Skip to content
conftrace_

memory saving

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backpropagation optimization (1) hadamard quantization (1) hadamard low-rank approximation (1) activation buffer compression (1) local loss (1) bias-variance balance (1) test top-1 accuracy (1) low-rank pruning (1) stochastic modified equation (1) linear combination (1)

Papers

BP-Modified Local Loss for Efficient Training of Deep Neural Networks ICLR 2025 HOT: Hadamard-based Optimized Training CVPR 2025 Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models ICML 2025