Skip to content
conftrace_
2015 ICML ICML 2015

Strongly Adaptive Online Learning

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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization
🐣 Hot Topic Early Bird - regret minimization

Authors

Amit Daniely, Alon Gonen, Shai Shalev-shwartz

Topics

Machine Learning > Optimization & Theory > Learning Theory Mathematics & Optimization > Optimization > Online Algorithms Machine Learning > Learning Types > Online Learning Machine Learning > Optimization & Theory > Online Algorithms

Keywords

learning theory online learning regret minimization adaptive algorithm low regret algorithm performance time interval
Download PDF

More from ICML 2015

All ICML 2015 papers →
The Composition Theorem for Differential Privacy
Convex Formulation for Learning from Positive and Unlabeled Data
Threshold Influence Model for Allocating Advertising Budgets
CUR Algorithm for Partially Observed Matrices
A Deterministic Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced Data
MRA-based Statistical Learning from Incomplete Rankings