Anru R. Zhang

2 accepted papers

2022

Provable Second-Order Riemannian Gauss-Newton Method for Low-Rank Tensor Estimation ‖

Yuetian Luo, Qin Ma, Chi Zhang, Anru R. Zhang

ICASSP 2022accepted

In this paper, we consider the estimation of a low Tucker rank tensor from a number of noisy linear measurements. We propose a Riemannian Gauss-Newton (RGN) method with fast implementations for low Tucker rank tensor estimation. Different from the generic (super)linear convergence guarantee of RGN i…

Cited by 0 Source ↗Scholar ↗

2020

Sparse and Low-rank Tensor Estimation via Cubic Sketchings

Botao Hao, Anru R. Zhang, Guang Cheng

AISTATS 2020poster

In this paper, we propose a general framework for sparse and low-rank tensor estimation from cubic sketchings. A two-stage non-convex implementation is developed based on sparse tensor decomposition and thresholded gradient descent, which ensures exact recovery in the noiseless case and stable recov…

Cited by 65 Source ↗PDF ↗Scholar ↗