5 papers
A Decomposed Bilevel Search for Variable-Metric Proximal Gradient Methods
Xinpeng Li, Ya-xiang Yuan
Variable-metric proximal methods accelerate composite convex optimization, but the scaled proximal map induced by a quasi-Newton metric rarely has a closed form. We develop \emph{D…
BUP-TR: Bayesian Underdetermined Projection Trust-Region Methods for Derivative-Free Optimization
Wei Hu, Pengcheng Xie, Ya-Xiang Yuan +1
Underdetermined quadratic interpolation is a central model-construction tool in model-based derivative-free trust-region methods: it limits sampling costs but leaves an affine fami…
MATRO: Metric-Aware Trust-Region Optimization with Fully Quadratic Models
Wei Hu, Pengcheng Xie, Ya-Xiang Yuan +1
Model-based derivative-free trust-region methods build local interpolation models and restrict trial steps to regions where those models are reliable. This paper studies the shape…
Optimization over the intersection of manifolds
Yan Yang, Bin Gao, Ya-xiang Yuan
Optimization over the intersection of two manifolds arises in a broad range of applications, but is hindered by the coupled geometry of the feasible region. In this paper, we prove…
Distributed Gradient-Regularized Newton Method: Scheduled Consensus and O(epsilon^{-1}) Global Iteration Complexity
Wei Hu, Pengcheng Xie, Ya-Xiang Yuan +1
We propose DisGrem, a fully decentralized second-order method for convex consensus optimization over networks. Each agent solves a local Newton system with vanishing gradient-norm…