AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

A method to automatically discover symbolic local learning rules

Andrea Perin, Fabio Anselmi, Stephane Deny

NeurIPS 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a method that automatically discovers symbolic, layer-specific local loss functions to replace backpropagation, by building a dictionary of local tensor monomials (inspired by Penrose diagrams) and regressing coefficients over them.

Problem

Backpropagation is the standard training algorithm for deep networks but is non-local and biologically implausible; the paper seeks local learning rules that can replace it across architectures and tasks.

Approach

Discovers per-layer local loss functions symbolically by constructing a dictionary of monomials of local tensor variables (inspired by Penrose diagram notation) and regressing coefficients weighting these monomials, rather than hand-designing or learning opaque local rules.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learn local rules for layer 1 instead of freezing it (degree 2)Learned local rule · Sliced MNIST classification (held-out)final loss: 0.97 -> 0.89Improved
learned local rule versus first layer frozen to PCALearned local rule · Sliced MNIST classification (held-out)final loss: 0.84 (PCA) vs 0.89 (rule)Hurt
learned local rules instead of backpropLearned local rule · Sliced MNIST classification (held-out)accuracy (%): 71 -> 67Hurt
learned local rules for layer 1 instead of freezing it (degree 2)Learned local rule · Sliced MNIST reconstruction (held-out)average loss: 3.35 -> 1.90Improved
learned local rules instead of backpropLearned local rule · Sliced MNIST reconstruction (held-out)average loss: 1.27 -> 1.90Hurt
learned layerwise local rules (degree 1) instead of freezing first two layersLearned local rule · MNIST self-supervised Barlow Twins (held-out)average loss: 22.47 -> 17.11Improved
learned local rules instead of backpropLearned local rule · MNIST self-supervised Barlow Twins (held-out)average loss: 5.50 -> 17.11Hurt
raise neighborhood degree from 1 to 2 (ablation)Learned local rule · Sliced MNIST classificationlossImproved
raise neighborhood degree from 1 to 2 (ablation)Learned local rule · Sliced MNIST reconstructionlossNo clear effect
raise neighborhood degree from 2 to 3 (global rules) (ablation)Learned local rule · Sliced MNIST classification and reconstructionlossHurt
transfer degree-2 rules to a network with different layer sizes (ablation)Learned local rule · Sliced MNIST classification (held-out)lossHurt

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