Workshops

Fall 2020

Learning and Testing in High Dimensions

Dec 14, 2020 to Dec 18, 2020

Return to event »

This workshop is being live streamed on our website. Full participation (including the capacity to ask questions) will be available via Zoom webinar.

All talk times are in Pacific Time.

Monday, December 14th, 2020
8:30 am–8:50 am		Coffee and Check-In
8:50 am–9:00 am		Opening Remarks
9:00 am–9:30 am		Testing Monotonicity of Distributions Over High-Dimensional Posets Maryam Aliakbarpour (University of Massachusetts Amherst)
9:30 am–10:00 am		VC Dimension and Distribution-Free Sample-Based Testing Eric Blais (University of Waterloo)
10:00 am–10:15 am		Break
10:15 am–11:15 am		Testing Noisy Linear Functions for Sparsity Rocco Servedio (Columbia University)
11:15 am–11:30 am		Break
11:30 am–12:30 pm		Reduction From Non-Unique Games to Boolean Unique Games Dana Moshkovitz (University of Texas, Austin)
12:30 pm–12:45 pm		Break
12:45 pm–1:30 pm		Learning Ising Models from One, Ten or a Thousand Samples Costis Daskalakis (MIT)

Tuesday, December 15th, 2020
9:00 am–9:30 am		Learning and Testing for Gradient Descent Emmanuel Abbe (EPFL)
9:30 am–10:15 am		Counting and Sampling Subgraphs in Sublinear Time Talya Eden (MIT)
10:15 am–10:30 am		Break
10:30 am–11:15 am		Low-Degree Hardness of Random Optimization Problems Alex Wein (New York University)
11:15 am–11:30 am		Break
11:30 am–12:30 pm		Phase Transitions for Detecting Latent Geometry in Random Graphs Dheeraj Nagaraj (MIT)
12:30 pm–12:45 pm		Break
12:45 pm–1:30 pm		Recent Progress in Algorithmic Robust Statistics via the Sum-of-Squares Method Pravesh Kothari (CMU)

Wednesday, December 16th, 2020
9:00 am–9:30 am		SGD Learns One-Layer Networks in WGANs Qi Lei (Princeton University)
9:30 am–10:15 am		Analyzing Optimization and Generalization in Deep Learning via Dynamics of Gradient Descent Nadav Cohen (Tel-Aviv University)
10:15 am–10:30 am		Break
10:30 am–11:15 am		The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks in High Dimension Wei Hu (Princeton University)
11:15 am–11:30 am		Break
11:30 am–12:30 pm		Learning Deep ReLU Networks is Fixed-Parameter Tractable Sitan Chen (MIT)

Thursday, December 17th, 2020
9:00 am–9:45 am		Directed Graphical Models for Extreme Value Statistics Ngoc Tran (University of Texas, Austin)
9:45 am–10:30 am		Learning Some Ill-Conditioned Gaussian Graphical Models Raghu Meka (UCLA)
10:30 am–10:45 am		Break
10:45 am–11:30 am		Near-Optimal Learning of Tree-Structured Distributions by Chow-Liu Eric Price (University of Texas, Austin)
11:30 am–11:45 am		Break
11:45 am–12:30 pm		Hardness of Identity Testing for Potts models and RBMs Antonio Blanca (Penn State)

Friday, December 18th, 2020
9:00 am–9:30 am		Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models Daniel Kane (UCSD)
9:30 am–10:15 am		An Equivalence Between Private Classification and Online Prediction Shay Moran (Technion)
10:15 am–10:30 am		Break
10:30 am–11:15 am		Testing and Reconstruction via Decision Trees Li-Yang Tan (Stanford University)
11:15 am–11:30 am		Break
11:30 am–12:30 pm		Recent Developments in Supervised Learning With Noise Ilias Diakonikolas (UW Madison)