Colloquium Series

The Contextual Bandits Problem: A Fast, Simple, and Optimal Algorithm 2017

Thursday, May 4, 2017 (All day)
Columbia University
New York, NY 10027
United States

Colloquium Series: Dr. Robert Schapire
Principal Researcher, Microsoft Research (NYC)

We study the general problem of how to learn through experience to make intelligent decisions.  In this setting, called the contextual bandits problem, the learner must repeatedly decide which action to take in response to an observed context, and is then permitted to observe the received reward, but only for the chosen action.  The goal is to learn through experience to behave nearly as well as the best policy (or decision rule) in some possibly very large and rich space of candidate policies.  Previous approaches to this problem were all highly inefficient and often extremely complicated.  In this work, we present a fast and simple algorithm that learns to behave as well as the best policy at a rate that is (almost) statistically optimal.  Our approach assumes access to a kind of “oracle” (or subroutine) for classification learning problems which can be used to select policies; in practice, most off-the-shelf classification algorithms could be used for this purpose.  Our algorithm makes very modest use of the oracle, which it calls far less than once per round, on average, a huge improvement over previous methods.  These properties suggest this may be the most practical contextual bandits algorithm among all existing approaches that are provably effective for general policy classes.

This is joint work with Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford and Lihong Li. 

Data Science Institute Colloquium: Dr. Michael Winter, Pratt & Whitney

Wednesday, April 26, 2017 - 5:00pm to 6:00pm
United States

Michael Winter, Advancted TechnologiesDr. Michael Winter
Senior Fellow, Advanced Technology
Pratt & Whitney, United Technologies Corporation

Systems Engineering: Imperatives, Definitions, Technology & Talent

The lecture will present the motivation, mechanics, and methodologies of model-based systems engineering as applied to product platforms and infrastructures that are often safety or operationally critical. Cyber-physical system-of-systems that combine both physics and controls form the basis of modern society. Application of systems engineering principles in an analytic context with focus on requirements, architecture, model-based development, and design flows will be presented as applied in an industrial context.

Once Upon a Graph: How to Get from Now to Then in Massive Networks

Thursday, April 20, 2017 - 5:00pm to 6:00pm
Davis Auditorium | The Schapiro Center
Columbia University
New York, NY 10027
United States

The Distinguished Colloquium Series in Interdisciplinary and Applied Mathematics, along with Columbia's Data Science Institute, proudly present a lecture by:

Jennifer Tour Chayes
Distinguished Scientist and Managing Director of Microsoft Research New England, Cambridge, MA.

Title: "Once upon a graph: How to get from now to then in massive networks"

Data Science Institute Colloquium, Faculty Spotlight: John Paisley

Thursday, March 23, 2017 - 5:00pm to 6:00pm
United States

John Paisley, Assistant Professor of Electrical Engineering TITLE: Structured and Scalable Probabilistic Topic Models ABSTRACT: Advances in scalable machine learning have made it possible to learn highly structured models on large data sets. In this talk, I will discuss some of our recent work in this direction. I will first briefly review scalable probabilistic topic modeling with stochastic variational inference. I will then then discuss two structured developments of the LDA model in the form of tree-structured topic models and graph-structured topic models.

Data Science Institute Colloquium, Faculty Spotlight: Suman Jana

Tuesday, March 7, 2017 - 5:00pm to 6:00pm
United States

Securing Software Systems: Beyond Whack-A-Mole

Data Science Institute Colloquium | Faculty Spotlight: Suman Jana

Developing secure software is notoriously hard! Security vulnerabilities resulting from software bugs cost our economy billions of dollars every year. Unfortunately, the current “whack-a-mole” approach to fixing bugs as they show up often break more things than they fix. In this talk, I will describe some of the fundamental challenges in software security and summarize the progress made towards solving them in the last decade. I'll also provide a broad overview of several principled approaches that software developers can follow to improve the robustness of software systems against malicious attackers.

Suman Jana is an Assistant Professor in the Department of Computer Science at Columbia University. His primary research interests are in the areas of computer security and privacy. More specifically, he is interested in building automated tools for finding and fixing security and privacy vulnerabilities. He also occasionally delves into software engineering and operating systems.

Data Science Institute Colloquium: Air Force Lt. Gen. William J. “Bill” Bender

Wednesday, March 8, 2017 - 2:00pm to 3:00pm
United States

Air Force Lt. Gen. William J. “Bill” Bender Chief, Information Dominance and Chief Information Officer Office of the Secretary of the Air Force TITLE: Online at the Front Line: Air Force Cybersecurity and the Challenge of Winning Wars in the Digital Age ABSTRACT: The U.S. Air Force was the world’s dominant air force in the industrial age – is it prepared to win in the digital era? Lt. Gen.

Data Science Institute Colloquium: Dr. James Ang

Friday, January 20, 2017 - 11:00am to 12:15pm
United States

The National Strategic Computing Initiative (NSCI) and Synergistic Opportunities for Massive-Scale Scientific and Data Analytic Computing On July 29, 2015, President Obama signed an Executive Order to establish the National Strategic Computing Initiative (NSCI), a whole-of-nation effort to sustain and enhance U.S. leadership in high-performance computing (HPC). This talk is framed by the five objectives of NSCI, and will focus on an overview of the first two.

Data, Polling, the Media and Democracy: Election 2016

Tuesday, December 6, 2016 - 5:30pm to 7:00pm
Rotunda, Low Memorial Library
Columbia University in the City of New York
New York, NY
United States
  Data & Society Taskforce, Columbia University
A panel discussion of Election 2016 featuring:
Nate Silver
Founder and Editor in Chief, FiveThirtyEight
Emily Bell
Director of the Tow Center for Digital Journalism, Columbia University
Robert Shapiro
Wallace S. Sayre Professor of Political Science, Columbia University
Ester Fuchs (Moderator)
Professor of International and Public Affairs and Political Science, Columbia University
Data, Polling, the Media and Democracy
Tuesday, December 6, 2016
5:30–7:00 p.m. (Doors open at 5:00 p.m.)
Rotunda, Low Memorial Library
Columbia University in the City of New York
Opening Remarks by David Madigan, Executive Vice President for Arts and Sciences, Professor of Statistics, Columbia University
Convened by President Bollinger and Provost Coatsworth, the Data & Society Taskforce is comprised of Deans and faculty from across the Columbia community with a special interest in data science and its impact on education and research at Columbia. The Taskforce is led by Mary Boyce, Dean of Engineering and Applied Science, and David Madigan, EVP for Arts & Sciences.
Sponsored by the Data Science Institute, Columbia University
 


Pages

Subscribe to RSS - Colloquium Series
Back to Top