Sponsor
Statistical Science
seminar
Representation Learning: A Causal Perspective
Friday, November 11,
-
Speaker(s): Yixin Wang, Assistant Professor, Statistics, University of Michigan
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 capture.
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: https://arxiv.org/abs/2109.03795
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 capture.
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: https://arxiv.org/abs/2109.03795
