17 citations · 24 across the 3 of their papers we have counts for
3 papers
cs.LG2023★ 1 cited
Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks
Wei Tao, Lei Bao, Sheng Long +2
Learning adversarial examples can be formulated as an optimization problem of maximizing the loss function with some box-constraints. However, for solving this induced optimization…
cs.LG2021★ 6 cited
The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods
Wei Tao, Sheng Long, Gaowei Wu +1
The adaptive stochastic gradient descent (SGD) with momentum has been widely adopted in deep learning as well as convex optimization. In practice, the last iterate is commonly used…
cs.LG2020★ 17 cited
The Strength of Nesterov's Extrapolation in the Individual Convergence of Nonsmooth Optimization
W. Tao, Z. Pan, G. Wu +1
The extrapolation strategy raised by Nesterov, which can accelerate the convergence rate of gradient descent methods by orders of magnitude when dealing with smooth convex objectiv…