Optimization, Statistics and Uncertainty

Program

Bridging Continuous and Discrete Optimization

Location

Calvin Lab Auditorium

Date

Tuesday, Nov. 28 – Friday, Dec. 1, 2017

Back to calendar

Click on the titles of individual talks for abstract, slides and archived video.

9 – 9:20 a.m.

Coffee and Check-In

9:20 – 9:30 a.m.

Opening Remarks

9:30 – 10:30 a.m.

Data Driven Optimization Models and Algorithms

Yinyu Ye, Stanford University

10:30 – 11 a.m.

Break

11 – 11:30 a.m.

Regularized Nonlinear Acceleration

Alex d'Aspremont, École Normale Supérieure

11:30 a.m. – 12 p.m.

Learning One-hidden-layer Neural Networks with Landscape Design

Tengyu Ma, Stanford University

12 – 2 p.m.

Lunch

2 – 2:30 p.m.

Algorithmic Stability for Interactive Data Analysis

Jonathan Ullman, Northeastern University

2:30 – 3 p.m.

Preventing Overfitting in Adaptive Data Analysis via Stability

Thomas Steinke, IBM Almaden

3 – 3:30 p.m.

Break

3:30 – 4 p.m.

The Convergence of Hamiltonian Monte Carlo

Santosh Vempala, Georgia Institute of Technology

4 – 4:30 p.m.

Distributional Robustness, Learning, and Empirical Likelihood

John Duchi, Stanford University

4:30 – 5:30 p.m.

Reception

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:30 a.m.

An Instability in Variational Methods for Learning Topic Models

Andrea Montanari, Stanford University

10:30 – 11 a.m.

Break

11 – 11:30 a.m.

A Few Connections Between Optimization and Probability

Sasha Rakhlin, University of Pennsylvania

11:30 a.m. – 12 p.m.

Implicit Regularization in Nonconvex Statistical Estimation

Yuxin Chen, Princeton University

12 – 2 p.m.

Lunch

2 – 3 p.m.

Low-rank Matrix Completion: Adaptive Sampling Can Help When, How?

Rachel Ward, University of Texas at Austin

3 – 3:30 p.m.

Break

3:30 – 4:30 p.m.

Open Problem Session

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:30 a.m.

Graph Powering

Emmanuel Abbe, Princeton University

10:30 – 11 a.m.

Break

11 – 11:30 a.m.

On Approximation Guarantees for Greedy Low Rank Optimization

Sahand Negahban, Yale University

11:30 a.m. – 12 p.m.

Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

Quentin Berthet, University of Cambridge

12 – 2 p.m.

Lunch

2 – 3 p.m.

Optimization's Untold Gift to Learning: Implicit Regularization

Nathan Srebro Bartom, Toyota Technological Institute at Chicago

3 – 3:30 p.m.

Break

3:30 – 4 p.m.

The Power and Limitations of Kernel Learning

Misha Belkin, Ohio State University

4 – 4:30 p.m.

Sampling Algorithms for Combinatorial Pure Exploration

Anupam Gupta, Carnegie Mellon University

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:30 a.m.

Compositional Properties of Statistical Procedures: An Information-Theoretic View

Max Raginsky, University of Illinois at Urbana-Champaign

10:30 – 11 a.m.

Break

11 – 11:30 a.m.

Stability and Convergence Trade-Off of Iterative Optimization Algorithms

Bin Yu, UC Berkeley

11:30 a.m. – 12 p.m.

Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained Empirical Risk Minimization

Katrina Ligett, Hebrew University of Jerusalem