Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate

Ähnliche Einträge

• Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
  von: Yang, Yingzhen, et al.
  Veröffentlicht: (2024)
• Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression
  von: Yang, Yingzhen, et al.
  Veröffentlicht: (2024)
• Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits
  von: Liu, Jingyu, et al.
  Veröffentlicht: (2025)
• Finite-Particle Rates for Regularized Stein Variational Gradient Descent
  von: He, Ye, et al.
  Veröffentlicht: (2026)
• Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
  von: Genans, Ferdinand, et al.
  Veröffentlicht: (2025)