Schedule for: 21w5070 - Mathematical Statistics and Learning

Beginning on Sunday, November 28 and ending Friday December 3, 2021

All times in Banff, Alberta time, MST (UTC-7).

Sunday, November 28
16:00 - 17:30 Check-in begins at 16:00 on Sunday and is open 24 hours (Front Desk - Professional Development Centre)
17:30 - 19:30 Dinner (KC 101)
Monday, November 29
07:00 - 08:45 Breakfast (KC 101)
08:45 - 09:00 Introduction and Welcome by BIRS Staff (TCPL 201)
09:00 - 10:00 Schramm Tselil: The Sum-of-Squares Algorithmic Paradigm in Statistics (TCPL 201)
10:00 - 10:30 Coffee Break (TCPL Foyer)
10:30 - 11:00 Bin Yu: Provable Recovery of Boolean Interactions based on Random Forests (Online)
11:00 - 11:30 Andrea Montanari: Tractability from overparametrization: The example of the negative perceptron (Online)
11:30 - 13:30 Lunch (KC 101)
13:00 - 14:00 Tour of Banff Centre (PDC Front Desk)
13:30 - 14:00 Roberto Imbuzeiro Oliveira: The contact process over a switching random d-regular graph (Online)
14:00 - 14:20 Group Photo (TCPL Foyer)
14:20 - 14:50 Ilias Diakonikolas: Non-Gaussian Component Analysis: Statistical Query Hardness and its Applications (Online)
15:00 - 15:30 Coffee Break (TCPL Foyer)
17:00 - 17:30 Gautam Kamath: Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism (TCPL 201)
17:30 - 19:30 Dinner (KC 101)
17:30 - 18:00 Cynthia Rush: Variational Inference and Robustness (TCPL 201)
Tuesday, November 30
07:00 - 08:45 Breakfast (KC 101)
09:00 - 10:00 Schramm Tselil: The Sum-of-Squares Algorithmic Paradigm in Statistics (TCPL 201)
10:00 - 10:30 Coffee Break (TCPL Foyer)
10:30 - 11:00 Andrew Nobel: Estimation of Stationary Optimal Transport Plans (Online)
11:00 - 11:30 Yury Polyanskiy: Rates of convergence of Gaussian smoothed empirical measures in Wasserstein and KL distances (Online)
11:30 - 13:30 Lunch (KC 101)
13:30 - 14:00 Yihong Wu: Self-regularization of nonparametric maximum likelihood in mixture models (Online)
14:00 - 14:30 Ery Arias-Castro: On Using Graph Distances to Estimate Euclidean and Related Distances (Online)
14:30 - 15:00 Nikita Zhivotovskiy: Some recent results on Algorithmic Stability (Online)
15:00 - 15:30 Coffee Break (TCPL Foyer)
17:00 - 17:30 Csaba Szepesvari: Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting (TCPL 201)
17:30 - 18:00 Tselil Schramm: Testing thresholds for sparse random geometric graphs (TCPL 201)
18:00 - 19:30 Dinner (KC 101)
Wednesday, December 1
07:00 - 08:45 Breakfast (KC 101)
09:00 - 10:00 Schramm Tselil: The Sum-of-Squares Algorithmic Paradigm in Statistics (TCPL 201)
10:00 - 10:30 Coffee Break (TCPL Foyer)
10:30 - 11:00 Varun Jog: Communication-efficient hypothesis testing (Online)
11:00 - 11:30 Emilie Kaufmann: Non-parametric exploration in multi-armed bandits (Online)
11:30 - 13:30 Lunch (KC 101)
11:30 - 12:00 Gergely Neu: A convex-analytic theory of generalization (TCPL 201)
16:30 - 17:00 Morgane Austern (Online)
17:00 - 17:30 Shai Ben-David: Fundamental models of statistical learning and their combinatorial characterizations - negative results and implied open problems (Online)
17:30 - 19:30 Dinner (KC 101)
17:30 - 18:00 Peter Bartlett: Adversarial examples in deep networks (TCPL 201)
Thursday, December 2
07:00 - 08:45 Breakfast (KC 101)
09:00 - 10:00 Schramm Tselil: The Sum-of-Squares Algorithmic Paradigm in Statistics (TCPL 201)
10:00 - 10:30 Coffee Break (TCPL Foyer)
10:30 - 11:00 Miklos Racz: Correlated stochastic block models: graph matching and community recovery (Online)
11:00 - 11:30 Afonso Bandeira: Noncommutative Matrix Concentration Inequalities (Online)
11:30 - 13:30 Lunch (KC 101)
15:00 - 15:30 Coffee Break (TCPL Foyer)
17:30 - 19:30 Dinner (KC 101)
19:00 - 21:00 Luc Devroye: Mixing time (TCPL 201)
Friday, December 3
07:00 - 08:45 Breakfast (KC 101)
10:00 - 10:30 Coffee Break (TCPL Foyer)
11:30 - 12:00 Checkout by 11AM (Front Desk - Professional Development Centre)
12:00 - 13:30 Lunch from 11:30 to 13:30 (KC 101)