A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Recently, there has been emerging interest in constructing reproducing kernel Banach spaces (RKBS) for applied and theoretical purposes such as machine learning, sampling reconstruction, sparse approximation and functional analysis. Existing constructions include the reflexive RKBS via a bilinear form, the semi-inner-p…
Develops vector-valued RKBS for neural networks and operators.
Motivated by multi-task machine learning with Banach spaces, we propose the notion of vector-valued reproducing kernel Banach spaces (RKBS). Basic properties of the spaces and the associated reproducing kernels are investigated. We also present feature map constructions and several concrete examples of vector-valued RK…
Deep networks are shown to be equivalent to a new type of kernel chain.
Gradient descent in neural networks analyzed using RKBS for broader applicability.
Paper characterizes embeddability of function spaces into -type RKBS via metric entropy.
The paper defines a hypothesis space for deep learning using DNNs.
This paper extends mirror descent to Banach spaces with reproducing kernels.
Paper introduces new neural network models and theories.