1 citations · 1 across the 8 of their papers we have counts for
9 papers
A Unified Theory of H-Duality in First-Order Methods
Kevin Shu, Alex L. Wang
We provide two complementary explanations of H-duality in smooth strongly convex optimization and contractive fixed-point problems. H-duality refers to the phenomenon where the wor…
Implicit Primal-Dual Guarantees in Unconstrained First-Order Minimization
Benjamin Grimmer, Alex L. Wang
This work considers the design of first-order convex optimization algorithms and convergence proofs. In particular, we consider nonsmooth Lipschitz and smooth problems accessed thr…
Online learning of smooth functions on
Jesse Geneson, Kuldeep Singh, Alexander Wang
We study adversarial online learning of real-valued functions on . In each round the learner is queried at , predicts , and then observes th…
Subgame Perfect Methods in Nonsmooth Convex Optimization
Benjamin Grimmer, Alex L. Wang
This paper considers nonsmooth convex optimization with either a subgradient or proximal operator oracle. In both settings, we identify algorithms that achieve the recently introdu…
Beyond Minimax Optimality: A Subgame Perfect Gradient Method
Benjamin Grimmer, Kevin Shu, Alex L. Wang
The study of convex optimization has historically been concerned with worst-case convergence rates. The development of the Optimized Gradient Method (OGM), due to \citet{drori2012P…
Composing Optimized Stepsize Schedules for Gradient Descent
Benjamin Grimmer, Kevin Shu, Alex L. Wang
Recent works by Altschuler and Parrilo and the authors have shown that it is possible to accelerate the convergence of gradient descent on smooth convex functions, even without mom…
A Strengthened Conjecture on the Minimax Optimal Constant Stepsize for Gradient Descent
Benjamin Grimmer, Kevin Shu, Alex L. Wang
Drori and Teboulle [4] conjectured that the minimax optimal constant stepsize for N steps of gradient descent is given by the stepsize that balances performance on Huber and quadra…
Accelerated Objective Gap and Gradient Norm Convergence for Gradient Descent via Long Steps
Benjamin Grimmer, Kevin Shu, Alex L. Wang
This work considers gradient descent for L-smooth convex optimization with stepsizes larger than the classic regime where descent can be ensured. The stepsize schedules considered…
Accelerated Gradient Descent via Long Steps
Benjamin Grimmer, Kevin Shu, Alex L. Wang
Recently Grimmer [1] showed for smooth convex optimization by utilizing longer steps periodically, gradient descent's textbook convergence guarantees can be improved by c…