AI Paper Atlas

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

Gauge-invariant representation holonomy

Vasileios Sevetlidis, George Pavlidis

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 2 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 separate k-NN sets per edge endpoint instead of shared midpoint neighbors (ablation)holonomy estimator · MNIST Hidden1, r=0.10h_norm: 6.42e-07 -> 0.222Hurt
add shared-midpoint neighbor selection (ablation)holonomy estimator · MNIST Hidden1h_norm bias: +2.22e-1 avoidedImproved
allow O(p) reflections instead of SO(p) (ablation)holonomy estimator · MNIST Hidden1, r=0.10h_norm: text +5.37e-7 vs appendix table 6.42e-07 -> 6.42e-07Mixed
per-neighborhood whitening instead of global (ablation)holonomy estimator · MNIST Hidden1, r=0.10h_norm: text +1.59e-7 vs appendix 6.42e-07 -> 2.22e-07Mixed
vary (k,q) over {96,128,192} x {32,64,96} (ablation)holonomy estimator · MNIST Hidden1, r=0.10h_norm: change 7.20e-7 (SD 2.86e-7)No clear effect
increase standardization pool from 10^3 to 8x10^3 (ablation)holonomy estimator · MNIST Hidden1, r=0.10h_norm: 4.05e-6 -> 4.06e-6No clear effect
random plane instead of local PCA plane (ablation)holonomy estimator · MNIST Hidden1, r=0.10h_norm: -1.92e-8No clear effect
holonomy correlates with robustness at regime levelholonomy vs FGSM accuracy · CIFAR-10 layer2, 4 regimesFGSM accuracy: r approx 0.94Improved
condition on clean accuracyholonomy vs robustness · CIFAR-10 layer2, per seedpartial correlation: FGSM 0.223, PGD 0.276, corruption 0.027No clear effect
replace nonlinearities with identity (linear null) (ablation)MLP · MNISTh_norm: to 9.57e-9 noise levelImproved

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