[Colloquium] REMINDER: [TTIC Talks] 3/6 Talks at TTIC: Ke Li, Berkeley

Alicia McClarin amcclarin at ttic.edu
Wed Mar 6 09:59:36 CST 2019


When:    Wednesday, March 6th at *11:00 am*

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:       Ke Li, Berkeley

*Title:*       Nearest Neighbour Search and Generative Modelling

*Abstract:* Machine learning is subject to the limits of computation, and
advances in algorithms can open up new possibilities for machine learning.
The problem of nearest neighbour search arises commonly in machine
learning; unfortunately, despite over 40 years of research, prior sublinear
algorithms for exact nearest neighbour search suffer from the curse of
dimensionality, that is, an exponential dependence of query time complexity
on either the ambient or the intrinsic dimensionality. In the first part of
this talk, I will present Dynamic Continuous Indexing (DCI), a new family
of exact randomized algorithms that avoids exponential dependence on both
the ambient and the intrinsic dimensionality. This advance enables us to
develop a new method for generative modelling, known as Implicit Maximum
Likelihood Estimation (IMLE), which I will present in the second part of
the talk. IMLE can be shown to be equivalent to maximum likelihood under
some conditions and simultaneously overcomes three fundamental issues of
generative adversarial nets (GANs), namely mode collapse, vanishing
gradients and training instability. I will illustrate why mode collapse
happens in GANs and how IMLE overcomes it, and also demonstrate empirical
results on image synthesis. I will close off with a brief discussion of
another approach I introduced, known as Learning to Optimize.

*Host:*  Greg Shakhnarovich <greg at ttic.edu>

-- 
*Alicia McClarin*
*Toyota Technological Institute at Chicago*
*6045 S. Kenwood Ave., **Office 510*
*Chicago, IL 60637*
*773-702-5370*
*www.ttic.edu* <http://www.ttic.edu/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20190306/ac26dad9/attachment.html>


More information about the Colloquium mailing list