arXiv AI
Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Aug 31
Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework
Deep networks trained on noisy labels simultaneously generalize on clean data and memorize flipped labels. These are usually conflated as pressures on one capacity. We present Topo^2, a measurement fr...
arXiv AI
Sep 30
Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...
arXiv AI
Jun 29
Applicability of memorization indicators for early spotting of overfitting while recalibrating sEMG-decoders on low sample sizes
arXiv:2606. 27855v1 Announce Type: cross Abstract: Deep learning models for surface electromyography (sEMG) can benefit substantially from subject-specific (re-)calibration, since no sufficiently large and diverse datasets are available to train fully generic decoders.
arXiv AI
Jun 29
Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning
arXiv:2605. 20282v3 Announce Type: replace-cross Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics.
arXiv AI
Oct 1
Unmerge: Efficient Machine Unlearning via Task Arithmetic
The paper introduces Unmerge, an efficient machine unlearning algorithm that treats unlearning as the inverse of task arithmetic. By representing the forget component as a low‑rank basis at each layer, Unmerge optimizes three goals—matching the merged vector, suppressing leakage, and bounding correction size—to limit forget leakage and retain damage. Experiments on ResNet‑50, ViT‑S/16, and Llama‑3.2‑3B show significant performance gains over existing methods while maintaining privacy and feature‑distribution fidelity.
arXiv Machine Learning
4d ago
Factual recall in linear associative memories: sharp asymptotics and mechanistic insights
arXiv:2605.10795v2 Announce Type: replace-cross Abstract: Large language models excel at factual recall, yet the fundamental limits of storing input--output associations with neural networks remain u...