paper-with-me

홈 › Papers

Fast Rates for Regularized Objectives

2008-12-01 · NeurIPS 2008 12 · Karthik Sridharan, Shai Shalev-Shwartz, Nathan Srebro

We show that the empirical minimizer of a stochastic strongly convex objective, where the stochastic component is linear, converges to the population minimizer with rate $O(1/n)$. The result applies, in particular, to the SVM objective. Thus, we get a rate of $O(1/n)$ on the convergence of the SVM objective to its infinite data limit. We demonstrate how this is essential for obtaining tight oracle inequalities for SVMs. The results extend also to strong convexity with respect to other $\ellnorm_p$ norms, and so also to objectives regularized using other norms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Similar Papers 제목 키워드 기반

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits

2026-03-02 · Kaixuan Ji, Qingyue Zhao, Heyang Zhao, Qiwei Di 외 arxiv

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized s…

Reinforcement LearningMulti-Armed Bandits

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

2026-05-09 · Qingyue Zhao, Kaixuan Ji, Heyang Zhao, Quanquan Gu arxiv

\emph{Kullback-Leibler} (KL) regularization is ubiquitous in reinforcement learning algorithms in the form of \emph{reverse} or \emph{forward} KL. Recent studies have demonstrated $ε^{-1}$-type fast rates for decision ma…

Reinforcement LearningDecision Making

Stochastic Nonconvex Optimization with Large Minibatches

2017-09-25 · Weiran Wang, Nathan Srebro

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearize…

Stochastic Optimization

Global Convergence of SGD On Two Layer Neural Nets

2022-10-20 · Pulkit Gopalani, Anirbit Mukherjee

In this note, we consider appropriately regularized $\ell_2-$empirical risk of depth $2$ nets with any number of gates and show bounds on how the empirical loss evolves for SGD iterates on it -- for arbitrary data and if…

Vocal Bursts Valence Prediction

Regularized Newton Method with Global $O(1/k^2)$ Convergence

2021-12-03 · Konstantin Mishchenko

We present a Newton-type method that converges fast from any initialization and for arbitrary convex objectives with Lipschitz Hessians. We achieve this by merging the ideas of cubic regularization with a certain adaptiv…