English
Related papers

Related papers: Accelerating Value Iteration with Anchoring

200 papers

While maximizing expected return is the goal in most reinforcement learning approaches, risk-sensitive objectives such as conditional value at risk (CVaR) are more suitable for many high-stakes applications. However, relatively little is…

Machine Learning · Computer Science 2020-04-06 Ramtin Keramati , Christoph Dann , Alex Tamkin , Emma Brunskill

The {\it forward-backward algorithm} is a powerful tool for solving optimization problems with a {\it additively separable} and {\it smooth} + {\it nonsmooth} structure. In the convex setting, a simple but ingenious acceleration scheme…

Optimization and Control · Mathematics 2017-05-18 Hedy Attouch , Juan Peypouquet

Recently, accelerated algorithms using the anchoring mechanism for minimax optimization and fixed-point problems have been proposed, and matching complexity lower bounds establish their optimality. In this work, we present the surprising…

Optimization and Control · Mathematics 2024-04-25 TaeHo Yoon , Jaeyeon Kim , Jaewook J. Suh , Ernest K. Ryu

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability. Crucial to the performance of VI is the selection of the associated divergence measure, as VI…

Machine Learning · Computer Science 2021-06-24 Ruqi Zhang , Yingzhen Li , Christopher De Sa , Sam Devlin , Cheng Zhang

Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has found significant empirical success. However, a principled understanding of why it works is lacking. This…

Machine Learning · Computer Science 2026-05-08 Joe Suk , Yaqi Duan

When using reinforcement learning (RL) algorithms to evaluate a policy it is common, given a large state space, to introduce some form of approximation architecture for the value function (VF). The exact form of this architecture can have a…

Artificial Intelligence · Computer Science 2017-03-06 Edward W. Barker , Charl J. Ras

We prove performance guarantees of two algorithms for approximating $Q^\star$ in batch reinforcement learning. Compared to classical iterative methods such as Fitted Q-Iteration---whose performance loss incurs quadratic dependence on…

Machine Learning · Computer Science 2020-08-25 Tengyang Xie , Nan Jiang

Anderson acceleration is an old and simple method for accelerating the computation of a fixed point. However, as far as we know and quite surprisingly, it has never been applied to dynamic programming or reinforcement learning. In this…

Machine Learning · Computer Science 2018-09-26 Matthieu Geist , Bruno Scherrer

We consider the question of estimating a solution to a system of equations that involve convex nonlinearities, a problem that is common in machine learning and signal processing. Because of these nonlinearities, conventional estimators…

Machine Learning · Computer Science 2018-08-14 Sohail Bahmani , Justin Romberg

Cross-validation (CV) is one of the most popular tools for assessing and selecting predictive models. However, standard CV suffers from high computational cost when the number of folds is large. Recently, under the empirical risk…

Methodology · Statistics 2023-05-30 Yuetian Luo , Zhimei Ren , Rina Foygel Barber

While value iteration (VI) is a standard solution approach to simple stochastic games (SSGs), it suffered from the lack of a stopping criterion. Recently, several solutions have appeared, among them also "optimistic" VI (OVI). However, OVI…

Computer Science and Game Theory · Computer Science 2022-08-01 Muqsit Azeem , Alexandros Evangelidis , Jan Křetínský , Alexander Slivinskiy , Maximilian Weininger

Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were…

Machine Learning · Computer Science 2020-11-18 Minyoung Kim , Vladimir Pavlovic

Asynchronous algorithms have attracted much attention recently due to the crucial demands on solving large-scale optimization problems. However, the accelerated versions of asynchronous algorithms are rarely studied. In this paper, we…

Optimization and Control · Mathematics 2018-02-28 Cong Fang , Yameng Huang , Zhouchen Lin

Reinforcement learning (RL) has emerged as a powerful tool for fine-tuning large language models (LLMs) to improve complex reasoning abilities. However, state-of-the-art policy optimization methods often suffer from high computational…

Machine Learning · Computer Science 2025-05-28 Kianté Brantley , Mingyu Chen , Zhaolin Gao , Jason D. Lee , Wen Sun , Wenhao Zhan , Xuezhou Zhang

We build on a recently introduced geometric interpretation of Markov Decision Processes (MDPs) to analyze classical MDP-solving algorithms: Value Iteration (VI) and Policy Iteration (PI). First, we develop a geometry-based analytical…

Machine Learning · Computer Science 2025-03-07 Arsenii Mustafin , Aleksei Pakharev , Alex Olshevsky , Ioannis Ch. Paschalidis

Cross-validation (CV) is one of the main tools for performance estimation and parameter tuning in machine learning. The general recipe for computing CV estimate is to run a learning algorithm separately for each CV fold, a computationally…

Machine Learning · Statistics 2015-07-02 Pooria Joulani , András György , Csaba Szepesvári

Scaling to larger systems, with current levels of reliability, requires cost-effective methods to mitigate hardware failures. One of the main causes of hardware failure is an uncorrected error in memory, which terminates the current job and…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-06 Isaac Boixaderas , Sergi Moré , Javier Bartolome , David Vicente , Petar Radojković , Paul M. Carpenter , Eduard Ayguadé

Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in…

Machine Learning · Computer Science 2026-02-17 Minh Nguyen

Distributional reinforcement learning improves performance by capturing environmental stochasticity, but a comprehensive theoretical understanding of its effectiveness remains elusive. In addition, the intractable element of the infinite…

Machine Learning · Computer Science 2025-05-14 Taehyun Cho , Seungyub Han , Seokhun Ju , Dohyeong Kim , Kyungjae Lee , Jungwoo Lee

We introduce a class of variational actor-critic algorithms based on a variational formulation over both the value function and the policy. The objective function of the variational formulation consists of two parts: one for maximizing the…

Machine Learning · Computer Science 2023-01-18 Yuhua Zhu , Lexing Ying
‹ Prev 1 3 4 5 6 7 10 Next ›