activity
20242026
collaborators

8 papers

cs.LG2026

Non-Euclidean Gradient Descent Operates at the Edge of Stability

Rustem Islamov, Michael Crawshaw, Jeremy Cohen +1

The Edge of Stability (EoS) is a phenomenon where the sharpness (largest eigenvalue) of the Hessian approaches and then hovers near the stability threshold during gradient d…

cs.LG2026

Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension

Michael Crawshaw, Mingrui Liu

We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $…

cs.LG2026

Muon Does Not Converge on Convex Lipschitz Functions

Tetiana Parshakova, Ahmed Khaled, Michael Crawshaw +2

Muon and its variants have shown strong empirical performance in a variety of deep learning tasks. Existing convergence analyses of Muon rely on smoothness assumptions, though argu…

cs.LG2025

An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants

Michael Crawshaw, Chirag Modi, Mingrui Liu +1

To define a steepest descent method over a neural network, we need to choose a norm for each layer, a way to aggregate these norms across layers, and whether to use normalization.…

cs.LG2025

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

Michael Crawshaw, Blake Woodworth, Mingrui Liu

Existing analysis of Local (Stochastic) Gradient Descent for heterogeneous objectives requires stepsizes where is the communication interval, which ensures monoton…

cs.LG2025

Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness

Michael Crawshaw, Mingrui Liu

Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the -smoothness condition, but the…