Image de couverture de livre

In almost all shallow analytic neural network optimization landscapes, efficient minimizers have strongly convex neighborhoods

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Benning, Felix, Dereich, Steffen
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Probability 60G15, 60G60, 62J02, 62M45, 68T07
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fractal and Regular Geometry of Deep Neural Networks
par: Di Lillo, Simmaco, et autres
Publié: (2025)

LDP for the covariance process in fully connected neural networks
par: Andreis, Luisa, et autres
Publié: (2025)

Spectral complexity of deep neural networks
par: Di Lillo, Simmaco, et autres
Publié: (2024)

Generalization Error of GAN from the Discriminator's Perspective
par: Yang, Hongkang, et autres
Publié: (2021)

Estimation of the invariant measure of a multidimensional diffusion from noisy observations
par: Maillet, Raphaël, et autres
Publié: (2024)

Dirichlet kernel density estimation for strongly mixing sequences on the simplex
par: Daayeb, Hanen, et autres
Publié: (2025)

A dependent and censored first hitting-time model with compound Poisson processes
par: Escobar-Bach, Mikael, et autres
Publié: (2025)

Edge-indexed network time series with graph Ornstein-Uhlenbeck dynamics
par: Chen, Jiaming, et autres
Publié: (2026)

Polynomial Chaos Surrogate Construction for Random Fields with Parametric Uncertainty
par: Mueller, Joy N., et autres
Publié: (2023)

Nonparametric estimation of trawl processes: Theory and applications
par: Sauri, Orimar, et autres
Publié: (2022)

Spatio-temporal probabilistic forecast using MMAF-guided learning
par: Bardi, Leonardo, et autres
Publié: (2026)

Sharp Convergence Rates of Empirical Unbalanced Optimal Transport for Spatio-Temporal Point Processes
par: Struleva, Marina, et autres
Publié: (2025)

Parameter Estimation of Long Memory Stochastic Processes with Deep Neural Networks
par: Csanády, Bálint, et autres
Publié: (2024)

On nonparametric estimation of the interaction function in particle system models
par: Belomestny, Denis, et autres
Publié: (2024)

Sobol' Matrices For Multi-Output Models With Quantified Uncertainty
par: Milton, Robert A., et autres
Publié: (2025)

Scalable non-separable spatio-temporal Gaussian process models for large-scale short-term weather prediction
par: Gyger, Tim, et autres
Publié: (2026)

Martingale Posterior Predictive Coherence: Hausdorff Moment Hierarchy
par: Polson, Nicholas G., et autres
Publié: (2026)

Deconvolution of distribution functions without integral transforms
par: Kaiser, Henrik
Publié: (2025)

Critical Points of Random Neural Networks
par: Di Lillo, Simmaco
Publié: (2025)

TwinKernel Estimation for Point Process Intensity Functions: Adaptive Nonparametric Methods via Orbital Regularity
par: Nembé, Jocelyn
Publié: (2025)

Nonparametric density estimation for stationary processes under multiplicative measurement errors
par: Dang, Duc Trong, et autres
Publié: (2024)

Wide stable neural networks: Sample regularity, functional convergence and Bayesian inverse problems
par: Soto, Tomás
Publié: (2024)

Deconvolution of Arbitrary Distribution Functions and Densities
par: Kaiser, Henrik
Publié: (2025)

Testing for jumps in processes with integral fractional part and jump-robust inference on the Hurst exponent
par: Bibinger, Markus, et autres
Publié: (2023)

Modified wavelet variation for the Hermite processes
par: Loosveldt, Laurent, et autres
Publié: (2024)

High-dimensional Bayesian filtering through deep density approximation
par: Bågmark, Kasper, et autres
Publié: (2025)

Nonlinear filtering based on density approximation and deep BSDE prediction
par: Bågmark, Kasper, et autres
Publié: (2025)

A hybrid-Hill estimator enabled by heavy-tailed block maxima
par: Neves, Claudia, et autres
Publié: (2025)

Modified weighted power variations of the Hermite process and applications to integrated volatility
par: Ayache, Antoine, et autres
Publié: (2026)

Statistical inference for Levy-driven graph supOU processes: From short- to long-memory in high-dimensional time series
par: Mehta, Shreya, et autres
Publié: (2025)

A convergent scheme for the Bayesian filtering problem based on the Fokker--Planck equation and deep splitting
par: Bågmark, Kasper, et autres
Publié: (2024)

Convergence rates of non-stationary and deep Gaussian process regression
par: Osborne, Conor, et autres
Publié: (2023)

Quasi-Banach spaces of random variables and stochastic processes
par: Kozachenko, Yuriy, et autres
Publié: (2026)

Model-free filtering in high dimensions via projection and score-based diffusions
par: Christensen, Sören, et autres
Publié: (2025)

Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs
par: Celli, Lucia
Publié: (2026)

A functional Hungarian construction for sums of independent random variables
par: Grama, Ion, et autres
Publié: (2024)

The Poisson transport map
par: López-Rivera, Pablo, et autres
Publié: (2024)

Hölder regularity and roughness: construction and examples
par: Bayraktar, Erhan, et autres
Publié: (2023)

Large deviation principles and functional limit theorems in the deep limit of wide random neural networks
par: Di Lillo, Simmaco, et autres
Publié: (2026)

Cluster size distributions of discrete random fields
par: Cheng, Dan, et autres
Publié: (2026)