3 papers
cs.CL2024
Efficient Stagewise Pretraining via Progressive Subnetworks
Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu +4
Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and…
cs.CL2024
On the Inductive Bias of Stacking Towards Improving Reasoning
Nikunj Saunshi, Stefani Karp, Shankar Krishnan +3
Given the increasing scale of model sizes, novel training strategies like gradual stacking [Gong et al., 2019, Reddi et al., 2023] have garnered interest. Stacking enables efficien…
cs.LG2024
Landscape-Aware Growing: The Power of a Little LAG
Stefani Karp, Nikunj Saunshi, Sobhan Miryoosefi +2
Recently, there has been increasing interest in efficient pretraining paradigms for training Transformer-based models. Several recent approaches use smaller models to initialize la…