Skip to content
conftrace_

gradient descent training

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

ridge function (1) parallel parameter optimization (1) group-sparse classification (1) statistical query lower bound (1) few-shot adaptation (1) two-layer neural network (1) information exponent (1) single-index model (1) recurrent neural network (1) additive model (1)

Papers

Transformer Learns Optimal Variable Selection in Group-Sparse Classification ICLR 2025 Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations COLT 2024 Oger: Modular Learning Architectures For Large-Scale Sequential Processing JMLR 2012