PaperScope
LIVE · 2026-09-15 05:40 UTC

Structured Features Overfit Where Random Features Grok

Chon-Fai Kam, Miloud Bessafi, Frederic Cadet

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.15047 v1
Category
Submitted
2026-09-14

Abstract

Xu, Vardi and Safran (ICML 2026) prove that over-parameterized ridge regression over an unstructured random Gaussian feature map groks, with the delay between memorization and generalization growing as $1/λ$ in the weight decay. We show that on a structured feature map the same delay does not appear. For a band-limited Fourier feature map over $\mathbb{Z}_p^2$ carrying a single-character target that lies inside the expressible class, enlarging the band at fixed positive weight decay drives peak held-out accuracy monotonically from $1.00$ to $0.07$, with no memorize-then-generalize regime anywhere along the sweep. The degradation is not an interpolation effect. It sets in at capacity ratio $q/n = 0.638$, far below the interpolation threshold, on separate grounds from the exact null space that appears above it. What does have a sharp boundary is the active support. Holding the nominal dimension fixed and masking the band back to $1089$ active modes restores held-out accuracy of $1.000$ with zero variance across seeds, while the full $4225$-mode band collapses to $0.185$. The number of active modes acts through the teacher-weighted spectrum of the empirical Gram matrix and not through the capacity ratio, which makes this a statement about feature geometry and not a restatement of double descent.

Comment: 13 pages, 2 figures, 3 tables. Submitted to OPT 2026 (18th Annual Workshop on Optimization for Machine Learning)

arXiv abs page · PDF · same-day batch