paper-with-me

홈 › Papers

Combining Online Learning Guarantees

2019-02-24 · Ashok Cutkosky

We show how to take any two parameter-free online learning algorithms with different regret guarantees and obtain a single algorithm whose regret is the minimum of the two base algorithms. Our method is embarrassingly simple: just add the iterates. This trick can generate efficient algorithms that adapt to many norms simultaneously, as well as providing diagonal-style algorithms that still maintain dimension-free guarantees. We then proceed to show how a variant on this idea yields a black-box procedure for generating optimistic online learning algorithms. This yields the first optimistic regret guarantees in the unconstrained setting and generically increases adaptivity. Further, our optimistic algorithms are guaranteed to do no worse than their non-optimistic counterparts regardless of the quality of the optimistic estimates provided to the algorithm.

📄 PDF Abstract BibTeX arXiv:1902.09003

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adaptive prediction theory combining offline and online learning

2025-11-29 · Haizheng Li, Lei Guo arxiv

Real-world intelligence systems usually operate by combining offline learning and online adaptation with highly correlated and non-stationary system data or signals, which, however, has rarely been investigated theoretic…

Anytime Online-to-Batch Conversions, Optimism, and Acceleration

2019-03-03 · Ashok Cutkosky

A standard way to obtain convergence guarantees in stochastic convex optimization is to run an online learning algorithm and then output the average of its iterates: the actual iterates of the online learning algorithm d…

Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning

2016-05-20 · NeurIPS 2016 12 · Wouter M. Koolen, Peter Grünwald, Tim van Erven

We consider online learning algorithms that guarantee worst-case regret rates in adversarial environments (so they can be deployed safely and will perform robustly), yet adapt optimally to favorable stochastic environmen…

An Analysis of Model-Based Reinforcement Learning From Abstracted Observations

2022-08-30 · NeurIPS 2021 12 · Rolf A. N. Starre, Marco Loog, Elena Congeduti, Frans A. Oliehoek

Many methods for Model-based Reinforcement learning (MBRL) in Markov decision processes (MDPs) provide guarantees for both the accuracy of the model they can deliver and the learning efficiency. At the same time, state a…

Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Data-driven system analysis of nonlinear systems using polynomial approximation

2021-08-25 · Tim Martin, Frank Allgöwer

In the context of data-driven control of nonlinear systems, many approaches lack of rigorous guarantees, call for nonconvex optimization, or require knowledge of a function basis containing the system dynamics. To tackle…