Workshops

Fall 2017

Optimization, Statistics and Uncertainty

Nov. 28 – Dec. 1, 2017

Return to event »

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

All events take place in the Calvin Lab auditorium.

Tuesday, November 28th, 2017
9:00 am – 9:20 am		Coffee and Check-In
9:20 am – 9:30 am		Opening Remarks
9:30 am – 10:30 am		Data Driven Optimization Models and Algorithms Yinyu Ye, Stanford University
10:30 am – 11:00 am		Break
11:00 am – 11:30 am		Regularized Nonlinear Acceleration Alex d'Aspremont, École Normale Supérieure
11:30 am – 12:00 pm		Learning One-hidden-layer Neural Networks with Landscape Design Tengyu Ma, Stanford University
12:00 pm – 2:00 pm		Lunch
2:00 pm – 2:30 pm		Algorithmic Stability for Interactive Data Analysis Jonathan Ullman, Northeastern University
2:30 pm – 3:00 pm		Preventing Overfitting in Adaptive Data Analysis via Stability Thomas Steinke, IBM Almaden
3:00 pm – 3:30 pm		Break
3:30 pm – 4:00 pm		The Convergence of Hamiltonian Monte Carlo Santosh Vempala, Georgia Institute of Technology
4:00 pm – 4:30 pm		Distributional Robustness, Learning, and Empirical Likelihood John Duchi, Stanford University
4:30 pm – 5:30 pm		Reception

Wednesday, November 29th, 2017
9:00 am – 9:30 am		Coffee and Check-In
9:30 am – 10:30 am		An Instability in Variational Methods for Learning Topic Models Andrea Montanari, Stanford University
10:30 am – 11:00 am		Break
11:00 am – 11:30 am		A Few Connections Between Optimization and Probability Sasha Rakhlin, University of Pennsylvania
11:30 am – 12:00 pm		Implicit Regularization in Nonconvex Statistical Estimation Yuxin Chen, Princeton University
12:00 pm – 2:00 pm		Lunch
2:00 pm – 3:00 pm		Low-rank Matrix Completion: Adaptive Sampling Can Help When, How? Rachel Ward, University of Texas at Austin
3:00 pm – 3:30 pm		Break
3:30 pm – 4:30 pm		Open Problem Session

Thursday, November 30th, 2017
9:00 am – 9:30 am		Coffee and Check-In
9:30 am – 10:30 am		Graph Powering Emmanuel Abbe, Princeton University
10:30 am – 11:00 am		Break
11:00 am – 11:30 am		On Approximation Guarantees for Greedy Low Rank Optimization Sahand Negahban, Yale University
11:30 am – 12:00 pm		Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe Quentin Berthet, University of Cambridge
12:00 pm – 2:00 pm		Lunch
2:00 pm – 3:00 pm		Optimization's Untold Gift to Learning: Implicit Regularization Nathan Srebro Bartom, Toyota Technological Institute at Chicago
3:00 pm – 3:30 pm		Break
3:30 pm – 4:00 pm		The Power and Limitations of Kernel Learning Misha Belkin, Ohio State University
4:00 pm – 4:30 pm		Sampling Algorithms for Combinatorial Pure Exploration Anupam Gupta, Carnegie Mellon University

Friday, December 1st, 2017
9:00 am – 9:30 am		Coffee and Check-In
9:30 am – 10:30 am		Compositional Properties of Statistical Procedures: An Information-Theoretic View Max Raginsky, University of Illinois at Urbana-Champaign
10:30 am – 11:00 am		Break
11:00 am – 11:30 am		Stability and Convergence Trade-Off of Iterative Optimization Algorithms Bin Yu, UC Berkeley
11:30 am – 12:00 pm		Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained Empirical Risk Minimization Katrina Ligett, Hebrew University of Jerusalem