Introduction to online convex optimization

E Hazan - Foundations and Trends® in Optimization, 2016 - nowpublishers.com
This monograph portrays optimization as a process. In many practical applications the
environment is so complex that it is infeasible to lay out a comprehensive theoretical model …

A survey on distributed online optimization and online games

X Li, L **e, N Li - Annual Reviews in Control, 2023 - Elsevier
Distributed online optimization and online games have been increasingly researched in the
last decade, mostly motivated by their wide applications in sensor networks, robotics (eg …

Revisiting Frank-Wolfe: Projection-free sparse convex optimization

M Jaggi - International conference on machine learning, 2013 - proceedings.mlr.press
We provide stronger and more general primal-dual convergence results for Frank-Wolfe-
type algorithms (aka conditional gradient) for constrained convex optimization, enabled by a …

Conditional gradient methods

G Braun, A Carderera, CW Combettes… - arxiv preprint arxiv …, 2022 - arxiv.org
The purpose of this survey is to serve both as a gentle introduction and a coherent overview
of state-of-the-art Frank--Wolfe algorithms, also called conditional gradient algorithms, for …

Optimization with non-differentiable constraints with applications to fairness, recall, churn, and other goals

A Cotter, H Jiang, M Gupta, S Wang, T Narayan… - Journal of Machine …, 2019 - jmlr.org
We show that many machine learning goals can be expressed as “rate constraints” on a
model's predictions. We study the problem of training non-convex models subject to these …

Reinforcement and imitation learning via interactive no-regret learning

S Ross, JA Bagnell - arxiv preprint arxiv:1406.5979, 2014 - arxiv.org
Recent work has demonstrated that problems--particularly imitation learning and structured
prediction--where a learner's predictions influence the input-distribution it is tested on can be …

Understanding alternating minimization for matrix completion

M Hardt - 2014 IEEE 55th Annual Symposium on Foundations …, 2014 - ieeexplore.ieee.org
Alternating minimization is a widely used and empirically successful heuristic for matrix
completion and related low-rank optimization problems. Theoretical guarantees for …

Variance-reduced and projection-free stochastic optimization

E Hazan, H Luo - International Conference on Machine …, 2016 - proceedings.mlr.press
Abstract The Frank-Wolfe optimization algorithm has recently regained popularity for
machine learning applications due to its projection-free property and its ability to handle …

Nearly optimal private lasso

K Talwar, A Guha Thakurta… - Advances in Neural …, 2015 - proceedings.neurips.cc
We present a nearly optimal differentially private version of the well known LASSO estimator.
Our algorithm provides privacy protection with respect to each training data item. The excess …

Optimization with first-order surrogate functions

J Mairal - International Conference on Machine Learning, 2013 - proceedings.mlr.press
In this paper, we study optimization methods consisting of iteratively minimizing surrogates
of an objective function. By proposing several algorithmic variants and simple convergence …