[Colloquium] 2/15 Talks at TTIC: Zhaoran Wang, Princeton

[Mary Marre via Colloquium]

When:     Wednesday, February 15th at 11:00 am

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

Who:       Zhaoran Wang, Princeton


Title: Taming Nonconvexity with Data

Abstract: Nonconvex optimization is becoming one of the most powerful
workhorses of data science and artificial intelligence. Compared with
convex optimization, it enjoys superior statistical accuracy, computational
efficiency, and modeling flexibility in modern scenarios. However, the
empirical success of nonconvex optimization largely eludes the reach of
classical statistical and optimization theory, which prohibits us from
designing more efficient algorithms in a principled manner.

In this talk, I will illustrate how statistical thinking enables us to
harness the power of nonconvex optimization. In particular, I will
present an algorithmic framework for exploiting the latent geometry induced
by the randomness of data. By integrating three new global exploration
meta-algorithms — namely, homotopy continuation, tightening after
relaxation, and noise regularization — with local search heuristics such as
gradient descent, this unified framework leads to new nonconvex
optimization algorithms for a wide variety of challenging learning
problems, which enjoy provably optimal statistical accuracy and
computational efficiency. Time permitting, I will also discuss the
corresponding statistical-computational tradeoffs.

Bio: Zhaoran is a graduate student at Princeton University, working at the
interface of machine learning, statistics, and optimization. He is the
recipient of the AISTATS notable paper award, ASA best student paper in
statistical learning and data mining, INFORMS best student paper finalist
in data mining, and the Microsoft fellowship.

Host: Yury Makarychev <yury at ttic.edu>



Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757 <(773)%20834-1757>*
*f: (773) 357-6970 <(773)%20357-6970>*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20170210/20589f8a/attachment.html>