English
Related papers

Related papers: Policy Newton Algorithm in Reproducing Kernel Hilb…

200 papers

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

Machine Learning · Computer Science 2017-01-11 Tanmay Shankar , Santosha K. Dwivedy , Prithwijit Guha

Second-order methods are provably faster than first-order methods, and their efficient implementations for large-scale optimization problems have attracted significant attention. Yet, optimization problems in ML often have nonsmooth…

Optimization and Control · Mathematics 2026-02-10 Amal Alphonse , Pavel Dvurechensky , Clemens Sirotenko

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models.…

Reinforcement learning (RL) is a powerful machine learning technique that enables an intelligent agent to learn an optimal policy that maximizes the cumulative rewards in sequential decision making. Most of methods in the existing…

Machine Learning · Statistics 2023-01-06 Chengchun Shi , Zhengling Qi , Jianing Wang , Fan Zhou

We analyze Newton's method with lazy Hessian updates for solving general possibly non-convex optimization problems. We propose to reuse a previously seen Hessian for several iterations while computing new gradients at each step of the…

Optimization and Control · Mathematics 2023-06-16 Nikita Doikov , El Mahdi Chayti , Martin Jaggi

A class of second-order algorithms is proposed for minimizing smooth nonconvex functions that alternates between regularized Newton and negative curvature steps in an iteration-dependent subspace. In most cases, the Hessian matrix is…

Optimization and Control · Mathematics 2023-08-22 Serge Gratton , Sadok Jerad , Philippe L. Toint

This paper designs novel nonparametric Bellman mappings in reproducing kernel Hilbert spaces (RKHSs) for reinforcement learning (RL). The proposed mappings benefit from the rich approximating properties of RKHSs, adopt no assumptions on the…

Signal Processing · Electrical Eng. & Systems 2024-04-01 Yuki Akiyama , Minh Vu , Konstantinos Slavakis

We initiate the mathematical study of replicability as an algorithmic property in the context of reinforcement learning (RL). We focus on the fundamental setting of discounted tabular MDPs with access to a generative model. Inspired by…

Machine Learning · Computer Science 2023-10-31 Amin Karbasi , Grigoris Velegkas , Lin F. Yang , Felix Zhou

Reinforcement Learning (RL) from Human Preference-based feedback is a popular paradigm for fine-tuning generative models, which has produced impressive models such as GPT-4 and Claude3 Opus. This framework often consists of two steps:…

Machine Learning · Computer Science 2024-04-17 Jonathan D. Chang , Wenhao Zhan , Owen Oertell , Kianté Brantley , Dipendra Misra , Jason D. Lee , Wen Sun

We present a general framework to learn functions in tensor product reproducing kernel Hilbert spaces (TP-RKHSs). The methodology is based on a novel representer theorem suitable for existing as well as new spectral penalties for tensors.…

Machine Learning · Computer Science 2013-10-21 Marco Signoretto , Lieven De Lathauwer , Johan A. K. Suykens

We propose kernel distributionally robust optimization (Kernel DRO) using insights from the robust optimization theory and functional analysis. Our method uses reproducing kernel Hilbert spaces (RKHS) to construct a wide range of convex…

Optimization and Control · Mathematics 2021-06-28 Jia-Jie Zhu , Wittawat Jitkrittum , Moritz Diehl , Bernhard Schölkopf

Vision Transformers (ViTs) have computational costs scaling quadratically with the number of tokens, calling for effective token pruning policies. Most existing policies are handcrafted, lacking adaptivity to varying inputs. Moreover, they…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Chenglong Lu , Shen Liang , Xuewei Wang , Wei Wang

This manuscript presents an algorithm for obtaining an approximation of a nonlinear high order control affine dynamical system. Controlled trajectories of the system are leveraged as the central unit of information via embedding them in…

Optimization and Control · Mathematics 2026-01-23 Moad Abudia , Tejasvi Channagiri , Joel A. Rosenfeld , Rushikesh Kamalapurkar

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of…

This paper introduces a novel data-driven approach to design a linear quadratic regulator (LQR) using a reinforcement learning (RL) algorithm that does not require a system model. The key contribution is to perform policy iteration (PI) by…

Systems and Control · Electrical Eng. & Systems 2023-11-20 Soroush Asri , Luis Rodrigues

Reinforcement learning (RL) has emerged as a promising approach to automating decision processes. This paper explores the application of RL techniques to optimise the polynomial order in the computational mesh when using high-order solvers.…

Machine Learning · Computer Science 2023-06-16 David Huergo , Gonzalo Rubio , Esteban Ferrer

Current methods for stochastic hyperparameter learning in Gaussian Processes (GPs) rely on approximations, such as computing biased stochastic gradients or using inducing points in stochastic variational inference. However, when using such…

Machine Learning · Computer Science 2025-08-29 Neta Shoham , Haim Avron

This study addresses the problem of selecting dynamically, at each time instance, the ``optimal'' p-norm to combat outliers in linear adaptive filtering without any knowledge on the potentially time-varying probability distribution function…

Signal Processing · Electrical Eng. & Systems 2022-10-24 Minh Vu , Yuki Akiyama , Konstantinos Slavakis

This paper addresses second-order stochastic optimization for estimating the minimizer of a convex function written as an expectation. A direct recursive estimation technique for the inverse Hessian matrix using a Robbins-Monro procedure is…

Optimization and Control · Mathematics 2025-03-11 Antoine Godichon-Baggioni , Wei Lu , Bruno Portier

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

Systems and Control · Electrical Eng. & Systems 2020-09-29 Milad Kazemi , Sadegh Soudjani
‹ Prev 1 3 4 5 6 7 10 Next ›