conftrace_

gpu memory efficiency

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hessian-informed optimization (1) transformer pruning (1) large language model fine-tuning (1) taylor approximation (1) model convergence (1) parameter-efficient fine-tuning (1) zeroth-order optimization (1) model pruning (1) fisher information (1) knowledge distillation (1)

Papers

Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer ICLR 2025 Resource-Efficient Transformer Pruning for Finetuning of Large Models CVPR 2024