5 papers · 1 filter
Restarted Accelerated Primal-Dual Algorithms with Adaptive Stepsizes for Nonlinear Conic Constrained Convex Optimization
Necdet Serhat Aybat, Jinxin Wang
We propose restarted accelerated primal-dual algorithms with (non-monotone) backtracking (rAPDB) for convex nonlinear conic programs, with quadratically constrained quadratic progr…
Randomized Submanifold Subgradient Method for Optimization over Stiefel Manifolds
Andy Yat-Ming Cheung, Jinxin Wang, Man-Chung Yue +1
Optimization over the Stiefel manifold is a fundamental computational problem in many scientific and engineering applications. Despite considerable research effort, high-dimensiona…
On the Estimation Performance of Generalized Power Method for Heteroscedastic Probabilistic PCA
Jinxin Wang, Chonghe Jiang, Huikang Liu +1
The heteroscedastic probabilistic principal component analysis (PCA) technique, a variant of the classic PCA that considers data heterogeneity, is receiving more and more attention…
Projected Tensor Power Method for Hypergraph Community Recovery
Jinxin Wang, Yuen-Man Pun, Xiaolu Wang +2
This paper investigates the problem of exact community recovery in the symmetric -uniform hypergraph stochastic block model (-HSBM). In this model, a -uniform…
Decentralized Weakly Convex Optimization Over the Stiefel Manifold
Jinxin Wang, Jiang Hu, Shixiang Chen +2
We focus on a class of non-smooth optimization problems over the Stiefel manifold in the decentralized setting, where a connected network of agents cooperatively minimize a fin…