Optimal rates for the regularized learning algorithms under general source condition
We consider the learning algorithms under general source condition with the polynomial decay of the eigenvalues of the integral operator in vector-valued function setting. We discuss the upper convergence rates of Tikhonov regularizer under general source condition corresponding to increasing monotone index function. The convergence issues are studied for general regularization schemes by using the concept of operator monotone index functions in minimax setting. Further we also address the minimum possible error for any learning algorithm.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On the Convergence of Approximate and Regularized Policy Iteration Schemes
Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifie…
Q-LearningReinforcement LearningReinforcement Learning (RL)Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces
We investigate regularized algorithms combining with projection for least-squares regression problem over a Hilbert space, covering nonparametric regression over a reproducing kernel Hilbert space. We prove convergence r…
regressionSelf-Regularized Learning Methods
We introduce a general framework for analyzing learning algorithms based on the notion of self-regularization, which captures implicit complexity control without requiring explicit regularization. This is motivated by pr…
Online Regularized Nonlinear Acceleration
Regularized nonlinear acceleration (RNA) estimates the minimum of a function by post-processing iterates from an algorithm such as the gradient method. It can be seen as a regularized version of Anderson acceleration, a …
General ClassificationGreedy stochastic algorithms for entropy-regularized optimal transport problems
Optimal transport (OT) distances are finding evermore applications in machine learning and computer vision, but their wide spread use in larger-scale problems is impeded by their high computational cost. In this work we …