arXiv:2607. 07156v2 Announce Type: replace Abstract: Implicit bias is usually explained as the preference of an optimization process for certain final solutions and their geometry.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2607. 07156v1 Announce Type: new Abstract: Different optimizers have different update biases, but these biases are usually implicit.
arXiv:2608. 07157v1 Announce Type: new Abstract: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone.
arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.
arXiv:2512. 12816v2 Announce Type: replace Abstract: We study how to allocate resources for training and deployment of machine learning (ML) models under concept drift and limited budgets.
arXiv:2608. 01032v1 Announce Type: new Abstract: Training error is what we can observe on a training set; test error is the quantity we actually care about.
arXiv:2606. 00340v1 Announce Type: new Abstract: We study optimal learning-rate selection in two-layer and three-layer linear neural networks trained to learn linear target functions.