Copertina

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dang, Thanh, Barsbey, Melih, Sonet, A K M Rokonuzzaman, Gurbuzbalaban, Mert, Simsekli, Umut, Zhu, Lingjiong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Optimization and Control Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Heavy-Tail Phenomenon in Decentralized SGD
di: Gurbuzbalaban, Mert, et al.
Pubblicazione: (2022)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
di: Şimşekli, Umut, et al.
Pubblicazione: (2024)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
di: Wan, Yijun, et al.
Pubblicazione: (2023)

Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise
di: Agrawal, Shubhada, et al.
Pubblicazione: (2026)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
di: Kassing, Sebastian, et al.
Pubblicazione: (2025)

Generalized EXTRA stochastic gradient Langevin dynamics
di: Gurbuzbalaban, Mert, et al.
Pubblicazione: (2024)

High-Order Langevin Monte Carlo Algorithms
di: Dang, Thanh, et al.
Pubblicazione: (2025)

Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
di: Ziyin, Liu, et al.
Pubblicazione: (2023)

Momentum Does Not Reduce Stochastic Noise in Stochastic Gradient Descent
di: Sato, Naoki, et al.
Pubblicazione: (2024)

RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
di: Fang, Cheng, et al.
Pubblicazione: (2025)

In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
di: Liu, Zijian
Pubblicazione: (2026)

An Improved Analysis of the Clipped Stochastic subGradient Method under Heavy-Tailed Noise
di: Parletta, Daniela Angela, et al.
Pubblicazione: (2024)

(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum
di: Dang, Anh, et al.
Pubblicazione: (2024)

Distributed Stochastic Optimization under Heavy-Tailed Noises
di: Sun, Chao, et al.
Pubblicazione: (2023)

Rényi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincaré Inequalities
di: Dupuis, Benjamin, et al.
Pubblicazione: (2025)

Non-Stationary Gradient Descent for Optimal Auto-Scaling in Serverless Platforms
di: Anselmi, Jonatha, et al.
Pubblicazione: (2025)

Bayesian Inferential Motion Planning Using Heavy-Tailed Distributions
di: Vaziri, Ali, et al.
Pubblicazione: (2025)

Distributed Stochastic Optimization under Heavy-Tailed Noise: A Federated Mirror Descent Approach with High Probability Convergence
di: Yu, Zhan, et al.
Pubblicazione: (2025)

Exact Dynamics of Multi-class Stochastic Gradient Descent
di: Collins-Woodfin, Elizabeth, et al.
Pubblicazione: (2025)

SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems
di: Zhang, Xuan, et al.
Pubblicazione: (2022)

DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks
di: Bajwa, Waheed U., et al.
Pubblicazione: (2025)

Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation
di: Mishkin, Aaron, et al.
Pubblicazione: (2024)

Almost Sure Convergence of Stochastic Approximation: An Interplay of Noise and Step Size
di: Nguyen, Quang Dinh Thien, et al.
Pubblicazione: (2026)

High Probability Convergence of Distributed Clipped Stochastic Gradient Descent with Heavy-tailed Noise
di: Yang, Yuchen, et al.
Pubblicazione: (2025)

Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
di: Liu, Zijian, et al.
Pubblicazione: (2024)

An Accelerated Primal Dual Algorithm with Backtracking for Decentralized Constrained Optimization
di: Xu, Qiushui, et al.
Pubblicazione: (2025)

Anchored Langevin Algorithms
di: Gurbuzbalaban, Mert, et al.
Pubblicazione: (2025)

Accelerated Gradient Methods with Biased Gradient Estimates: Risk Sensitivity, High-Probability Guarantees, and Large Deviation Bounds
di: Gürbüzbalaban, Mert, et al.
Pubblicazione: (2025)

Gradient estimates for semigroups associated with stochastic differential equations driven by cylindrical Lévy processes
di: Dang, Thanh, et al.
Pubblicazione: (2024)

Generalized Stochastic Gradient Descent with Momentum Methods for Smooth Optimization
di: Wang, Zimeng, et al.
Pubblicazione: (2026)

Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
di: Fradin, Adrien, et al.
Pubblicazione: (2025)

One-Dimensional McKean-Vlasov Stochastic Variational Inequalities and Coupled BSDEs with Locally Holder Noise Coefficients
di: Ning, Ning, et al.
Pubblicazione: (2023)

Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises
di: Zhu, Tianxi, et al.
Pubblicazione: (2025)

Optimal Asynchronous Stochastic Nonconvex Optimization under Heavy-Tailed Noise
di: Wu, Yidong, et al.
Pubblicazione: (2026)

A Stochastic GDA Method With Backtracking For Solving Nonconvex Concave Minimax Problems
di: Aybat, Necdet Serhat, et al.
Pubblicazione: (2024)

Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise
di: Bakkali, Taha El, et al.
Pubblicazione: (2026)

Flatness-Aware Stochastic Gradient Langevin Dynamics
di: Bruno, Stefano, et al.
Pubblicazione: (2025)

Linear Algebraic Truncation Algorithm with A Posteriori Error Bounds for Computing Markov Chain Equilibrium Gradients
di: Mahdian, Saied, et al.
Pubblicazione: (2025)

Distributed Stochastic Optimization for Non-Smooth and Weakly Convex Problems under Heavy-Tailed Noise
di: Hu, Jun, et al.
Pubblicazione: (2025)

Computing Stationary Distribution via Dirichlet-Energy Minimization by Coordinate Descent
di: Avrachenkov, Konstantin, et al.
Pubblicazione: (2026)