Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization

Documenti analoghi

• MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity
  di: Macko, Vladimír, et al.
  Pubblicazione: (2025)
• Addition is almost all you need: Compressing large language models with double binary factorization
  di: Boža, Vladimír, et al.
  Pubblicazione: (2025)
• Fast and Effective Weight Update for Pruned Large Language Models
  di: Boža, Vladimír
  Pubblicazione: (2024)
• The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
  di: Chaabouni, Youssef, et al.
  Pubblicazione: (2025)
• Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
  di: Farnik, Lucy, et al.
  Pubblicazione: (2025)