Stochastic Gradient Descent for Operator Learning in Hilbert Spaces: Convergence Rates and Minimax Lower Bounds
stat.ML, cs.LG, math.FA, math.ST, stat.TH
Submitted: 2024-02-07
Updated: 2026-09-12
Comments: 62 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Structure-Preserving Operator Learning
- Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem
- Randomized Nystr\"om approximation of non-negative self-adjoint operators
- Learning operators for identifying weak solutions to the Navier-Stokes equations
- Neural Operators for Nonlinear Functionals on RKHS
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey