Skip to content
conftrace_

sparse initialization

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network pruning (2) extreme sparsity (1) dct plus sparse (1) magnitude-based pruning (1) network sparsification (1) dense initialization (1) arbitrary densities (1) orthogonality (1) deep feature learning (1) givens rotation (1)

Papers

Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization ICML 2024 Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training NeurIPS 2023 Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck NeurIPS 2023 Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset ICML 2021