conftrace_

subnetwork training

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

evolving subnetworks (1) flops saving (1) gpt2 (1) tinyllama (1) stagewise training (1) layer dropping (1) pre-training method (1) large language model (1) neural network initialization (1) convolutional neural network (1)

Papers

Efficient stagewise pretraining via progressive subnetworks ICLR 2025 Evolving Subnetwork Training for Large Language Models ICML 2024 Exclusive Supermask Subnetwork Training for Continual Learning ACL 2023 Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks ICLR 2022