From the 1 of 5 linked papers with an AI index.
5 papers
Optimal Parameter-Free First-Order Methods for Convex Optimization with Unknown Growth and Smoothness
Liwei Jiang, Ke Tang, Zhe Zhang
The paper introduces parameter-free first-order optimization methods that automatically adapt to unknown smoothness and growth properties of convex functions, achieving optimal con…
Instance-optimal stochastic convex optimization: Can we improve upon sample-average and robust stochastic approximation?
Liwei Jiang, Ashwin Pananjady
We study the unconstrained minimization of a smooth and strongly convex population loss function under a stochastic oracle that introduces both additive and multiplicative noise; t…
Gradient descent with adaptive stepsize converges (nearly) linearly under fourth-order growth
Damek Davis, Dmitriy Drusvyatskiy, Liwei Jiang
A prevalent belief among optimization specialists is that linear convergence of gradient descent is contingent on the function growing quadratically away from its minimizers. In th…
Preconditioned subgradient method for composite optimization: overparameterization and fast convergence
Mateo DÃaz, Liwei Jiang, Abdel Ghani Labassi
Composite optimization problems involve minimizing the composition of a smooth map with a convex function. Such objectives arise in numerous data science and signal processing appl…
Online Covariance Estimation in Nonsmooth Stochastic Approximation
Liwei Jiang, Abhishek Roy, Krishna Balasubramanian +3
We consider applying stochastic approximation (SA) methods to solve nonsmooth variational inclusion problems. Existing studies have shown that the averaged iterates of SA methods e…