Copertina

Accelerated zero-order SGD under high-order smoothness and overparameterized regime

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bychkov, Georgii, Dvinskikh, Darina, Antsiferova, Anastasia, Gasnikov, Alexander, Lobanov, Aleksandr
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Optimization and Control Machine Learning 65K10 G.1.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Decentralised convex optimisation with probability-proportional-to-size quantization
di: Pasechniuk, Dmitrii, et al.
Pubblicazione: (2025)

Heterogeneous-Horizon Exact-Weight Local SGD
di: Pasechnyuk-Vilensky, Dmitry, et al.
Pubblicazione: (2026)

Cubic Regularized Newton Method with Variance Reduction for Finite-sum Non-convex Problems
di: Pasechnyuk-Vilensky, Dmitry, et al.
Pubblicazione: (2025)

Zeroth-order gradient estimators for stochastic problems with decision-dependent distributions
di: Hikima, Yuya, et al.
Pubblicazione: (2025)

Handbook of Convergence Theorems for (Stochastic) Gradient Methods
di: Garrigos, Guillaume, et al.
Pubblicazione: (2023)

Accelerating MPGP-type Methods Through Preconditioning
di: Kružík, Jakub, et al.
Pubblicazione: (2025)

An objective-function-free algorithm for general smooth constrained optimization
di: Bellavia, S., et al.
Pubblicazione: (2026)

Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity
di: Suvorikova, Alexandra, et al.
Pubblicazione: (2026)

Where's Ben Nevis? A 2D optimisation benchmark with 957,174 local optima based on Great Britain terrain data
di: Wei, Yuhang, et al.
Pubblicazione: (2024)

Data-Dependent Complexity of First-Order Methods for Binary Classification
di: Hough, Matthew, et al.
Pubblicazione: (2025)

A Primal-Dual Frank-Wolfe Algorithm for Linear Programming
di: Hough, Matthew, et al.
Pubblicazione: (2024)

Projections onto Spectral Matrix Cones
di: Cederberg, Daniel, et al.
Pubblicazione: (2025)

Gradient-free algorithm for saddle point problems under overparametrization
di: Statkevich, Ekaterina, et al.
Pubblicazione: (2024)

Accelerated Zero-Order SGD Method for Solving the Black Box Optimization Problem under "Overparametrization" Condition
di: Lobanov, Aleksandr, et al.
Pubblicazione: (2023)

Majorization-Minimization-Based Levenberg--Marquardt Method for Constrained Nonlinear Least Squares
di: Marumo, Naoki, et al.
Pubblicazione: (2020)

Physics-based Approximation and Prediction of Speedlines in Compressor Performance Maps
di: Akiev, Abdul-Malik, et al.
Pubblicazione: (2026)

ASMOP: Additional sampling stochastic trust region method for multi-objective problems
di: Jerinkić, Nataša Krklec, et al.
Pubblicazione: (2025)

IPAS: An Adaptive Sample Size Method for Weighted Finite Sum Problems with Linear Equality Constraints
di: Krejić, Nataša, et al.
Pubblicazione: (2025)

Privacy of the last iterate in cyclically-sampled DP-SGD on nonconvex composite losses
di: Kong, Weiwei, et al.
Pubblicazione: (2024)

Stochastic Multiresolution Image Sketching for Inverse Imaging Problems
di: Perelli, Alessandro, et al.
Pubblicazione: (2024)

A Simple First-Order Algorithm for Full-Rank Equality Constrained Optimization
di: Gratton, Serge, et al.
Pubblicazione: (2025)

An objective-function-free algorithm for nonconvex stochastic optimization with deterministic equality and inequality constraints
di: Gratton, S., et al.
Pubblicazione: (2026)

Active set identification and rapid convergence for degenerate primal-dual problems
di: Díaz, Mateo, et al.
Pubblicazione: (2026)

A trust-region funnel algorithm for gray-box optimization
di: Hameed, Gul, et al.
Pubblicazione: (2025)

Adaptive Stochastic Gradient Descent Ascent Algorithm for Nonconvex Minimax Problems with Decision-Dependent Distributions
di: Gao, Yan, et al.
Pubblicazione: (2025)

PETScML: Second-order solvers for training regression problems in Scientific Machine Learning
di: Zampini, Stefano, et al.
Pubblicazione: (2024)

Subgradient Langevin Methods for Sampling from Non-smooth Potentials
di: Habring, Andreas, et al.
Pubblicazione: (2023)

Sampling-Based Risk-Aware Path Planning Around Dynamic Engagement Zones
di: Wolek, Artur, et al.
Pubblicazione: (2024)

Optimal Matrix-Mimetic Tensor Algebras via Variable Projection
di: Newman, Elizabeth, et al.
Pubblicazione: (2024)

Learning Gradient Flow: Using Equation Discovery to Accelerate Engineering Optimization
di: Norman, Grant, et al.
Pubblicazione: (2026)

Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum
di: Zhang, Minxin, et al.
Pubblicazione: (2026)

Randomized gradient-free methods in convex optimization
di: Gasnikov, Alexander, et al.
Pubblicazione: (2022)

A Data-Constrained Framework for Marine Biogeochemistry Modeling with Applications to the Paranaguá Estuarine Complex
di: Becher, Leticia
Pubblicazione: (2026)

The ensmallen library for flexible numerical optimization
di: Curtin, Ryan R., et al.
Pubblicazione: (2021)

About some works of Boris Polyak on convergence of gradient methods and their development
di: Ablaev, Seydamet, et al.
Pubblicazione: (2023)

Bregman Proximal Method for Efficient Communications under Similarity
di: Beznosikov, Aleksandr, et al.
Pubblicazione: (2023)

A three-step framework for noisy image segmentation in brain MRI
di: Antonelli, Laura, et al.
Pubblicazione: (2025)

Regularization of the discrete source problem in the nonlinear diffusive-logistic equation
di: Krivorotko, Olga, et al.
Pubblicazione: (2024)

Diffusion at Absolute Zero: Langevin Sampling using Successive Moreau Envelopes [journal paper]
di: Habring, Andreas, et al.
Pubblicazione: (2025)

Formalization of Complexity Analysis of the First-order Algorithms for Convex Optimization
di: Li, Chenyi, et al.
Pubblicazione: (2024)