All talks listed in Pacific Time. Schedule subject to change.

–
Coffee and Check-In
–
From the Ball-proximal (Broximal) Point Method to Efficient Training of LLM

Peter Richtarik (KAUST)
Video
–
Scale Learning and Reasoning Across Heterogeneous Gradients and Semantics

Tian Li (University of Chicago)
Video
–
Lunch (on your own)
–
"Federated Reinforcement Learning: Statistical and Communication Trade-offs

Yuejie Chi (Yale University)
Video
–
Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration

Ahmed Khaled (Princeton University)
Video
–
The Many Faces of Heterogeneity: Federated, Continual, and Modular Learning

Marco Ciccone (Vector Institute)
Video
–
Break
–
Symbiotic Relations between Decoupled Training, Optimization, and Federated Learning

Zachary Charles (Google Research)
Video
–
Reception
–
Coffee and Check-In
–
Privacy Amplification from Structured Algorithmic Randomness

Ayfer Ozgur (Stanford University)
Video
–
Break
–
Federated, Synthetic, Personalized: Heterogeneity Here or There?

Zheng Xu (Meta)
Video
–
Lunch (on your own)
–
Privacy of Decentralized Machine Learning

Edwige Cyffers (CNRS)
Video
–
Exact Unlearning of Finetuning Data via Model Merging at Scale

Kevin Kuo (Carnegie Mellon University)
Video
–
Privacy versus Robustness in Federated Learning: Limits and Algorithms

Youssef Allouah (Stanford University)
Video
–
Break
–
Richard M. Karp Distinguished Lecture

Brendan McMahan (Google)
–
Coffee and Check-In
–
Exploiting Similarity in Federated Learning

Sebastian Stich (CISPA)
Video
–
Federated Learning in the Generative AI Era

Gauri Joshi (Carnegie Mellon University)
Video
–
Lunch (on your own)
–
FlexOlmo: Open Language Models for Flexible Data Use

Sewon Min (UC Berkeley)
Video
–
On continual learning with gradient descent for neural networks

Arya Mazumdar (UC San Diego)
Video
–
Break
–
Not all data are created Equal: Robust Mean Estimation from Heterogeneous and Unreliable Users

Maryam Aliakbarpour (Rice)
Video
–
Group Hike
–
Coffee and Check-In
–
A Complex Picture of Multi-task Learning

Samory Kpotufe (Columbia University)
Video
–
Break
–
Learning from multiple modalities, Predicting on unseen tasks

Zaid Harchaoui (University of Washington)
Video
–
Lunch
–
Personalized Collaborative Learning with Affinity-Based Variance Reduction

Chenyu Zhang (MIT)
Video
–
The Statistical Fairness-Accuracy Frontier

Alireza Fallah (Rice University)
Video
–
Break
–
Jane Street Estimathon
–
Coffee and Check-In
–
Are We Measuring the Right Thing? Distribution Shift Lessons for Federated Learning

Sanmi Koyejo (Stanford University)
Video
–
Open Problems Session #1
–
Lunch (on your own)
–
Tight analyses of first-order methods with error feedback, in homogeneous and heterogeneous setups

Aymeric Dieuleveut (CMAP)
Video
–
Open Problems Session #2
–
Break
–
Group Discussion
–
Concluding Remarks