Strongly Adaptive Online Learning
arXiv:1502.07073
Abstract
Strongly adaptive algorithms are algorithms whose performance on every time interval is close to optimal. We present a reduction that can transform standard low-regret algorithms to strongly adaptive. As a consequence, we derive simple, yet efficient, strongly adaptive algorithms for a handful of problems.
References in corpus (2)
Cited by in corpus (23)
- Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
- Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach
- Non-stationary Online Learning with Memory and Non-stochastic Control
- Online Forecasting of Total-Variation-bounded Sequences
- Non-Stationary Bandits with Habituation and Recovery Dynamics
- Bandit Convex Optimization in Non-stationary Environments
- Random Feature-based Online Multi-kernel Learning in Environments with Unknown Dynamics
- Proximal Online Gradient is Optimum for Dynamic Regret
- Optimal Dynamic Regret in Exp-Concave Online Learning
- Taking a hint: How to leverage loss predictors in contextual bandits?
- Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications
- Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions
- Dynamic Regret Minimization for Control of Non-stationary Linear Dynamical Systems
- Convergence Analyses of Online ADAM Algorithm in Convex Setting and Two-Layer ReLU Neural Network
- Non-stationary Stochastic Optimization under -Variation Measures
- Similarity Function Tracking using Pairwise Comparisons
- Universal Online Convex Optimization Meets Second-order Bounds
- Active Online Learning with Hidden Shifting Domains
- Online Learning for Non-Stationary A/B Tests
- LeadCache: Regret-Optimal Caching in Networks
- Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory
- Online Learning with Automata-based Expert Sequences
- Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR