Skip to content
conftrace_

lazy regime

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

feature learning (2) catastrophic forgetting (2) batch size (1) task similarity (1) magnitude pruning (1) neural network (1) phase diagram (1) approximation capacity (1) gradient pruning (1) balanced regime (1)

Papers

The Importance of Being Lazy: Scaling Limits of Continual Learning ICML 2025 Continual learning with the neural tangent ensemble NeurIPS 2024 How Two-Layer Neural Networks Learn, One (Giant) Step at a Time JMLR 2024 Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes NeurIPS 2024 Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together! ICLR 2023