Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements

07/16/2021
by   Kimon Antonakopoulos, et al.
0

We propose a new family of adaptive first-order methods for a class of convex minimization problems that may fail to be Lipschitz continuous or smooth in the standard sense. Specifically, motivated by a recent flurry of activity on non-Lipschitz (NoLips) optimization, we consider problems that are continuous or smooth relative to a reference Bregman function - as opposed to a global, ambient norm (Euclidean or otherwise). These conditions encompass a wide range of problems with singular objectives, such as Fisher markets, Poisson tomography, D-design, and the like. In this setting, the application of existing order-optimal adaptive methods - like UnixGrad or AcceleGrad - is not possible, especially in the presence of randomness and uncertainty. The proposed method - which we call adaptive mirror descent (AdaMir) - aims to close this gap by concurrently achieving min-max optimal rates in problems that are relatively continuous or smooth, including stochastic ones.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

02/22/2020

Private Stochastic Convex Optimization: Efficient Algorithms for Non-smooth Objectives

In this paper, we revisit the problem of private stochastic convex optim...
10/22/2020

Adaptive extra-gradient methods for min-max optimization and games

We present a new family of min-max optimization algorithms that automati...
04/06/2022

Black-Box Min–Max Continuous Optimization Using CMA-ES with Worst-case Ranking Approximation

In this study, we investigate the problem of min-max continuous optimiza...
07/07/2017

Non-smooth Non-convex Bregman Minimization: Unification and new Algorithms

We propose a unifying algorithm for non-smooth non-convex optimization. ...
05/11/2018

Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions

Error bound conditions (EBC) are properties that characterize the growth...
08/15/2016

Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back

In stochastic convex optimization the goal is to minimize a convex funct...
08/03/2016

Fast and Simple Optimization for Poisson Likelihood Models

Poisson likelihood models have been prevalently used in imaging, social ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.