All roads lead to Markov kernel networks: A representation theorem for discretization-stable learning
cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Hybrid operator learning of wave scattering maps in high-contrast media
- Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning
- Transformers through the lens of support-preserving maps between measures
- Transformers are Universal In-context Learners
- Function graph transformers universally approximate operators between function spaces
- Continuum limit of total variation on point clouds
- Discretization Error of Fourier Neural Operators
- Fourier Neural Operator for Parametric Partial Differential Equations
- DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
- Flowers: A Warp Drive for Neural PDE Solvers
- Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
- Attention Is All You Need
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis