works on

From the 2 of 5 linked papers with an AI index.

collaborators

5 papers

cs.LG2026

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking

Gunner Levi Howe

The paper investigates why certain representational priors speed up the delayed generalization phenomenon known as grokking, showing that feature‑family alignment, label‑free invar…

cs.LG2026

Structure-Specific Representational Priors Causally Control the Grokking Delay

Gunner Levi Howe

The paper experimentally shows that the delayed generalization known as grokking is caused by the time needed to form task‑specific representations, using injected representational…

cs.LG2026

Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource

Gunner Levi Howe

On analog neuromorphic hardware, intrinsic device noise is normally an accuracy tax. We ask whether it can instead consolidate memories. We cast per-synapse consolidation as a Doob…

cs.LG2026

Level-Crossing Density as a Mesh-Free High-Frequency Auxiliary Loss for Implicit Neural Representations

Gunner Levi Howe

The Minkowski functionals of a field's excursion sets -- area, boundary measure, and Euler characteristic -- describe its level-set morphology; the Euler characteristic is the chea…

cs.LG2026

Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting

Gunner Levi Howe

Training data for machine learning is routinely collected by a selection process the model never sees: loans are observed only when granted, outcomes only when a test was ordered.…