Article

What Makes Neural Networks Trainable? Invexity as a Structural Design Principle in AI

2025-08-04

Abstract excerpt

<title>Abstract</title> <p>Despite their non-convex loss landscapes and vast parameter spaces, deep neural networks consistently achieve high performance across domains –from medical diagnostics to natural language processing and computer vision. However, the theoretical basis for their trainability remains unclear. Classical frameworks, such as convex optimization or probabilistic models (e.g., Bayesian optimiza...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8fce93fd-528a-57fe-bf97-8e19b2c75a7c
DOI: 10.21203/rs.3.rs-7215670/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

What Makes Neural Networks Trainable? Invexity as a Structural Design Principle in AIDOI 10.21203/rs.3.rs-7215670/v1Read

Specxai - Spectral Interpretability of Deep Learning ModelsSemantic proximity Read

Backpropagation-Free Continual Learning: A Unified Energy-Based Framework, Reproducible Benchmark, and Open ChallengesSemantic proximity Read

A Research Programme for Continual and Neurosymbolic Learning in Epistemic Artificial IntelligenceSemantic proximity Read

DNNBrain: a unifying toolbox for mapping deep neural networks and brainsSemantic proximity Read

Scalable and Interpretable Mixture of Experts Models in Machine Learning: Foundations, Applications, and ChallengesSemantic proximity Read

A layer-resolved diagnostic identifies bias-driven decisions in deep neural networksSemantic proximity Read

Task-Conditional Accuracy–Support Trade-offs of Sparse Attention Normalizers in Compact ClassifiersSemantic proximity Read

Direct-fit to nature: an evolutionary perspective on biological (and artificial) neural networksSemantic proximity Read

Scaffolded representation learning in deep networksSemantic proximity Read

Statistical Order in Representation Learning: Sufficiency, Architectural Blindness, and Generalization Bounds via Maximum EntropySemantic proximity Read

Large-scale hyperparameter search for predicting human brain responses in the Algonauts challengeSemantic proximity Read

Training stochastic stabilized supralinear networks by dynamics-neutral growthSemantic proximity Read