paper-with-me

Papers

Online Learning with Optimism and Delay

2021-06-13 · Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey

Inspired by the demands of real-time climate and weather forecasting, we develop optimistic online learning algorithms that require no parameter tuning and have optimal regret guarantees under delayed feedback. Our algorithms -- DORM, DORM+, and AdaHedgeD -- arise from a novel reduction of delayed online learning to optimistic online learning that reveals how optimistic hints can mitigate the regret penalty caused by delay. We pair this delay-as-optimism perspective with a new analysis of optimistic learning that exposes its robustness to hinting errors and a new meta-algorithm for learning effective hinting strategies in the presence of delay. We conclude by benchmarking our algorithms on four subseasonal climate forecasting tasks, demonstrating low regret relative to state-of-the-art forecasting models.

📄 PDF Abstract BibTeX arXiv:2106.06885

Code (1)

geflaspohler/poold 공식 구현

Tasks

BenchmarkingWeather Forecasting

Similar Papers 제목 키워드 기반

Linear Convergence in Games with Delayed Feedback via Extra Prediction

2026-02-19 · Yuma Fujimoto, Kenshi Abe, Kaito Ariu arxiv

Feedback delays are inevitable in real-world multi-agent learning. They are known to severely degrade performance, and the convergence rate under delayed feedback is still unclear, even for bilinear games. This paper der…

Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism

2020-12-21 · Yu-Guan Hsieh, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos

In this paper, we provide a general framework for studying multi-agent online learning problems in the presence of delays and asynchronicities. Specifically, we propose and analyze a class of adaptive dual averaging sche…

Optimistic Online Non-stochastic Control via FTRL

2024-04-04 · Naram Mhaisen, George Iosifidis

This paper brings the concept of ``optimism" to the new and promising framework of online Non-stochastic Control (NSC). Namely, we study how NSC can benefit from a prediction oracle of unknown quality responsible for for…

Optimism and Delays in Episodic Reinforcement Learning

2021-11-15 · Benjamin Howson, Ciara Pike-Burke, Sarah Filippi

There are many algorithms for regret minimisation in episodic reinforcement learning. This problem is well-understood from a theoretical perspective, providing that the sequences of states, actions and rewards associated…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Tactical Optimism and Pessimism for Deep Reinforcement Learning

2021-02-07 · NeurIPS 2021 12 · Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel 외

In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improved performance is the use of pessimistic…

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+2