AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data

Viktoria Schuster, Sana Tonekaboni, Caroline Uhler

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 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
add R(D) fidelity-guided bidirectional rank adjustment to SVD rank reduction (ablation)FiGuRO · Simulated B subsetsshared rank k_s (Bs): 1.0 -> 3.6 ± 0.06Improved
add R(D) to SVD rank reduction (ablation)FiGuRO · Simulated Bi1shared rank k_s (GT 20): 1.0 -> 13.4 ± 0.4Improved
add R(D) to SVD rank reduction (ablation)FiGuRO · Simulated Blshared rank k_s (GT 20): 1.0 -> 19.2 ± 0.7Improved
use FiGuRO instead of JIVE/AJIVE/SLIDE/ShIndICAFiGuRO · Simulated Bavg deviation from GT rank: 9.5 -> 2.9Improved
add Frobenius norm or L1 regularizer for disentanglement (ablation)FiGuRO · Simulated Bdisentanglement / rank accuracyHurt
add L2 regularization (ablation)FiGuRO · Simulated B (fully independent modalities)disentanglementMixed
use FiGuRO shared subspace instead of unimodal embeddingFiGuRO · So2SatAcc_all: 0.41 -> 0.55Improved
use FiGuRO instead of AJIVEFiGuRO · Audio MNISTAcc_s: 0.99 -> 0.94Hurt
use FiGuRO instead of SLIDEFiGuRO · So2SatAcc_s: 0.24 -> 0.55Improved
vary distortion budget lambda, tau, gamma, patience (grid search) (ablation)FiGuRO · Dataset A (N=1080 runs)estimated ID (true 5): 4.89 ± 0.01No clear effect
use R^2 distortion metric instead of MSE/RMSE (ablation)FiGuRO · Simulated sparse datarobustnessImproved
use R^2 distortion metric instead of Explained Variance Score (ablation)FiGuRO · Simulated nonlinear datarobustnessImproved

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