conftrace_

block-wise descent

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

memory-efficient fine-tuning (1) gradient sparsity (1) large language model (1) hybrid training (1) zeroth-order optimization (1)

Papers

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024