AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Non-Convex Projected Gradient Descent for Generalized Low-Rank Tensor Regression

Han Chen, Garvesh Raskutti, Ming Yuan

JMLR 2019 · Learning theory and algorithms › Matrix and tensor methods · approach: Nonconvex low-rank and sparse optimization

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use non-convex PGD instead of convex regularizationLow-rank tensor regression · Case 6a Gaussian low CP rank, high SNRnormalized rmse: 0.28 -> 0.11Improved
Use non-convex PGD instead of convex regularizationLow-rank tensor regression · Case 6c Poisson low CP rank, high SNRnormalized rmse: 0.57 -> 0.09Improved
Use non-convex PGD instead of convex regularizationLow-rank tensor regression · Case 8c Poisson sparse low-rank slices, high SNRnormalized rmse: 0.79 -> 0.13Improved
Use non-convex PGD instead of convex regularizationLow-rank tensor regression · Case 8a Gaussian sparse low-rank slices, high SNRnormalized rmse: 0.12 -> 0.08Improved
Use non-convex PGD instead of convex regularizationLow-rank tensor regression · Case 7a Gaussian low Tucker rank, low SNRnormalized rmse: 0.51 -> 0.28Improved
Use a larger assumed rank r' or sparsity s' in the PGD projection (misspecification) (ablation)Non-convex PGD · Cases 1a-3a Gaussian third-order tensors, p=50^3converged rmseHurt
Use a larger step size eta (below the divergence tolerance) (ablation)Non-convex PGD · Cases 1a-3a Gaussian third-order tensors, p=50^3convergence speedImproved
Use too large a step size eta (ablation)Non-convex PGD · Cases 1a-3a Gaussian third-order tensors, p=50^3convergenceHurt
Use the relaxed (misspecified) projection instead of the true rank (ablation)Non-convex PGD · Cases 1b-1c logistic and Poisson low CP rankconvergence rmseHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy