3 papers
math.OC2026
Lower Bounds for Anytime Acceleration of Gradient Descent
Chung-En Tsai, Ilyas Fatkhullin, Liang Zhang +1
Recent work suggests that the convergence rate of gradient descent (GD) in smooth convex optimization can be significantly improved by employing large stepsizes that may violate th…
math.OC2024
Linear Convergence in Hilbert's Projective Metric for Computing Augustin Information and a Rényi Information Measure
Chung-En Tsai, Guan-Ren Wang, Hao-Chung Cheng +1
Consider the problems of computing the Augustin information and a Rényi information measure of statistical independence, previously explored by Lapidoth and Pfister (IEEE Informat…
cs.IT2024
Computing Augustin Information via Hybrid Geodesically Convex Optimization
Guan-Ren Wang, Chung-En Tsai, Hao-Chung Cheng +1
We propose a Riemannian gradient descent with the Poincaré metric to compute the order- Augustin information, a widely used quantity for characterizing exponential error behav…