3 papers
math.OC2026
Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise
Jiayu Zhang, Tianyi Lin
A growing lesson from neural network optimization is that optimizer design should respect how the model is parametrized. The layerwise input-output structure of neural networks mot…
math.OC2026
A Control-Theoretic Perspective on Optimal High-Order Optimization
Tianyi Lin, Michael. I. Jordan
We provide a control-theoretic perspective on optimal tensor algorithms for minimizing a convex function in a finite-dimensional Euclidean space. Given a function $Φ: \mathbb{R}^d…
cs.LG2024
On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
Tianyi Lin, Chi Jin, Michael I. Jordan
We consider nonconvex-concave minimax problems, , where is nonconvex in but concave…