Skip to main content

Utility navigation

  • Calendar
  • Contact
  • Login
  • MAKE A GIFT
Berkeley University of California
Home Home

Main navigation

  • Home
  • Programs & Events
    • Research Programs
    • Workshops & Symposia
    • Public Lectures
    • Research Pods
    • Internal Program Activities
    • Algorithms, Society, and the Law
  • People
    • Scientific Leadership
    • Staff
    • Current Long-Term Visitors
    • Research Fellows
    • Postdoctoral Researchers
    • Scientific Advisory Board
    • Governance Board
    • Industry Advisory Council
    • Affiliated Faculty
    • Science Communicators in Residence
    • Law and Society Fellows
  • Participate
    • Apply to Participate
    • Plan Your Visit
    • Location & Directions
    • Postdoctoral Research Fellowships
    • Law and Society Fellowships
    • Science Communicator in Residence Program
    • Circles
    • Breakthroughs Workshops and Goldwasser Exploratory Workshops
  • Support
    • Annual Fund
    • Funders
    • Industrial Partnerships
  • News & Videos
    • News
    • Videos
  • About
Image

Deep Learning Reunion

Program
Foundations of Deep Learning
Location

<p>Zoom</p>

Date
Monday, Aug. 10 – Thursday, Aug. 13, 2020
Back to calendar

Breadcrumb

  1. Home
  2. Workshop & Symposia
  3. Schedule

Secondary tabs

  • The Workshop
  • Schedule

9:50 – 10 a.m.
Opening Remarks
10 – 10:15 a.m.
Benign Overfitting and Double Descent
Peter Bartlett (UC Berkeley)
10:15 – 10:30 a.m.
Toward a Theory of Optimization for Over-Parameterized Systems of Non-Linear Equations: The Lessons of Deep Learning
Misha Belkin (UC San Diego)
10:30 – 10:45 a.m.
Overparameterization in Regression vs Classification Problems
Anant Sahai (UC Berkeley)
10:45 – 11 a.m.
Two Vignettes on Narrow Networks
Matus Telgarsky (University of Illinois)
11 – 11:15 a.m.
Finite vs. Infinite Neural Networks
Jascha Sohl-Dickstein (Google Brain)
11:15 a.m. – 12:15 p.m.
Gather.town
12:15 – 1 p.m.
Break
1 – 1:15 p.m.
The Large Learning Rate Phase of Deep Learning
Yasaman Bahri (Google Brain)
1:15 – 1:30 p.m.
Finite-Sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime
Phil Long (Google)
1:30 – 1:45 p.m.
Chasing the Long Tail: What Neural Networks Memorize and Why
Vitaly Feldman (Apple)
1:45 – 2 p.m.
On Uniform Convergence and Interpolation Learning
Nati Srebo (Toyota Technical Institute at Chicago)
2 – 2:15 p.m.
Approximation Schemes for ReLU Regression
Surbhi Goel (Microsoft Research)
2:15 – 3:15 p.m.
Gather.town
10 – 10:15 a.m.
Reverse Isoperimetric Inequalities for Adversarial Machine Learning
Varun Jog (University of Wisconsin, Madison)
10:15 – 10:30 a.m.
Precise Tradeoffs in Adversarial Training
Mahdi Soltanolkotabi (University of Southern California)
10:30 – 10:45 a.m.
Extracting Robust and Accurate Features via a Robust Information Bottleneck
Po-Ling Loh (University of Wisconsin, Madison)
10:45 – 11 a.m.
Neural Perceptual Adversarial Robustness: Generalizable Defenses to Unforeseen Attacks
Soheil Feizi (University of Maryland)
11 – 11:15 a.m.
A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
Quanquan Gu (UCLA)
11:15 a.m. – 12:15 p.m.
Gather.town
12:15 – 1 p.m.
Break
1 – 1:15 p.m.
The Implicit Regularization of Stochastic Gradient Flow for Least Squares
Edgar Dobriban (University of Pennsylvania)
1:15 – 1:30 p.m.
The Complexity of Non-Convex Stochastic Optimization
Dylan Foster (MIT)
1:30 – 1:45 p.m.
Initialization Scale vs Training Accuracy Effects on Implicit Bias in Deep Linear Classification
Suriya Gunasekar (Microsoft Research)
1:45 – 2 p.m.
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry
Yossi Arjevani (New York University)
2 – 2:15 p.m.
Beyond Linearization: On Quadratic and Higher-order Taylor Models of Wide Neural Networks
Yu Bai (Salesforce Research)
2:15 – 3:15 p.m.
Gather.town
10 – 10:15 a.m.
A Trichotomy of Rates in Supervised Learning
Amir Yehudayoff (Technion)
10:15 – 10:30 a.m.
Contrastive Estimation Reveals Topic Posterior Information to Linear Models
Daniel Hsu (Columbia University)
10:30 – 10:45 a.m.
Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?
Daniel Soudry (Technion)
10:45 – 11 a.m.
Few-Shot Learning via Learning the Representation, Provably
Qi Lei (Princeton University)
11 – 11:15 a.m.
How to Make Our Models Learn (the Right Things)?
Aleksander Madry (MIT)
11:15 a.m. – 12:15 p.m.
Gather.town
12:15 – 1 p.m.
Break
1 – 1:15 p.m.
Generalization via Derandomization With an Application to Interpolating Predictors
Gintare Karolina Dziugaite (Element AI)
1:15 – 1:30 p.m.
How Does Our Mind Store Information in Memory?
Rina Panigrahy (Google Research)
1:30 – 1:45 p.m.
Fine-Tuning Language Models With Human Feedback
Paul, Christian
1:45 – 2 p.m.
Equilibrium in Nonconvex-Nonconcave Min-Max Optimization and GANs
Nisheeth Vishnoi (Yale)
2 – 2:15 p.m.
Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
Maithra Raghu (Cornell University)
2:15 – 2:30 p.m.
Data Augmentation as Stochastic Optimization
Boris Hanin (Princeton)
2:30 – 3:15 p.m.
Gather.town
10 – 10:15 a.m.
Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance
Daniel Roy (University of Toronto)
10:15 – 10:30 a.m.
The Intriguing Role of Module Criticality in the Generalization of Deep Networks
Hanie Sedghi (Google Brain)
10:30 – 10:45 a.m.
Predicting What You Already Know Helps: Provable Self-Supervised Learning
Jason Lee (Princeton University)
10:45 – 11 a.m.
Probabilistic Approximate Variants of Dimensional and Margin Complexity
Pritish Kamath (Toyota Technological Institute at Chicago)
11 – 11:15 a.m.
Shape Matters: Understanding the Implicit Bias of the Noise Covariance
Tengyu Ma (Stanford University)
11:15 a.m. – 12:15 p.m.
Gather.town
12:15 – 1 p.m.
Break
1 – 2:15 p.m.
Group Discussion
Share this page
Copy URL of this page
Home
The Simons Institute for the Theory of Computing is the world's leading venue for collaborative research in theoretical computer science.

Footer

  • Programs & Events
  • About
  • Participate
  • Workshops & Symposia
  • Contact Us
  • Calendar
  • Accessibility

Footer social media

  • Twitter
  • Facebook
  • Youtube
© 2013–2025 Simons Institute for the Theory of Computing. All Rights Reserved.
link to homepage

Main navigation

  • Home
  • Programs & Events
    • Research Programs
    • Workshops & Symposia
    • Public Lectures
    • Research Pods
    • Internal Program Activities
    • Algorithms, Society, and the Law
  • People
    • Scientific Leadership
    • Staff
    • Current Long-Term Visitors
    • Research Fellows
    • Postdoctoral Researchers
    • Scientific Advisory Board
    • Governance Board
    • Industry Advisory Council
    • Affiliated Faculty
    • Science Communicators in Residence
    • Law and Society Fellows
  • Participate
    • Apply to Participate
    • Plan Your Visit
    • Location & Directions
    • Postdoctoral Research Fellowships
    • Law and Society Fellowships
    • Science Communicator in Residence Program
    • Circles
    • Breakthroughs Workshops and Goldwasser Exploratory Workshops
  • Support
    • Annual Fund
    • Funders
    • Industrial Partnerships
  • News & Videos
    • News
    • Videos
  • About

Utility navigation

  • Calendar
  • Contact
  • Login
  • MAKE A GIFT
link to homepage