243 citations · 409 across the 22 of their papers we have counts for
5 papers · 1 filter
On the Global Convergence of Continuous-Time Stochastic Heavy-Ball Method for Nonconvex Optimization
Wenqing Hu, Chris Junchi Li, Xiang Zhou
We study the convergence behavior of the stochastic heavy-ball method with a small stepsize. Under a change of time scale, we approximate the discrete method by a stochastic differ…
A convergence analysis of the perturbed compositional gradient flow: averaging principle and normal deviations
Wenqing Hu, Chris Junchi Li
We consider in this work a system of two stochastic differential equations named the perturbed compositional gradient flow. By introducing a separation of fast and slow scales of t…
On the fast convergence of random perturbations of the gradient flow
Jiaojiao Yang, Wenqing Hu, Chris Junchi Li
We consider in this work small random perturbations (of multiplicative noise type) of the gradient flow. We prove that under mild conditions, when the potential function is a Morse…
On the diffusion approximation of nonconvex stochastic gradient descent
Wenqing Hu, Chris Junchi Li, Lei Li +1
We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the d…
Dropping Convexity for More Efficient and Scalable Online Multiview Learning
Zhehui Chen, Lin F. Yang, Chris J. Li +1
Multiview representation learning is very popular for latent factor analysis. It naturally arises in many data analysis, machine learning, and information retrieval applications to…