conftrace_

backward propagation

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

n:m sparsity (2) weight permutation (1) stochastic modified equation (1) quantized fine-tuning (1) activation compression (1) forward propagation (1) large language model (1) non-linear layer (1) moving average (1) transfer-based attack (1)

Papers

BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training ICML 2025 BP-Modified Local Loss for Efficient Training of Deep Neural Networks ICLR 2025 DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation NeurIPS 2024 Bi-directional Masks for Efficient N:M Sparse Training ICML 2023 DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023 Rethinking the Backward Propagation for Adversarial Transferability NeurIPS 2023 Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation EACL 2023 Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization ICLR 2020