On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “neurovarieties”

Activation degree thresholds and expressiveness of polynomial neural networkscs.LG

Polynomial neural networks explore thresholds for maximum expressiveness.

problem Understanding the limits of polynomial neural networks' expressiveness.

method Introducing activation degree threshold to measure network expressiveness and proving its existence and upper bounds.

result Polynomial neural networks with equi-width architectures achieve the maximum expressiveness.

polynomial neural networks expressiveness neurovariety activation degree threshold maximal expressiveness

2024-08-08abs ↗pdf ↗

Geometry of Polynomial Neural Networksmath.AG

Study the expressivity and training complexity of polynomial neural networks.

problem Understanding the expressivity and training complexity of polynomial neural networks.

method Use algebraic geometry to describe neuromanifolds and neurovarieties, analyzing their dimension and learning degree.

result Characterized the dimension and learning degree of neuromanifolds, providing geometric and complexity measures.

polynomial neural networks algebraic geometry neuromanifolds neurovarieties expressivity

2024-02-01abs ↗pdf ↗

Identifiability of Deep Polynomial Neural Networkscs.LG

Study on identifiability of deep polynomial neural networks.

problem Understanding when polynomial neural networks can be uniquely identified.

method Comprehensive analysis including various architectures, using tensor decompositions and Kruskal-type theorems.

result Identifiability conditions for deep PNNs, including layer width and activation degree constraints.

Polynomial Neural Networks Identifiability Tensor Decompositions Kruskal's Theorem Layer Width

2025-06-20abs ↗pdf ↗