AI Paper Atlas

Research map / Optimization / Optimizers

Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent

Guillaume Larue, Louis-Adrien Dufrène, Quentin Lampin, Hadi Ghauch, Rekaya-Ben Othman

ICML 2026 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 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
use product XOR node instead of MLP when training on unit-sparse inputsparity learner · Subset parity N=16, sparse regimevalidation accuracy on full truth table: MLP stagnates near 50% vs product node 100%Improved
train on uniform samples of the truth table instead of sparse samples (ablation)Product node vs MLP · Subset parity N=16, uniform regimeconvergence speedMixed
use constant pe=2/N instead of the theoretical pe=1/N (ablation)Product node · Subset parity N=100training steps to convergence: optimum p*e about 2/NImproved
use dense inputs from the start (pe at or above about 7/N) (ablation)Product node · Subset parity N=100convergence within 25,000 steps: no convergence for pe >= 7/NHurt
use pe far below 1/N (ultra-sparse inputs) (ablation)Product node · Subset parity N=100convergence speedHurt
raise learning rate up to about N/2 (ablation)Product node · Subset parity N from 10 to 1000convergence time: alpha_lim about N/2Improved
raise learning rate beyond alpha_lim (ablation)Product node · Subset parity N from 10 to 1000convergenceHurt
vary the proportion pw of oracle weights equal to 1 (ablation)Product node · Subset parity N=100,000convergenceNo clear effect
scale learning rate with N to keep alpha times pe constant (ablation)Product node · Subset parity across Nconvergence speedImproved

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