Deep Learning Theory Workshop and Summer School

Program

Summer Cluster: Deep Learning Theory

Location

Calvin Lab Auditorium

Date

Monday, Aug. 1 – Friday, Aug. 5, 2022

Back to calendar

9 – 9:25 a.m.

Coffee and Check-In

9:25 – 9:30 a.m.

Opening Remarks

9:30 – 10:30 a.m.

Tutorial: Statistical Learning Theory, Optimization, and Neural Networks I

Spencer Frei (UC Davis)

10:30 – 11 a.m.

Break

11 a.m. – 12 p.m.

Tutorial: Statistical Learning Theory, Optimization, and Neural Networks II

Spencer Frei (UC Davis)

12 – 1:30 p.m.

Lunch

1:30 – 2:30 p.m.

Understanding the Robustness of Deep Learning

Aditi Raghunathan (Stanford)

2:30 – 3 p.m.

Break

3 – 4 p.m.

Feature Selection with Gradient Descent on Two-layer Networks in Low-rotation Regimes

Matus Telgarsky (New York University)

4 – 6 p.m.

Reception

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:45 a.m.

Tutorial: Implicit Bias I

Nati Srebro (Toyota Technological Institute at Chicago)

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12:30 p.m.

Tutorial: Implicit Bias II

Nati Srebro (Toyota Technological Institute at Chicago)

12:30 – 2:30 p.m.

Lunch

2:30 – 3:30 p.m.

The Devil is in the Tails and Other Stories of Interpolation

Niladri Chatterji (UC Berkeley)

3:30 – 4 p.m.

Break

4 – 5 p.m.

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting

Neil Mallinar (UCSD),
Preetum Nakkiran (Apple Inc)

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:30 a.m.

Tutorial: Methods from Statistical Physics I

Ahmed El Alaoui (Cornell)

10:30 – 11 a.m.

Break

11 a.m. – 12 p.m.

Tutorial: Methods from Statistical Physics II

Ahmed El Alaoui (Cornell)

12 – 1:30 p.m.

Lunch

1:30 – 2:30 p.m.

Panel: Perspectives on Machine Learning and Statistics

2:30 – 2:45 p.m.

Break

2:45 – 3:45 p.m.

Distribution Shift as Underspecification, and What We Might Do About It

Chelsea Finn (Stanford)

3:45 – 4 p.m.

Break

4 – 5 p.m.

A New Perspective on High-Dimensional Causal Inference

Pragya Sur (Harvard)

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:45 a.m.

Tutorial: Methods from Statistical Physics III

Ahmed El Alaoui (Cornell)

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12:30 p.m.

Tutorial: Training & Deploying Multi-Modal Models

Brandon McKinzie (Apple)

12:30 – 2:30 p.m.

Lunch

2:30 – 3:30 p.m.

A Theoretical Framework of Convolutional Kernels on Image Datasets

Song Mei (UC Berkeley)

3:30 – 4 p.m.

Break

4 – 5 p.m.

Universality of Approximate Message Passing on Semi-random Matrices

Subhabrata Sen (Harvard University)

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:45 a.m.

When is Scale Enough?

Ethan Dyer (Google Research, Blueshift Team)

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12:30 p.m.

Deep Learning in Structural Biology and Protein Design: How, Where, and Why

Chloe Hsu (UC Berkeley)

12:15 – 12:20 p.m.

Concluding Remarks