Modern Paradigms in Generalization Boot Camp

Program

Modern Paradigms in Generalization

Location

Calvin Lab Auditorium

Date

Tuesday, Aug. 27 – Friday, Aug. 30, 2024

Back to calendar

8:30 – 8:45 a.m.

Coffee and Check-In

8:45 – 10 a.m.

Modern paradigms of generalization, the heliocentric model of Aristarchus, gradient descent is a lazy scientist, and other stories

Matus Telgarsky (Courant Institute, NYU)

10 – 10:15 a.m.

Break

10:15 – 11:30 a.m.

Towards Understanding Generalization Properties of Score-Based Losses

Andrej Risteski (Carnegie Mellon University)

11:30 a.m. – 1:30 p.m.

Lunch (on your own)

1:30 – 2:45 p.m.

Overview of Statistical Learning Theory Part 1

Nati Srebro (Toyota Technological Institute at Chicago)

2:45 – 3 p.m.

Break

3 – 4:15 p.m.

Generalization in natural language processing

Alane Suhr (University of California, Berkeley)

4:15 – 5 p.m.

Reception

8:30 – 8:45 a.m.

Coffee and Check-In

8:45 – 10 a.m.

Prediction, Generalization, Complexity: Revisiting the Classical View from Statistics Part 1

Ryan Tibshirani (University of California, Berkeley)

10 – 10:15 a.m.

Break

10:15 – 11:30 a.m.

Robust Optimization and Generalization

John Duchi (Stanford University)

11:30 a.m. – 1 p.m.

Lunch (on your own)

1 – 2:15 p.m.

An overview of classical robust statistics and generalizations to the future

Po-Ling Loh (University of Cambridge)

2:15 – 2:30 p.m.

Break

2:30 – 3:30 p.m.

Prediction, Generalization, Complexity: Revisiting the Classical View from Statistics Part 2

Ryan Tibshirani (University of California, Berkeley)

3:30 – 3:45 p.m.

Break

3:45 – 4:45 p.m.

Overview of Statistical Learning Theory Part 2

Nati Srebro (Toyota Technological Institute at Chicago)

8:30 – 8:45 a.m.

Coffee and Check-In

8:45 – 10 a.m.

Statistical Limits of Causal Inference

Sivaraman Balakrishnan (Carnegie Mellon University)

10 – 10:15 a.m.

Break

10:15 – 11:30 a.m.

TBD

Zico Kolter (CMU Bosch)

11:30 a.m. – 12:45 p.m.

Lunch (on your own)

12:45 – 2 p.m.

Learning probability distributions; what can, what can't be done (virtual)

Shai Ben-David (University of Waterloo)

2 – 2:15 p.m.

Break

2:15 – 3:30 p.m.

Understanding Generalization from Pre-training Loss to Downstream Tasks

Tengyu Ma (Stanford University)

3:30 – 3:45 p.m.

Break

3:45 – 5 p.m.

A Theory of Multi-objective Machine Learning

Nika Haghtalab (University of California, Berkeley)

8:30 – 8:45 a.m.

Coffee and Check-In

8:45 – 10 a.m.

Reconsidering Overfitting in the Age of Overparameterized Models (virtual)

Fanny Yang (ETH Zurich)

10 – 10:15 a.m.

Break

10:15 – 11:30 a.m.

The elusive generalization: classical bounds to double descent to grokking

Misha Belkin (University of California, San Diego)

11:30 a.m. – 1:30 p.m.

Lunch (on your own)

1:30 – 2:45 p.m.

Measures of relatedness in domain adaptation and related problems.

Samory Kpotufe (Columbia University)

2:45 – 3 p.m.

Break

3 – 4:45 p.m.

Above Average-Case Analysis

Ankur Moitra (Massachusetts Institute of Technology)

4:45 – 5 p.m.

Closing