English
Related papers

Related papers: Krylov-Bellman boosting: Super-linear policy evalu…

200 papers

The high variance issue in unbiased policy-gradient methods such as VPG and REINFORCE is typically mitigated by adding a baseline. However, the baseline fitting itself suffers from the underfitting or the overfitting problem. In this paper,…

Artificial Intelligence · Computer Science 2017-01-05 Nithyanand Kota , Abhishek Mishra , Sunil Srinivasa , Xi , Chen , Pieter Abbeel

In this paper, we present a novel optimization algorithm designed specifically for estimating state-space models to deal with heavy-tailed measurement noise and constraints. Our algorithm addresses two significant limitations found in…

Signal Processing · Electrical Eng. & Systems 2024-11-19 Yifan Yu , Shengjie Xiu , Daniel P. Palomar

Policy-based methods currently dominate reinforcement learning (RL) pipelines for large language model (LLM) reasoning, leaving value-based approaches largely unexplored. We revisit the classical paradigm of Bellman Residual Minimization…

Machine Learning · Computer Science 2025-11-13 Yurun Yuan , Fan Chen , Zeyu Jia , Alexander Rakhlin , Tengyang Xie

The K-means algorithm is one of the most widely studied clustering algorithms in machine learning. While extensive research has focused on its ability to achieve a globally optimal solution, there still lacks a rigorous analysis of its…

Machine Learning · Computer Science 2025-06-12 Mingyi Li , Michael R. Metel , Akiko Takeda

In reinforcement learning, temporal difference-based algorithms can be sample-inefficient: for instance, with sparse rewards, no learning occurs until a reward is observed. This can be remedied by learning richer objects, such as a model of…

Machine Learning · Computer Science 2021-01-19 Léonard Blier , Corentin Tallec , Yann Ollivier

Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interacts with their environment. However, existing algorithms often view these problem as static, focusing on point estimates for model…

Machine Learning · Statistics 2024-03-21 Frank Shih , Faming Liang

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman…

Machine Learning · Computer Science 2014-06-13 Matthieu Geist , Olivier Pietquin

We present a new procedure for enhanced variable selection for component-wise gradient boosting. Statistical boosting is a computational approach that emerged from machine learning, which allows to fit regression models in the presence of…

This work provides test error bounds for iterative fixed point methods on linear predictors -- specifically, stochastic and batch mirror descent (MD), and stochastic temporal difference learning (TD) -- with two core contributions: (a) a…

Machine Learning · Computer Science 2022-06-29 Matus Telgarsky

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

Gradient boosting is widely popular due to its flexibility and predictive accuracy. However, statistical inference and uncertainty quantification for gradient boosting remain challenging and under-explored. We propose a unified framework…

Machine Learning · Statistics 2025-09-30 Haimo Fang , Kevin Tan , Giles Hooker

Most of the existing works for reinforcement learning (RL) with general function approximation (FA) focus on understanding the statistical complexity or regret bounds. However, the computation complexity of such approaches is far from being…

Machine Learning · Computer Science 2023-04-19 Dingwen Kong , Ruslan Salakhutdinov , Ruosong Wang , Lin F. Yang

Boosting is a learning scheme that combines weak prediction rules to produce a strong composite estimator, with the underlying intuition that one can obtain accurate prediction rules by combining "rough" ones. Although boosting is proved to…

Machine Learning · Computer Science 2015-05-07 Shaobo Lin , Yao Wang , Lin Xu

TD($\lambda$) with function approximation has proved empirically successful for some complex reinforcement learning problems. For linear approximation, TD($\lambda$) has been shown to minimise the squared error between the approximate value…

Machine Learning · Computer Science 2025-12-24 Lex Weaver , Jonathan Baxter

Least squares regression is a ubiquitous tool for building emulators (a.k.a. surrogate models) of problems across science and engineering for purposes such as design space exploration and uncertainty quantification. When the regression data…

Numerical Analysis · Mathematics 2024-07-08 Nuojin Cheng , Osman Asif Malik , Yiming Xu , Stephen Becker , Alireza Doostan , Akil Narayan

We propose a novel Krylov subspace method for estimating the finite impulse response (FIR) of a one-dimensional linear time-invariant systems. The method approximates the system's FIR using a kernel-based formulation combined with…

Numerical Analysis · Mathematics 2026-05-12 Fabio Matti , Martin Skovgaard Andersen , Tianshi Chen , Daniel Kressner

To solve discrete Markov decision models with a large number of dimensions is always difficult (and at times, impossible), because size of state space and computation cost increases exponentially with the number of dimensions. This…

Computation · Statistics 2016-11-14 Masaaki Imaizumi

Statistical boosting algorithms have triggered a lot of research during the last decade. They combine a powerful machine-learning approach with classical statistical modelling, offering various practical advantages like automated variable…

We study the Extended Kalman Filter in constant dynamics, offering a bayesian perspective of stochastic optimization. We obtain high probability bounds on the cumulative excess risk in an unconstrained setting. In order to avoid any…

Machine Learning · Computer Science 2020-06-29 Joseph de Vilmarest , Olivier Wintenberger