Timezone: »

Online Learning with Optimism and Delay
Genevieve Flaspohler · Francesco Orabona · Judah Cohen · Soukayna Mouatadid · Miruna Oprescu · Paulo Orenstein · Lester Mackey

Thu Jul 22 08:40 PM -- 08:45 PM (PDT) @ None

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.

Author Information

Genevieve Flaspohler (Massachusetts Institute of Technology)
Francesco Orabona (Boston University)
Francesco Orabona

Francesco Orabona is an Assistant Professor at Boston University. His background covers both theoretical and practical aspects of machine learning and optimization. His current research interests lie in online learning, and more generally the problem of designing and analyzing adaptive and parameter-free learning algorithms. He received the PhD degree in Electrical Engineering at the University of Genoa in 2007. He is (co)author of more than 60 peer reviewed papers.

Judah Cohen (AER)
Soukayna Mouatadid (University of Toronto)
Miruna Oprescu (Microsoft Research)

Miruna Oprescu is a Data and Applied Scientist at Microsoft Research New England. In her current role, Miruna works alongside researchers and software engineers to build the next generation machine learning tools for interdisciplinary applications. Miruna spends her time between two projects: project ALICE, a Microsoft Research initiative aimed at applying artificial intelligence concepts to economic decision making, and the Machine Learning for Cancer Immunotherapies initiative, a collaboration with doctors and cancer researchers with the goal of applying machine learning techniques to improving cancer therapies.

Paulo Orenstein (Instituto de Matemática Pura e Aplicada)
Lester Mackey (Microsoft Research)
Lester Mackey

Lester Mackey is a machine learning researcher at Microsoft Research, where he develops new tools, models, and theory for large-scale learning tasks driven by applications from healthcare, climate, recommender systems, and the social good. Lester moved to Microsoft from Stanford University, where he was an assistant professor of Statistics and (by courtesy) of Computer Science. He earned his PhD in Computer Science and MA in Statistics from UC Berkeley and his BSE in Computer Science from Princeton University. He co-organized the second place team in the \$1M. Netflix Prize competition for collaborative filtering, won the \$50K Prise4Life ALS disease progression prediction challenge, won prizes for temperature and precipitation forecasting in the yearlong real-time \$800K Subseasonal Climate Forecast Rodeo, and received a best student paper award at the International Conference on Machine Learning.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors