ziv Goldfeld , Kengo Kato

Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research. In this paper, we extend previous work on the \textbf{Quadratic Gradient (QG)} and rigorously…

Optimization and Control · Mathematics 2026-04-01 John Chiang

Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead to suboptimal…

Machine Learning · Computer Science 2025-12-09 Yajat Yadav , Patrick Mendoza , Jathin Korrapati

Policy gradients methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a parameterized class of polices. Unfortunately, even for simple control problems solvable by standard dynamic…

Machine Learning · Computer Science 2022-06-22 Jalaj Bhandari , Daniel Russo

Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient method based on the Fisher information matrix of the…

Optimization and Control · Mathematics 2025-02-05 Johannes Müller , Semih Çaycı , Guido Montúfar

In this short note, we give the convergence analysis of the policy in the recent famous policy mirror descent (PMD). We mainly consider the unregularized setting following [11] with generalized Bregman divergence. The difference is that we…

Optimization and Control · Mathematics 2024-06-04 Dachao Lin , Zhihua Zhang

Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically…

Machine Learning · Computer Science 2020-09-22 James Martens
‹ Prev 1 3 4 5 6 7 10 Next ›