Tagged articles

Polynomial Representation

2 articles · Page 1 of 1

Sep 12, 2026 · Artificial Intelligence

Quantifying Neural Network Simplicity with Effective Degree: A Polynomial Approach

Tsinghua researchers propose Effective Degree (ED), a differentiable measure of neural network simplicity based on polynomial representations along data interpolation paths, which correlates strongly with generalization gap and can be used as a regularizer to improve performance across vision, language, and RL tasks.

Deep Learning TheoryEffective DegreeICML 2026

0 likes · 18 min read

Quantifying Neural Network Simplicity with Effective Degree: A Polynomial Approach

Machine Heart

Aug 6, 2026 · Artificial Intelligence

Measuring and Optimizing Neural Network Simplicity—A Year Before LeCun’s World‑Model Study

The Qianjue‑Tsinghua team introduces the Effective Degree (ED) metric, derived from polynomial representations of neural functions along data‑driven paths, enabling measurable simplicity bias that can be evaluated on real‑scale models and directly optimized during training, outperforming traditional complexity proxies.

Effective DegreePolynomial RepresentationSimplicity Bias

0 likes · 15 min read

Measuring and Optimizing Neural Network Simplicity—A Year Before LeCun’s World‑Model Study