SS-17.2
Provable Second-order Riemannian Gauss-Newton Method for Low-rank Tensor Estimation
Yuetian Luo, University of Wisconsin-Madison, United States of America; Qin Ma, Ohio State University, United States of America; Chi Zhang, Indiana University, United States of America; Anru Zhang, Duke University, United States of America
Session:
Provable Tensor and Matrix Methods for Sensing and Learning
Track:
Special Sessions
Location:
Gather Area A
Presentation Time:
Fri, 13 May, 21:00 - 21:45 China Time (UTC +8)
Fri, 13 May, 13:00 - 13:45 UTC
Fri, 13 May, 13:00 - 13:45 UTC
Session Co-Chairs:
Yuejie Chi, Carnegie Mellon University and Xiao Fu, Oregon State University
Session SS-17
SS-17.1: Communication-Efficient Distributed MAX-VAR Generalized CCA via Error Feedback-Assisted Quantization
Sagar Shrestha, Xiao Fu, Oregon State University, United States of America
SS-17.2: Provable Second-order Riemannian Gauss-Newton Method for Low-rank Tensor Estimation
Yuetian Luo, University of Wisconsin-Madison, United States of America; Qin Ma, Ohio State University, United States of America; Chi Zhang, Indiana University, United States of America; Anru Zhang, Duke University, United States of America
SS-17.3: BOUNDED SIMPLEX-STRUCTURED MATRIX FACTORIZATION
Olivier Vu Thanh, Nicolas Gillis, Fabian Lecron, Université de Mons, Belgium
SS-17.4: CPD computation via recursive eigenspace decompositions
Eric Evert, Michiel Vandecappelle, Lieven De Lathauwer, KU Leuven, Belgium
SS-17.5: ACCELERATING ILL-CONDITIONED ROBUST LOW-RANK TENSOR REGRESSION
Tian Tong, Yuejie Chi, Carnegie Mellon University, United States of America; Cong Ma, University of Chicago, United States of America
SS-17.6: Ada-JSR: SAMPLE EFFICIENT ADAPTIVE JOINT SUPPORT RECOVERY FROM EXTREMELY COMPRESSED MEASUREMENT VECTORS
Sina Shahsavari, Pulak Sarangi, Mehmet Hucumenoglu, Piya Pal, University of California San Diego, United States of America