The Role of TCS in Modern Machine Learning

Location

Calvin Lab auditorium

Date

Tuesday, May 26 – Friday, May 29, 2026

Back to calendar

8:30 – 9 a.m.

Coffee and Check-In

9 – 9:05 a.m.

Welcome and Introduction

9:05 – 9:35 a.m.

Questions for Theory in the New Age of Machine Learning

Tom Mitchell (Carnegie Mellon University)

9:35 – 10:10 a.m.

Disincentivizing Hallucination

Adam Kalai (OpenAI)

10:10 – 10:45 a.m.

Enhanced and Efficient Reasoning in Large Language Models

Les Valiant (Harvard University)

10:45 – 11:15 a.m.

Break

11:15 – 11:50 a.m.

Latent Variable models and Subset Smoothing

Ravi Kannan (Simons Institute, UC Berkeley)

11:50 a.m. – 12:25 p.m.

Red Points and Blue Points

Santosh Vempala (Georgia Institute of Technology)

12:25 – 2:20 p.m.

Lunch (on your own)

2:20 – 2:55 p.m.

An Occam's Razor Principle for Transformers?

John Langford (Microsoft Research)

2:55 – 3:30 p.m.

Learnability of Complex Objects in Modern AI

Nina Balcan (Carnegie Mellon University)

3:30 – 4:30 p.m.

Reception

8:30 – 9 a.m.

Coffee and Check-In

9 – 9:35 a.m.

The Conscious Turing Machine (CTM), a formally defined Theoretical model of Consciousness

Manuel Blum (Carnegie Mellon University)

9:35 – 10:10 a.m.

The Role of TCS in Understanding (AI) Consciousness

Lenore Blum (CMU)

10:10 – 10:45 a.m.

AI and Safety

Ron Rivest (MIT)

10:45 – 11:15 a.m.

Break

11:15 – 11:50 a.m.

Probably Approximately Precision and Recall Learning

Yishay Mansour (Tel Aviv Univ and Google Research)

11:50 a.m. – 12:25 p.m.

Astral Space: Convex Analysis at Infinity

Robert Schapire (Microsoft Research)

12:25 – 2:20 p.m.

Lunch (on your own)

2:20 – 2:55 p.m.

Unfamiliar Terrain

Prabhakar Raghavan (Google)

2:55 – 3:30 p.m.

Venturing out into the world with AI

Jon Kleinberg (Cornell University)

3:30 – 4 p.m.

Break

4 – 5 p.m.

Lightning Talks

8:30 – 9 a.m.

Coffee and Check-In

9 – 9:35 a.m.

Approximately Packing Dijoins Via Nowhere-Zero Flows

R Ravi (Carnegie Mellon University)

9:35 – 10:10 a.m.

Multi-objective Learning: An Algorithmic Toolbox for Optimal Predictions Anytime Anywhere!

Nika Haghtalab (UC Berkeley)

10:10 – 10:45 a.m.

On the Komlós Conjecture

Nikhil Bansal (University of Michigan)

10:45 – 11:15 a.m.

Break

11:15 – 11:50 a.m.

Computational Thinking on Learning Models

Nati Srebro (Toyota Technological Institute at Chicago)

11:50 a.m. – 12:25 p.m.

Efficient Algorithms for Reliable Machine Learning

Adam Klivans (University of Texas, Austin)

12:25 – 2:20 p.m.

Lunch (on your own)

2:20 – 2:55 p.m.

Trust Without Transparency

Katrina Ligett (Hebrew University of Jerusalem)

2:55 – 3:30 p.m.

Length Generalization via Auxiliary Tasks

Pranjal Awasthi (Google)

3:30 – 4 p.m.

Break

4 – 5 p.m.

Group Activity

8:30 – 9 a.m.

Coffee and Check-In

9 – 9:35 a.m.

Can LLMs Reason Structurally? Benchmarking via the lens of Data Structures (in person only)

Ellen Vitercik (Stanford University)

9:35 – 10:10 a.m.

Sequences of Logits and The Low Rank Structure of Language Models (in person only)

Abhishek Shetty (MIT)

10:10 – 10:45 a.m.

Optimization with Costly Information (in person only)

Shuchi Chawla (University of Texas at Austin)

10:45 – 11:15 a.m.

Break

11:15 – 11:50 a.m.

Calibration in the Age of AI: From Prediction to Decision Making to AI Assisted Research (in person only)

Aaron Roth (University of Pennsylvania)

11:50 a.m. – 12:35 p.m.

Approximation Guarantees for Data-Driven Algorithm Design (in person only)

Avrim Blum (Toyota Technological Institute at Chicago)