conftrace_

backward propagation

5 papers

Explore in graph

Co-occurring keywords

weight permutation (8) quantized fine-tuning (4) activation compression (4) large language model (13587) non-linear layer (2) transfer-based attack (15) n:m sparsity (4) integer propagation (1) 8-bit arithmetic (1) adversarial example (564)

Papers

DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation NIPS 2024
DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023
Bi-directional Masks for Efficient N:M Sparse Training ICML 2023
Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation EACL 2023
Rethinking the Backward Propagation for Adversarial Transferability NIPS 2023