Image de couverture de livre

Fast Spawn\&Prune (FS\&P): Global convergence of stochastic conic particle gradient descent via birth/death process

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	De Castro, Yohann, Gadat, Sébastien, Marteau, Clément
Format:	Preprint
Publié:	2026
Sujets:	Optimization and Control Probability Statistics Theory Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures
par: De Castro, Yohann, et autres
Publié: (2023)

CV@R penalized portfolio optimization with biased stochastic mirror descent
par: Costa, Manon, et autres
Publié: (2024)

Consistent estimation in subcritical birth-and-death processes
par: Hautphenne, Sophie, et autres
Publié: (2025)

A stochastic gradient descent algorithm with random search directions
par: Gbaguidi, Eméric
Publié: (2025)

Universality of high-dimensional scaling limits of stochastic gradient descent
par: Gheissari, Reza, et autres
Publié: (2025)

Privately Learning Smooth Distributions on the Hypercube by Projections
par: Lalanne, Clément, et autres
Publié: (2024)

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
par: Mou, Wenlong, et autres
Publié: (2021)

Exponential convergence rates for momentum stochastic gradient descent in the overparametrized setting
par: Gess, Benjamin, et autres
Publié: (2023)

Linear convergence of proximal descent schemes on the Wasserstein space
par: Lascu, Razvan-Andrei, et autres
Publié: (2024)

An abstract effective convergence theorem for stochastic processes, with applications to stochastic approximation
par: Neri, Morenikeji, et autres
Publié: (2025)

To spike or not to spike: the whims of the Wonham filter in the strong noise regime
par: Bernardin, Cédric, et autres
Publié: (2022)

High dimensional analysis reveals conservative sharpening and a stochastic edge of stability
par: Agarwala, Atish, et autres
Publié: (2024)

Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting
par: Neufeld, Ariel, et autres
Publié: (2022)

Gaussian Mixture Model with unknown diagonal covariances via continuous sparse regularization
par: Giard, Romane, et autres
Publié: (2025)

Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks
par: Liang, Luxu, et autres
Publié: (2024)

Target search optimization by threshold resetting
par: Biswas, Arup, et autres
Publié: (2025)

Optimal threshold resetting in collective diffusive search
par: Biswas, Arup, et autres
Publié: (2026)

Finding planted cliques using gradient descent
par: Gheissari, Reza, et autres
Publié: (2023)

Sharp Rates of MMD Empirical Estimation with Power Kernels
par: Colasanto, Francesco, et autres
Publié: (2026)

Queues with service resetting
par: Bonomo, Ofek Lauber, et autres
Publié: (2023)

Central limit theorems for vector-valued composite functionals with smoothing and applications
par: Chen, Huihui, et autres
Publié: (2024)

Wasserstein Distributionally Robust Optimization with Heterogeneous Data Sources
par: Rychener, Yves, et autres
Publié: (2024)

Optimal transport and Wasserstein distances for causal models
par: Cheridito, Patrick, et autres
Publié: (2023)

Optimal distributions for randomized unbiased estimators with an infinite horizon and an adaptive algorithm
par: Zheng, Chao, et autres
Publié: (2023)

Gaussian random field's anisotropy using excursion sets
par: Azaïs, Jean-Marc, et autres
Publié: (2025)

Controlled stochastic processes for simulated annealing
par: Molin, Vincent, et autres
Publié: (2025)

Markov decision processes: on the convergence of the Monte-Carlo first visit algorithm
par: Delattre, Sylvain, et autres
Publié: (2025)

Efficient factored gradient descent algorithm for quantum state tomography
par: Wang, Yong, et autres
Publié: (2022)

Nonconvex optimization and convergence of stochastic gradient descent, and solution of asynchronous game
par: Buck, Kevin, et autres
Publié: (2025)

Randomized coordinate gradient descent almost surely escapes strict saddle points
par: Chen, Ziang, et autres
Publié: (2025)

Wasserstein convergence rates for empirical measures of point processes
par: Huang, Dongzhou, et autres
Publié: (2026)

Estimation of a pure-jump stable Cox-Ingersoll-Ross process
par: Bayraktar, Elise, et autres
Publié: (2023)

Global-in-time optimal control of stochastic third-grade fluids with additive noise
par: Kinra, Kush, et autres
Publié: (2025)

Optimal sampling for stochastic and natural gradient descent
par: Gruhlke, Robert, et autres
Publié: (2024)

Error analysis for stochastic gradient optimization schemes using modified equations
par: Bréhier, Charles-Edouard, et autres
Publié: (2024)

The generator gradient estimator is an adjoint state method for stochastic differential equations
par: Badolle, Quentin, et autres
Publié: (2024)

Approximation of birth-death processes
par: Li, Liping
Publié: (2024)

Global convergence of gradient descent for phase retrieval
par: Fougereux, Théodore, et autres
Publié: (2024)

Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression
par: Agrawalla, Bhavya, et autres
Publié: (2023)

Well-posedness and approximation of reflected McKean-Vlasov SDEs with applications
par: Hinds, P. D., et autres
Publié: (2024)