The optimal dynamic regret for smoothed online convex optimization with squared l₂ norm switching costs

DOI10.1016/J.JFRANKLIN.2023.02.013MaRDI QIDQ6157294zbMATH OpenFDO

Authors

Publication date 21 June 2023

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JFRANKLIN.2023.02.013

Mathematics Subject Classification ID

Convex programming (90C25)

Recommendations

• A tight lower bound for online convex optimization with switching costs
• A 2-competitive algorithm for online convex optimization with switching costs
• Regret bounded by gradual variation for online convex optimization
• Logarithmic Regret Algorithms for Online Convex Optimization
• Logarithmic regret algorithms for online convex optimization

Cites work

• Linear coupling: an ultimate unification of gradient and mirror descent
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Non-stationary stochastic optimization
• Online Optimization With Predictions and Switching Costs: Fast Algorithms and the Fundamental Limit

Cited in

(8)

• A tight lower bound for online convex optimization with switching costs
• Regret bounded by gradual variation for online convex optimization
• Logarithmic regret in online linear quadratic control using Riccati updates
• A 2-competitive algorithm for online convex optimization with switching costs
• Online composite optimization with time-varying regularizers
• Regret of general-norm online gradient descent for relatively smooth convex loss functions
• Dynamic regret for decentralized online bandit gradient descent with local steps
• Distributed online optimization with switching costs

This page was built for publication: The optimal dynamic regret for smoothed online convex optimization with squared \(l_2\) norm switching costs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6157294)