AI Paper Atlas

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

Computational and Statistical Guarantees for Tensor-on-Tensor Regression With Tensor Train Decomposition

Zhen Qin, Zhihui Zhu

TPAMI 2025 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank tensor completion · 11 citations (OpenAlex)

Read the paper

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 TT structure rank (20,20,20) instead of full rank under noise variance 5 (ablation)IHT · LFW, m=5000, noise 5relative test error: 0.523 -> 0.3892Improved
use TT ranks (20,20,20) instead of full rank under noise variance 5 (ablation)RGD · LFW, m=5000, noise 5relative test error: 0.5509 -> 0.4181Improved
use TT ranks (30,30,30) instead of full rank under noise variance 1 (ablation)IHT · LFW, m=5000, noise 1relative test error: 0.3422 -> 0.3199Improved
use TT rank (50,50,50) instead of full rank with noiseless data (ablation)IHT · LFW, m=5000, noise 0relative test error: 0.2957 -> 0.2956No clear effect
use TT rank (10,10,10) instead of (50,50,50) under noiseless data (ablation)IHT · LFW, m=5000, noise 0relative test error: 0.2956 -> 0.3673Hurt
use IHT instead of RGDTT-ToT regression · LFW, m=5000, noise 1, rank (50,50,50)relative test error: 0.3713 -> 0.3275Improved
use IHT instead of RGDTT-ToT regression · LFW, m=10000, noise 0, rank (50,50,50)relative test error: 0.315 -> 0.2821Improved
increase training observations from 5000 to 10000IHT full rank · LFW, noise 1relative test error: 0.3422 -> 0.3056Improved
increase training observations from 5000 to 10000RGD TT ranks (30,30,30) · LFW, noise 5relative test error: 0.4365 -> 0.381Improved
use RGD with TT ranks (50,50,50) instead of IHT regarding per-iteration timeRGD vs IHT · LFW, m=5000relative test error: 0.99 -> 0.88Mixed

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