[AI Seminar] Fwd: OR Seminar on Friday, November 11, 2016
arielpro at cs.cmu.edu
Fri Nov 4 13:04:27 EDT 2016
Talk of possible interest.
---------- Forwarded message ----------
From: Willem-Jan van Hoeve <vanhoeve at andrew.cmu.edu>
Date: Fri, Nov 4, 2016 at 12:38 PM
Subject: Fwd: OR Seminar on Friday, November 11, 2016
To: arielpro at cs.cmu.edu
Next week's OR seminar may be of interest to attendants of the AI seminar
Could you please forward the announcement via the AI Lunch Seminar
-------- Forwarded Message --------
Subject: OR Seminar on Friday, November 11, 2016
Date: Fri, 4 Nov 2016 08:21:23 -0400
From: maobrien at andrew.cmu.edu
To: vanhoeve at andrew.cmu.edu
**Distributed via the Faculty Services mail distribution system.**
The below OR seminar is posted at: https://econ.tepper.cmu.edu/Se
Please take the time to schedule a meeting with the speaker on an
individual basis When you are at the seminar site, proceed to this
seminar. To add yourself for a meeting, click on View/Edit Schedule link
and then click on the Edit Schedule link. Enter the name portion of your
e-mail address (the @andrew.cmu.edu part is not needed) and click Update at
bottom of page.
Name: Dimitris Bertsimas, MIT
Date: Friday, November 11, 2016
Time: 1:30 to 3:00 pm
Location: Faculty Conference Room 322
Title: Machine learning and statistics via a modern optimization lens
Abstract: The field of Statistics has historically been linked with
Probability Theory. However, some of the central problems of
classification, regression and estimation can naturally be written as
optimization problems. While continuous optimization approaches has had a
significant impact in Statistics, mixed integer optimization (MIO) has
played a very limited role, primarily based on the belief that MIO models
are computationally intractable. The period 1991-2015 has witnessed a)
algorithmic advances in mixed integer optimization (MIO), which coupled
with hardware improvements have resulted in an astonishing 450 billion
factor speedup in solving MIO problems, b) significant advances in our
ability to model and solve very high dimensional robust and convex
In this talk, we demonstrate that modern convex, robust and especially
mixed integer optimization methods, when applied to a variety of classical
Machine Learning (ML) /Statistics (S) problems can lead to certifiable
optimal solutions for large scale instances that have often significantly
improved out of sample accuracy compared to heuristic methods used in
ML/S. Specifically, we report results on
1) The classical variable selection problem in regression currently
solved by Lasso heuristically.
2) We show that robustness and not sparsity is the major reason of the
success of Lasso in contrast to widely held beliefs in ML/S.
3) A systematic approach to design linear and logistic regression
models based on MIO.
4) Optimal trees for classification solved by CART heuristically.
5) Robust classification including robust Logistic regression, robust
optimal trees and robust support vector machines.
6) Sparse matrix estimation problems: Principal Component Analysis,
Factor Analysis and Covariance matrix estimation.
In all cases we demonstrate that optimal solutions to large scale instances
(a) can be found in seconds, (b) can be certified to be optimal in minutes
and (c) outperform classical approaches. Most importantly, this body of
work suggests that linking ML/S to modern optimization leads to significant
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the ai-seminar-announce