AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Scaling Recurrent Models via Orthogonal Approximations in Tensor Trains

Ronak Mehta, Rudrasis Chakraborty, Yunyang Xiong, Vikas Singh

ICCV 2019 · Architectures and efficiency › CNN design · approach: Theory of convolutional inductive bias · 4 citations (OpenAlex)

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 orthogonal tensor train (OTT) instead of Riemannian SGD on TTtensorized weight learning · Synthetic least squarestime per iteration: 10xImproved
use OTT instead of Riemannian SGD on TTtensorized weight learning · Synthetic least squaresconvergence speed (MSE)Improved
use OTT layers instead of TT layersLSTM/GRU · Hollywood2mean average precisionNo clear effect
use OTT instead of TTLSTM/GRU · Hollywood2parameter count: 3104 -> 1864Improved
use OTT instead of TTRNN on ADNI · ADNI RAVLT regressionvalidation loss convergenceImproved
use OTT instead of TTRNN on ADNI · ADNI RAVLT regression95% interval width (MC Dropout)Improved
use lower OTT ranks (higher compression) (ablation)OTT-RNN · ADNI gray matter predictionreconstruction qualityHurt

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