Copertina

The global convergence time of stochastic gradient descent in non-convex landscapes: Sharp estimates via large deviations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Azizian, Waïss, Iutzeler, Franck, Malick, Jérôme, Mertikopoulos, Panayotis
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Optimization and Control Machine Learning Primary 90C15, 90C26, 60F10, secondary 90C30, 68Q32
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

What is the long-run distribution of stochastic gradient descent? A large deviations analysis
di: Azizian, Waïss, et al.
Pubblicazione: (2024)

The rate of convergence of Bregman proximal methods: Local geometry vs. regularity vs. sharpness
di: Azizian, Waïss, et al.
Pubblicazione: (2022)

$\texttt{skwdro}$: a library for Wasserstein distributionally robust machine learning
di: Vincent, Florian, et al.
Pubblicazione: (2024)

Exact Solution to Data-Driven Inverse Optimization of MILPs in Finite Time via Gradient-Based Methods
di: Kitaoka, Akira
Pubblicazione: (2024)

Gaussian smoothing gradient descent for minimizing functions (GSmoothGD)
di: Starnes, Andrew, et al.
Pubblicazione: (2023)

A parameter-free approach for solving SOS-convex semi-algebraic fractional programs
di: Yang, Chengmiao, et al.
Pubblicazione: (2024)

Kinetic description and convergence analysis of genetic algorithms for global optimization
di: Borghi, Giacomo, et al.
Pubblicazione: (2023)

Bi-Objective Optimization over the Efficient Set of Multi-Objective Integer Quadratic Problem
di: Bencheikh, Ali, et al.
Pubblicazione: (2024)

New results on the local-nonglobal minimizers of the generalized trust-region subproblem
di: Ai, Wenbao, et al.
Pubblicazione: (2024)

Edge expansion of a graph: SDP-based computational strategies
di: Gupte, Akshay, et al.
Pubblicazione: (2024)

Closing the duality gap of the generalized trace ratio problem
di: Yang, Meijia, et al.
Pubblicazione: (2024)

Optimality Conditions and Duality for Multiobjective Fractional Bilevel Optimization Problems
di: Lara, Felipe, et al.
Pubblicazione: (2025)

A polynomially solvable case of unconstrained (-1,1)-quadratic fractional optimization
di: Yang, Meijia, et al.
Pubblicazione: (2024)

On convergence of a $q$-random coordinate constrained algorithm for non-convex problems
di: Ghaffari-Hadigheh, Alireza, et al.
Pubblicazione: (2022)

On the convergence of proximal gradient methods for convex simple bilevel optimization
di: Latafat, Puya, et al.
Pubblicazione: (2023)

An efficient proximal algorithm for squared L1 over L2 regularized sparse recovery
di: Zhang, Na, et al.
Pubblicazione: (2025)

The Geometry of Linear Program Compression: An Exact Characterization and Learning Algorithm
di: Ye, Yuhan, et al.
Pubblicazione: (2026)

Conductance Estimation in Digraphs: Submodular Transformation, Lovász Extension and Dinkelbach Iteration
di: Shao, Sihong, et al.
Pubblicazione: (2025)

A constraint-based approach to function interpolation, with application to performance estimation for weakly convex optimisation
di: Rubbens, Anne, et al.
Pubblicazione: (2024)

A feasible smoothing accelerated projected gradient method for nonsmooth convex optimization
di: Nishioka, Akatsuki, et al.
Pubblicazione: (2023)

Bundle methods with quadratic cuts for deterministic and stochastic strongly convex optimization problems
di: Guigues, Vincent, et al.
Pubblicazione: (2017)

A Globally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization
di: Lin, Yizun, et al.
Pubblicazione: (2024)

On Optimality Conditions for Mathematical Programming Problems Based on Strong Subdifferentials
di: Lara, Felipe, et al.
Pubblicazione: (2026)

An ODE approach to multiple choice polynomial programming
di: Shao, Sihong, et al.
Pubblicazione: (2022)

Time-Varying Semidefinite Programming: Path Following a Burer-Monteiro Factorization
di: Bellon, Antonio, et al.
Pubblicazione: (2022)

Solving Regularized Multifacility Location Problems with Unknown Number of Centers via Difference-of-Convex Optimization
di: Geremew, W., et al.
Pubblicazione: (2026)

Nesterov's accelerated gradient for unbounded convex functions finds the minimum-norm point in the dual space
di: Sakabe, Keiya
Pubblicazione: (2026)

A min-max reformulation and proximal algorithms for a class of structured nonsmooth fractional optimization problems
di: Zhou, Junpeng, et al.
Pubblicazione: (2025)

Benchmarking of quantum and classical SDP relaxations for QUBO formulations of real-world logistics problems
di: Ostermann, Birte, et al.
Pubblicazione: (2025)

Auto-tuned Primal-dual Successive Convexification for Hypersonic Reentry Guidance
di: Mceowen, Skye, et al.
Pubblicazione: (2024)

Efficient parameter-free restarted accelerated gradient methods for convex and strongly convex optimization
di: Sujanani, Arnesh, et al.
Pubblicazione: (2024)

Hidden convexity of quadratic systems and its application to quadratic programming
di: Huy, Nguyen Quang, et al.
Pubblicazione: (2026)

Accelerating preconditioned ADMM via degenerate proximal point mappings
di: Sun, Defeng, et al.
Pubblicazione: (2024)

Adaptive proximal algorithms for convex optimization under local Lipschitz continuity of the gradient
di: Latafat, Puya, et al.
Pubblicazione: (2023)

Stochastic dynamic programming with non-linear discounting
di: Bäuerle, Nicole, et al.
Pubblicazione: (2020)

Benign landscapes of low-dimensional relaxations for orthogonal synchronization on general graphs
di: McRae, Andrew D., et al.
Pubblicazione: (2023)

Improved global performance guarantees of second-order methods in convex minimization
di: Dvurechensky, Pavel, et al.
Pubblicazione: (2024)

On the convergence of adaptive first order methods: proximal gradient and alternating minimization algorithms
di: Latafat, Puya, et al.
Pubblicazione: (2023)

A stochastic use of the Kurdyka-Lojasiewicz property: Investigation of optimization algorithms behaviours in a non-convex differentiable framework
di: Fest, Jean-Baptiste, et al.
Pubblicazione: (2023)

Application and issues in abstract convexity
di: Millán, Reinier Díaz, et al.
Pubblicazione: (2022)