English
Related papers

Related papers: PAGE-PG: A Simple and Loopless Variance-Reduced Po…

200 papers

Despite the strong theoretical guarantees that variance-reduced finite-sum optimization algorithms enjoy, their applicability remains limited to cases where the memory overhead they introduce (SAG/SAGA), or the periodic full gradient…

Optimization and Control · Mathematics 2021-03-24 Ayoub El Hanchi , David A. Stephens

Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications. This inefficiency stems from two…

Machine Learning · Computer Science 2024-07-01 Yudong Luo , Yangchen Pan , Han Wang , Philip Torr , Pascal Poupart

A major hurdle in machine learning is scalability to massive datasets. Approaches to overcome this hurdle include compression of the data matrix and distributing the computations. \textit{Leverage score sampling} provides a compressed…

Information Theory · Computer Science 2020-09-16 Neophytos Charalambides , Mert Pilanci , Alfred O. Hero

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood

In this paper, we propose a probabilistic optimization method, named probabilistic incremental proximal gradient (PIPG) method, by developing a probabilistic interpretation of the incremental proximal gradient algorithm. We explicitly model…

Optimization and Control · Mathematics 2019-06-20 Ömer Deniz Akyildiz , Émilie Chouzenoux , Víctor Elvira , Joaquín Míguez

Policy gradient (PG) estimators are ineffective in dealing with softmax policies that are sub-optimally saturated, which refers to the situation when the policy concentrates its probability mass on sub-optimal actions. Sub-optimal policy…

Machine Learning · Computer Science 2022-02-25 Shivam Garg , Samuele Tosatto , Yangchen Pan , Martha White , A. Rupam Mahmood

This study presents an importance sampling formulation based on adaptively relaxing parameters from the indicator function and/or the probability density function. The formulation embodies the prevalent mathematical concept of relaxing a…

Applications · Statistics 2024-04-11 Jianhua Xian , Ziqi Wang

The advent of parameter-efficient fine-tuning methods has significantly reduced the computational burden of adapting large-scale pretrained models to diverse downstream tasks. However, existing approaches often struggle to achieve robust…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Haotian Zhang , Liu Liu , Baosheng Yu , Jiayan Qiu , Yanwei Ren , Xianglong Liu

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the…

Machine Learning · Computer Science 2023-04-20 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

Policy Gradient methods that explore directly in parameter space are among the most effective and robust direct policy search methods and have drawn a lot of attention lately. The basic method from this field, Policy Gradients with…

Machine Learning · Computer Science 2013-12-16 Frank Sehnke

Robust Markov Decision Processes (RMDPs) have recently been recognized as a valuable and promising approach to discovering a policy with creditable performance, particularly in the presence of a dynamic environment and estimation errors in…

Optimization and Control · Mathematics 2024-06-04 Zhenwei Lin , Chenyu Xue , Qi Deng , Yinyu Ye

Managing risk in dynamic decision problems is of cardinal importance in many fields such as finance and process control. The most common approach to defining risk is through various variance related criteria such as the Sharpe Ratio or the…

Machine Learning · Computer Science 2012-07-03 Dotan Di Castro , Aviv Tamar , Shie Mannor

Estimating spatial regression models on large, irregularly structured datasets poses significant computational hurdles. While Pairwise Likelihood (PL) methods offer a pathway to simplify these estimations, the efficient selection of…

Methodology · Statistics 2025-07-11 Giuseppe Arbia , Vincenzo Nardelli , Niccolo Salvini

Grammatical Evolution (GE) is one of the most popular Genetic Programming (GP) variants, and it has been used with success in several problem domains. Since the original proposal, many enhancements have been proposed to GE in order to…

Neural and Evolutionary Computing · Computer Science 2021-03-16 Jessica Mégane , Nuno Lourenço , Penousal Machado

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

This paper considers the decision-dependent optimization problem, where the data distributions react in response to decisions affecting both the objective function and linear constraints. We propose a new method termed repeated projected…

Optimization and Control · Mathematics 2025-08-13 Zifan Wang , Changxin Liu , Thomas Parisini , Michael M. Zavlanos , Karl H. Johansson

Recent developments in generative modeling have utilized score-based methods coupled with stochastic differential equations to sample from complex probability distributions. However, these and other performant sampling methods generally…

Machine Learning · Computer Science 2025-06-03 Bryan Riel , Tobias Bischoff

We study policy gradient methods for continuous-action, entropy-regularized reinforcement learning through the lens of Wasserstein geometry. Starting from a Wasserstein proximal update, we derive Wasserstein Proximal Policy Gradient (WPPG)…

Machine Learning · Computer Science 2026-03-04 Zhaoyu Zhu , Shuhan Zhang , Rui Gao , Shuang Li

We study robust Markov decision processes (RMDPs) with general policy parameterization under s-rectangular and non-rectangular uncertainty sets. Prior work is largely limited to tabular policies, and hence either lacks sample complexity…

Machine Learning · Computer Science 2026-02-13 Anirudh Satheesh , Ziyi Chen , Furong Huang , Heng Huang

Estimating a policy that maps states to actions is a central problem in reinforcement learning. Traditionally, policies are inferred from the so called value functions (VFs), but exact VF computation suffers from the curse of…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques