Skip to main content.
Advanced search >

Upcoming Events

Monday, August 28, 2017

Bin Yu — Three principles of data science: predictability, stability, and computability

Seminar: Distinguished Lecture Series | August 28 | 3:30-5 p.m. | 3108 Etcheverry Hall

Bin Yu, Professor, UC Berkeley Departments of Statistics and EECS

Industrial Engineering & Operations Research

In this talk, I'd like to discuss the intertwining importance and connections of three principles of data science in the title in data-driven decisions. Making prediction as its central task and embracing computation as its core, machine learning has enabled wide-ranging data-driven successes. Prediction is a useful way to check with reality. Good prediction implicitly assumes stability between...   More >

Monday, September 11, 2017

Yong Zeng — NSF Funding Opportunities Related to Data Science

Seminar: Distinguished Lecture Series | September 11 | 3:30-5 p.m. | 3108 Etcheverry Hall

Yong Zeng, National Science Foundation

Industrial Engineering & Operations Research

This presentation will provide an overview of the funding opportunities related to data science in National Science Foundation. The funding opportunities will include those in the directorates of Computer & Information Science & Engineering (CISE), Engineering (ENG), and Mathematical and Physical Sciences (MPS), and the focus will be those supported by Division of Mathematical Sciences (DMS) in MPS.

Monday, September 18, 2017

Matteo Basei - The coordination of centralised and distributed generation

Seminar | September 18 | 3:30-5 p.m. | 3108 Etcheverry Hall

Matteo Basei, UC Berkeley

Industrial Engineering & Operations Research

Abstract. This paper analyses the interaction between centralised carbon-emissive technologies and distributed intermittent non-emissive technologies. In our model, there is a representative consumer who can satisfy her electricity demand by investing in distributed generation (solar panels) and by buying power from a centralised firm at a price the firm sets. Distributed generation is...   More >

Monday, September 25, 2017

Adam Elmachtoub - The value of opaque products

Seminar: Distinguished Lecture Series | September 25 | 3:30-5 p.m. | 3108 Etcheverry Hall

Adam Elmachtoub, Columbia University

Industrial Engineering & Operations Research

Abstract: A product is said to be opaque if one or more of its attributes are not revealed until after the product has been sold. Opaque products have historically been used in the travel industry where airline and hotel brands might be hidden to the customer, in exchange for a discount. More recently, online retailers have also used opaque products, where customers can sacrifice their choice of...   More >

Monday, October 2, 2017

Nick Sahinidis — ALAMO: Machine learning from data and first principles

Seminar: Distinguished Lecture Series | October 2 | 3:30-5 p.m. | 3108 Etcheverry Hall

Nick Sahinidis, Carnegie Mellon University

Industrial Engineering & Operations Research

We have developed the ALAMO methodology with the aim of producing a tool capable of using data to learn algebraic models that are accurate and as simple as possible. ALAMO relies on (a) integer nonlinear optimization to build low-complexity models from input-output data, (b) derivative-free optimization to collect additional data points
that can be used to improve tentative models, and (c)...   More >

Monday, October 9, 2017

Peter Bartlett - Representation, optimization and generalization in deep learning

Seminar | October 9 | 3:30-5 p.m. | 3108 Etcheverry Hall

Peter Bartlett, UC Berkeley Departments of Statistics and EECS

Industrial Engineering & Operations Research

Deep neural networks have improved state-of-the-art performance for prediction problems across an impressive range of application areas, and they have become a central ingredient in AI systems. This talk considers factors that affect their performance, describing some recent results in two directions. First, we investigate the impact of depth on representation and optimization properties of these...   More >

Monday, October 16, 2017

Philip Protter - Issues of Incomplete Markets

Seminar | October 16 | 3:30-5 p.m. | 3108 Etcheverry Hall

Philip Protter, Columbia University

Industrial Engineering & Operations Research

Abstract: In a complete market, there is a unique risk neutral measure, unique prices, and all contingent claims can be (at least theoretically) perfectly hedged. In an incomplete market, in contrast, there is an infinite number of risk neutral measures, a continuum of “fair” prices, and contingent claims can in general not be perfectly hedged, even theoretically. Unfortunately, there seems to be...   More >

Monday, November 6, 2017

Bob Oliver — Fishy Predictions or Fish Stew

Seminar: Distinguished Lecture Series | November 6 | 3:30-5 p.m. | 3108 Etcheverry Hall

Bob Oliver, UC Berkeley IEOR

Industrial Engineering & Operations Research

Because of current federal laws on endangered fish species, water exports to California Aqueducts in San Joaquin Valley and Southern California are restricted by a combination of low Delta Smelt counts and densities in the Bay Delta and judgments by experts. This seminar suggests some ways in which Bayes’ Factors and combinations of forests of Information Odds Scores can help us improve our...   More >

Monday, November 20, 2017

Fatma Kilinc-Karzan — Online First-Order Framework for Robust Convex Optimization

Colloquium | November 20 | 3:30-5 p.m. | 3108 Etcheverry Hall

Fatma Kilinc-Karzan, Carnegie Mellon University

Industrial Engineering & Operations Research

Robust optimization (RO) has emerged as one of the leading paradigms to efficiently model parameter uncertainty. The recent connections between RO and problems in statistics and machine learning domains demand for solving RO problems in ever more larger scale. However, the traditional approaches for solving RO formulations based on building and solving robust counterparts or the iterative...   More >

Monday, November 27, 2017

Agostino Capponi - Bail-Ins And Bail-Outs: Incentives, Connectivity, And Systemic Stability

Seminar | November 27 | 3:30-5 p.m. | 3108 Etcheverry Hall

Agostino Capponi, Columbia University

Industrial Engineering & Operations Research

We develop a framework to analyze the consequences of alternative designs for interbank networks, in which a failure of one bank may lead to others. Earlier work had suggested that, provided shocks were not too large (or too correlated), denser networks were preferred to more sparsely connected networks because they were better able to absorb shocks. With large shocks, especially when systems are...   More >

Jon Lee — Comparing relaxations via volume for nonconvex optimization

Colloquium | November 27 | 3:30-5 p.m. | 3108 Etcheverry Hall

Jon Lee, University of Michigan

Industrial Engineering & Operations Research

Abstract: Practical exact methods for global optimization of mixed-integer nonlinear optimization formulations rely on convex relaxation. Then, one way or another (via refinement and/or disjunction), global optimality is sought. Success of this paradigm depends on balancing tightness and lightness of relaxations. We will investigate this from a mathematical viewpoint, comparing polyhedral...   More >