Scaling Recurrent Neural Networks to a Billion Parameters with Zero-Order Optimization

Documenti analoghi

• Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering
  di: Chaubard, Francois, et al.
  Pubblicazione: (2024)
• Graph Q-Learning for Combinatorial Optimization
  di: Dax, Victoria M., et al.
  Pubblicazione: (2024)
• Hierarchical Zero-Order Optimization for Deep Neural Networks
  di: Cao, Sansheng, et al.
  Pubblicazione: (2026)
• Failure Probability Estimation for Black-Box Autonomous Systems using State-Dependent Importance Sampling Proposals
  di: Delecki, Harrison, et al.
  Pubblicazione: (2024)
• Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
  di: Lützow, Laura, et al.
  Pubblicazione: (2025)