research
∙
06/21/2023
Task-Robust Pre-Training for Worst-Case Downstream Adaptation
Pre-training has achieved remarkable success when transferred to downstr...
share
research
∙
08/13/2022
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
Adaptive gradient algorithms borrow the moving average idea of heavy bal...
research
∙
05/27/2022
Global Convergence of Over-parameterized Deep Equilibrium Models
A deep equilibrium model (DEQ) is implicitly defined through an equilibr...
research
∙
05/27/2021
Optimization Induced Equilibrium Networks
Implicit equilibrium models, i.e., deep neural networks (DNNs) defined b...
research
∙
07/09/2020
Maximum-and-Concatenation Networks
While successful in many fields, deep neural networks (DNNs) still suffe...
research
∙
05/15/2019
Differentiable Linearized ADMM
Recently, a number of learning-based optimization methods that combine d...
research
∙
11/09/2018
Matrix Recovery with Implicitly Low-Rank Data
In this paper, we study the problem of matrix recovery, which aims to re...
research
∙
01/12/2017