Research
A Bregman Proximal Viewpoint on Neural Operators
arXiv:2610.20120v1 Announce Type: new Abstract: We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems
arXiv:2610.20120v1 Announce Type: new Abstract: We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems over Banach function spaces. The proposed framework allows interpreting the activation operators as Bregman proximity operators from dual to primal space. This novel viewpoint is general enough to recover classical neural operators as well as a new variant, coined Bregman neural operators, which includes the inverse activation operator and features the same expressivity of standard neural operators. Numerical experiments support the added benefits of the Bregman variant of Fourier neural operators for training deeper and more accurate models.
Related
- Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels
- Taming Nonconvexity with Epigraph Lifting
- Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces
- Unrolled Neural Networks for Constrained Optimization
Source: arXiv cs.LG | 2026-10-15