Skip to content
conftrace_

training speedup

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network (2) efficient computing (2) computational complexity (2) neural network training (2) parallel cyclic reduction (1) sequential operation (1) incremental growth (1) variance transfer (1) weight-data correlation (1) run-length encoding (1)

Papers

Dynamic Sparse Training of Diagonally Sparse Networks ICML 2025 Don't Look Twice: Faster Video Transformers with Run-Length Tokenization NeurIPS 2024 Understanding the Training Speedup from Sampling with Approximate Losses ICML 2024 When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models ICML 2024 Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation NeurIPS 2023 Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing NeurIPS 2023 DeepPCR: Parallelizing Sequential Operations in Neural Networks NeurIPS 2023