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

–
Coffee and Check-in
–
Opening Remarks
–
Exploiting geometric structure in (matrix-valued) optimization
Melanie Weber (Harvard University)
–
A Stochastic Newton Algorithm for Distributed Convex Optimization
Brian Bullins (Purdue University)
–
Break
–
Hitting the High-D(imensional) Notes: An ODE for SGD learning dynamics in high-dimensions
Courtney Paquette (McGill University)
–
Lunch (on your own)
–
Beyond NTK: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
Tengyu Ma (Stanford University)
–
Break
–
Theoretical and Practical Insights from Linear Transformers
Xiang Cheng (Massachusetts Institute of Technology)
–
Lightning Talks
–
Reception
–
Coffee and Check-in
–
Flat minima generalize for low-rank matrix recovery
Maryam Fazel (University of Washington)
–
Break
–
Robust Gradient Descent: Agnostically Estimating an Unknown Affine Transformation with Near-optimal Error
Santosh Vempala (Georgia Tech)
–
Lunch (on your own)
–
Randomized Linear Algebra for Interior Point Methods
Petros Drineas (Purdue University)
–
IPM and Nested Dissection for Planar and Separable LPs
Sally Dong (University of Washington)
–
Break
–
Nash Social Welfare and A Tale of Mathematical Programs
Mohit Singh (Georgia Institute of Technology)
–
Short-Flat Decompositions and Faster Algorithms for Linear Inverse Problems
Kevin Tian (UT Austin)
–
Break
–
Open Discussion (in-person only)
–
Coffee and Check-in
–
Fast Algorithms for Regression Problems
Deeksha Adil (ETH Zurich)
–
Break
–
The Complexity of Dynamic Least-Squares Regression
Shunhua Jiang (Columbia University)
–
Lunch (on your own)
–
Tight Bounds for Active lp Regression and Beyond
David Woodruff (Carnegie Mellon University)
–
Break
–
Robust Learning of a Single Neuron via Sharpness
Jelena Diakonikolas (University of Wisconsin-Madison)
–
Instance Optimal Iterative Methods for Matrix Function Approximation
Cameron Musco (University of Massachusetts Amherst)
–
Break
–
Open Discussion (in-person only)
–
Coffee and Check-in
–
Sparsifying Generalized Linear Models
Yang Liu (Stanford University)
–
Break
–
Breaking the quadratic gap for strongly polynomial solvers to combinatorial linear programs
Bento Natura (UC Berkeley & Georgia Tech)
–
Lunch (on your own)
–
Discrepancy Minimization via Regularization
Adrian Vladu (IRIF)
–
Break
–
Quotient Sparsification for Submodular Functions
Kent Quanrud (Purdue University)
–
Recent Progress on Submodular Function Minimization
Haotian Jiang (Microsoft Research, Redmond)
–
Break
–
Open Discussion (in-person only)
–
Coffee and Check-in
–
Network Unreliability in Sub-quadratic Time
Debmalya Panigrahi (Duke University)
–
Break
–
Approximating k-Edge-Connected Spanning Subgraphs via a Near-Linear Time LP Solver
Sorrachai Yingchareonthawornchai (Simons Institute)