paper-with-me

Papers

A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer

2017-09-09 · Tianbao Yang, Zhe Li, Lijun Zhang

In this paper, we present a simple analysis of {\bf fast rates} with {\it high probability} of {\bf empirical minimization} for {\it stochastic composite optimization} over a finite-dimensional bounded convex set with exponential concave loss functions and an arbitrary convex regularization. To the best of our knowledge, this result is the first of its kind. As a byproduct, we can directly obtain the fast rate with {\it high probability} for exponential concave empirical risk minimization with and without any convex regularization, which not only extends existing results of empirical risk minimization but also provides a unified framework for analyzing exponential concave empirical risk minimization with and without {\it any} convex regularization. Our proof is very simple only exploiting the covering number of a finite-dimensional bounded set and a concentration inequality of random vectors.

📄 PDF Abstract BibTeX arXiv:1709.02909

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optimal Sketching Bounds for Exp-concave Stochastic Minimization

2018-05-21 · Naman Agarwal, Alon Gonen

We derive optimal statistical and computational complexity bounds for exp-concave stochastic minimization in terms of the effective dimension. For common eigendecay patterns of the population covariance matrix, this quan…

A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise

2019-02-05 · Francis Bach, Kfir. Y. Levy

We consider variational inequalities coming from monotone operators, a setting that includes convex minimization and convex-concave saddle-point problems. We assume an access to potentially noisy unbiased values of the m…

A unified complexity bound for logconcave sampling

2026-06-10 · Yunbum Kook, Santosh S. Vempala arxiv

We give a simple, unified, and nearly tight bound for sampling arbitrary logconcave distributions from a warm start using the In-and-Out algorithm along with exponential lifting. The main new ingredient in the analysis i…

Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving

2021-05-27 · NeurIPS 2021 12 · Julien Grand-Clément, Christian Kroer

We develop new parameter-free and scale-free algorithms for solving convex-concave saddle-point problems. Our results are based on a new simple regret minimizer, the Conic Blackwell Algorithm$^+$ (CBA$^+$), which attains…

counterfactual

Fast Rates for Exp-concave Empirical Risk Minimization

2015-12-01 · NeurIPS 2015 12 · Tomer Koren, Kfir Levy

We consider Empirical Risk Minimization (ERM) in the context of stochastic optimization with exp-concave and smooth losses---a general optimization framework that captures several important learning problems including li…

regressionStochastic Optimization