PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training

Documenti analoghi

• Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
  di: Chmiel, Brian, et al.
  Pubblicazione: (2022)
• OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
  di: Pardeshi, Kanad, et al.
  Pubblicazione: (2025)
• Beyond ReinMax: Low-Variance Gradient Estimators for Discrete Latent Variables
  di: Wang, Daniel, et al.
  Pubblicazione: (2026)
• Gradient Weight-normalized Low-rank Projection for Efficient LLM Training
  di: Huang, Jia-Hong, et al.
  Pubblicazione: (2024)
• Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion Models
  di: Zhang, Fengzhe, et al.
  Pubblicazione: (2025)