Image de couverture de livre

Cubic regularized subspace Newton for non-convex optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Jim, Lucchi, Aurelien, Doikov, Nikita
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Numerical Analysis Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Stochastic Cubic Newton with Momentum
par: Chayti, El Mahdi, et autres
Publié: (2024)

Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods
par: Chayti, El Mahdi, et autres
Publié: (2023)

A distributed semismooth Newton based augmented Lagrangian method for distributed optimization
par: Ma, Qihao, et autres
Publié: (2026)

Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization
par: Ranganath, Aditya, et autres
Publié: (2025)

First-order methods for stochastic and finite-sum convex optimization with deterministic constraints
par: Lu, Zhaosong, et autres
Publié: (2025)

Random Subspace Cubic-Regularization Methods, with Applications to Low-Rank Functions
par: Cartis, Coralia, et autres
Publié: (2025)

A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks
par: Mishra, Neel, et autres
Publié: (2024)

Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton
par: Niu, Chengmei, et autres
Publié: (2025)

RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees
par: Laufer, Eilon Vaknin, et autres
Publié: (2025)

Convergence of Adam for Non-convex Objectives: Relaxed Hyperparameters and Non-ergodic Case
par: He, Meixuan, et autres
Publié: (2023)

Linear convergence of forward-backward accelerated algorithms without knowledge of the modulus of strong convexity
par: Li, Bowen, et autres
Publié: (2023)

Online Covariance Matrix Estimation in Sketched Newton Methods
par: Kuang, Wei, et autres
Publié: (2025)

A novel dual-decomposition method for non-convex two-stage stochastic mixed-integer quadratically constrained quadratic problems
par: Belyak, Nikita, et autres
Publié: (2023)

Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems
par: Dereich, Steffen, et autres
Publié: (2025)

Continuum-marginal optimal transport: a mesh-free kernel method
par: Nakano, Yumiharu
Publié: (2026)

Extended-Krylov-subspace methods for trust-region and norm-regularization subproblems
par: Daas, Hussam Al, et autres
Publié: (2025)

Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance
par: Stollenwerk, Alexander, et autres
Publié: (2024)

PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning
par: Jentzen, Arnulf, et autres
Publié: (2025)

Real-time optimal control of high-dimensional parametrized systems by deep learning-based reduced order models
par: Tomasetto, Matteo, et autres
Publié: (2024)

Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses
par: Dereich, Steffen, et autres
Publié: (2024)

Regularized methods via cubic model subspace minimization for nonconvex optimization
par: Bellavia, Stefania, et autres
Publié: (2023)

A second-order method landing on the Stiefel manifold via Newton$\unicode{x2013}$Schulz iteration
par: Xiong, Xinhui, et autres
Publié: (2026)

Nonlinear Assimilation via Score-based Sequential Langevin Sampling
par: Ding, Zhao, et autres
Publié: (2024)

Langevin dynamics based algorithm e-TH$\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient
par: Lim, Dong-Young, et autres
Publié: (2022)

On a fixed-point continuation method for a convex optimization problem
par: Fest, Jean-Baptiste, et autres
Publié: (2022)

An accelerated gradient method with adaptive restart for convex multiobjective optimization problems
par: Luo, Hao, et autres
Publié: (2025)

WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points
par: Li, Dongyue, et autres
Publié: (2026)

Backtracking New Q-Newton's method, Newton's flow, Voronoi's diagram and Stochastic root finding
par: Fornaess, John Erik, et autres
Publié: (2024)

On the non-convexity issue in the radial Calderón problem
par: Alberti, Giovanni S., et autres
Publié: (2025)

Ensemble Kalman inversion with non-smooth regularization
par: Weissmann, Simon
Publié: (2026)

Augmented Lagrangian methods for infeasible convex optimization problems and diverging proximal-point algorithms
par: Andrews, Roland, et autres
Publié: (2025)

Creating walls to avoid unwanted points in root finding and optimization
par: Truong, Tuyen Trung
Publié: (2023)

Stochastic dual coordinate descent with adaptive heavy ball momentum for linearly constrained convex optimization
par: Zeng, Yun, et autres
Publié: (2023)

The Rank-1 Completion Problem for Cubic Tensors
par: Zhou, Jinling, et autres
Publié: (2024)

A non-monotone smoothing Newton algorithm for solving the system of generalized absolute value equations
par: Chen, Cairong, et autres
Publié: (2021)

On the numerical reliability of nonsmooth autodiff: a MaxPool case study
par: Boustany, Ryan
Publié: (2024)

Subhomogeneous Deep Equilibrium Models
par: Sittoni, Pietro, et autres
Publié: (2024)

Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging
par: Banerjee, Amartya, et autres
Publié: (2024)

Anderson Acceleration in Nonsmooth Problems: Local Convergence via Active Manifold Identification
par: Li, Kexin, et autres
Publié: (2024)

KANtrol: A Physics-Informed Kolmogorov-Arnold Network Framework for Solving Multi-Dimensional and Fractional Optimal Control Problems
par: Aghaei, Alireza Afzal
Publié: (2024)