Tue, Oct 29, 2019 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Aditya Grover, Stanford University
Talk Title: Mitigating Bias in Generative Modeling
Series: Computer Science Colloquium
Abstract: In the last few years, there has been remarkable progress in deep generative modeling. However, the learned models are noticeably inaccurate w.r.t. to the underlying data distribution, as evident from downstream metrics that compare statistics of interest across the true and generated data samples. This bias in downstream evaluation can be attributed to imperfections in learning (\"model bias\") or be propagated due to the bias in the training dataset itself (\"dataset bias\"). In this talk, I will present an importance weighting approach for mitigating both these kinds of biases of generative models. Our approach assumes only \'black-box\' sample access to a generative model and is broadly applicable to both likelihood-based and likelihood-free generative models. Empirically, we find that our technique consistently improves standard goodness-of-fit metrics for evaluating the sample quality of state-of-the-art deep generative models, suggesting reduced bias. We demonstrate its utility on representative applications in a) data augmentation and b) model-based policy evaluation using off-policy data. Finally, I will present some recent work extending these ideas to fair data generation in the presence of biased training datasets.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Aditya Grover is a 5th-year Ph.D. candidate in Computer Science at Stanford University advised by Stefano Ermon. His research focuses on probabilistic machine learning, including topics in generative modeling, approximate inference, and deep learning as well as applications in sustainability. His research has been cited widely in academia, deployed into production at major technology companies, and recognized with a best paper award (StarAI), a Lieberman Fellowship, a Data Science Institute Scholarship, and a Microsoft Research Ph.D. Fellowship. He is also a Teaching Fellow at Stanford since 2018, where he co-designed and teaches a new class on Deep Generative Models. Previously, Aditya obtained his bachelors in Computer Science and Engineering from IIT Delhi in 2015, where he received a best undergraduate thesis award.
Host: If you would like to meet the speaker, please email the host Bistra Dilkina at firstname.lastname@example.org
Audiences: Everyone Is Invited
Contact: Computer Science Department