SEMINAR

Optimal Transport for Distributionally Robust Optimization and Applications in Machine Learning

Speaker

Bahar Taskesen

Working
EPFL
Timeline
Fri, Jun 17 2022 - 03:00 pm (GMT + 7)
About Speaker

Bahar Taskesen is currently a Ph.D. student in Risk Analytics and Optimization at Ecole Polytechnique Federale de Lausanne (Switzerland), working with Daniel Kuhn. She received a B.Sc. degree in Electrical and Electronics Engineering from Middle East Technical University (Ankara, Turkey) in 2018. Her research interests revolve around optimal transport problems, decision making under uncertainty and its use for machine learning.

Abstract

Optimal Transport (OT) seeks the most efficient way to morph one probability distribution into another one, and Distributionally Robust Optimization (DRO) studies worst-case risk minimization problems under distributional ambiguity. It is well known that OT gives rise to a rich class of data-driven DRO models, where the decision-maker plays a zero-sum game against nature who can adversely reshape the empirical distribution of the uncertain problem parameters within a prescribed transportation budget. Even though generic OT problems are computationally hard, optimal decisions of OT-based DRO problems can often be computed by solving tractable convex optimization problems. In this talk, we will show that OT-based DRO offers a principled approach to dealing with distribution shifts and heterogeneous data sources, and we will highlight new applications of OT-based DRO in responsible artificial intelligence. Finally, we will argue that, while OT is useful for DRO, ideas from DRO can also help us to solve challenging OT problems.

Related seminars

Anh Nguyen

Microsoft GenAI

The Revolution of Small Language Models
Fri, Mar 8 2024 - 02:30 pm (GMT + 7)

Thang D. Bui

Australian National University (ANU)

Recent Progress on Grokking and Probabilistic Federated Learning
Fri, Jan 26 2024 - 10:00 am (GMT + 7)

Tim Baldwin

MBZUAI, The University of Melbourne

LLMs FTW
Tue, Jan 9 2024 - 10:30 am (GMT + 7)

Quan Vuong

Google DeepMind

Scaling Robot Learning
Wed, Dec 27 2023 - 10:00 am (GMT + 7)