A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, variance reduction, and variational bounds

DOI10.1016/J.TCS.2019.11.015zbMATH Open1436.68306OpenAlexW2985478892MaRDI QIDQ2290691FDOQ2290691

Authors: Pooria Joulani, András György, Csaba Szepesvári 

Publication date: 29 January 2020

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2019.11.015

Recommendations

• A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, and variational bounds
• A survey of algorithms and analysis for adaptive online learning
• Regret bounded by gradual variation for online convex optimization
• Analysis of Online Composite Mirror Descent Algorithm
• Scale-free online learning

zbMATH Keywords

stochastic optimizationadaptive algorithmsonline learningmirror descentregret boundfollow the regularized leader

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27) Stochastic programming (90C15)

Cites Work

• Adaptive subgradient methods for online learning and stochastic optimization
• Prediction, Learning, and Games
• Convex analysis and monotone operator theory in Hilbert spaces
• Deep learning
• Primal-dual subgradient methods for convex problems
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Title not available (Why is that?)
• Proximal Minimization Methods with Generalized Bregman Functions
• Logarithmic regret algorithms for online convex optimization
• Stochastic optimal control. The discrete time case
• Online learning and online convex optimization
• An optimal method for stochastic composite optimization
• Title not available (Why is that?)
• Solving variational inequalities with stochastic mirror-prox algorithm
• Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization
• Cubic regularization of Newton method and its global performance
• Exponentiated gradient versus gradient descent for linear predictors
• Optimal distributed online prediction using mini-batches
• A generalized online mirror descent with applications to classification and regression
• Title not available (Why is that?)
• A survey of algorithms and analysis for adaptive online learning
• Gradient descent learns linear dynamical systems

Cited In (4)

• Online composite optimization with time-varying regularizers
• Optimistic optimisation of composite objective with exponentiated update
• A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, and variational bounds
• A survey of algorithms and analysis for adaptive online learning

Uses Software

• AdaGrad

This page was built for publication: A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, variance reduction, and variational bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2290691)