AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Neural Low-Discrepancy Sequences

Michael Etienne Van Huffel, Nathan Kirk, Makram Chahine, Daniela Rus, T. Konstantin Rusch

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Counterfactual and statistical explanations · 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 discrepancy fine-tuning on top of Sobol' pretraining (vs Sobol')NeuroLDS · D2 sym, d=4, N=10000discrepancy: 0.000167 -> 0.000098Improved
add NeuroLDS vs Sobol'NeuroLDS · D2 star, d=4, N=100discrepancy: 0.009477 -> 0.008603Improved
add NeuroLDS vs Sobol'NeuroLDS · D2 ctr, d=4, N=10000discrepancy: 0.000167 -> 0.000114Improved
add Sobol' pre-training before discrepancy fine-tuning (ablation)NeuroLDS · 2d, 3d, 4dpoint set qualityImproved
replace index-conditioned MLP with autoregressive GNN (ablation)NeuroLDS · 2ddiscrepancyHurt
increase sinusoidal bandwidth K from 8 to 32 (ablation)NeuroLDS · 4dstability of D2 sym curveImproved
replace deep MLP with purely linear map (ablation)NeuroLDS · 2d and 3ddiscrepancyHurt
use one hidden layer instead of deeper MLP (ablation)NeuroLDS · 2d and 3ddiscrepancyNo clear effect
use length-proportional weights instead of uniform prefix weights (ablation)NeuroLDS · d=4, N=10000prefix discrepancyMixed
use NeuroLDS points for training instead of Sobol'MLP on Black-Scholes · 2D Black-ScholesMSE (x1e-4): 4.04 -> 3.34Improved
use NeuroLDS ext discrepancy instead of Sobol' (ablation)MLP on Black-Scholes · 2D Black-ScholesMSE (x1e-4): 4.04 -> 4.01No clear effect
use NMGreedy instead of Sobol' pointsMLP on Black-Scholes · 2D Black-ScholesMSE (x1e-4): 4.04 -> 4.72Hurt

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