Yixin Wang, University of Michigan
When
TAP Computation and Data Initiative Lecturer, Yixin Wang, University of Michigan
Refreshments served from 1:00 - 1:30 in the 3rd Floor Atrium
Title: Representation Learning: A Casual Perspective
Abstract: Representation learning constructs low-dimensional
representations to summarize essential features of high-dimensional
data like images and texts. Ideally, such a representation should
efficiently capture non-spurious features of the data. It shall also
be disentangled so that we can interpret what feature each of its
dimensions captures. However, these desiderata are often intuitively
defined and challenging to quantify or enforce.
In this talk, we take on a causal perspective of representation
learning. We show how desiderata of representation learning can be
formalized using counterfactual notions, enabling metrics and
algorithms that target efficient, non-spurious, and disentangled
representations of data. We discuss the theoretical underpinnings of
the algorithm and illustrate its empirical performance in both
supervised and unsupervised representation learning.
This is joint work with Michael Jordan, Kartik Ahuja, Divyat Mahajan,
and Yoshua Bengio.
Bio: Yixin Wang is an assistant professor of statistics at the University
of Michigan. She works in the fields of Bayesian statistics, machine
learning, and causal inference. Previously, she was a postdoctoral
researcher with Professor Michael Jordan at the University of
California, Berkeley. She completed her PhD in statistics at Columbia,
advised by Professor David Blei, and her undergraduate studies in
mathematics and computer science at the Hong Kong University of
Science and Technology. Her research has been recognized by the j-ISBA
Blackwell-Rosenbluth Award, ICSA Conference Young Researcher Award,
ISBA Savage Award Honorable Mention, ACIC Tom Ten Have Award Honorable
Mention, and INFORMS data mining and COPA best paper awards.