Copertina

Losing momentum in continuous-time stochastic optimisation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jin, Kexin, Latz, Jonas, Liu, Chenguang, Scagliotti, Alessandro
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Optimization and Control Machine Learning Numerical Analysis 90C15, 37N40, 37H30, 65C40, 68T07, 68W20
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Power Homotopy for Zeroth-Order Non-Convex Optimizations
di: Xu, Chen
Pubblicazione: (2025)

Global Optimization with A Power-Transformed Objective and Gaussian Smoothing
di: Xu, Chen
Pubblicazione: (2024)

On the boundedness of the sequence generated by minibatch stochastic gradient descent
di: Bauschke, Heinz H., et al.
Pubblicazione: (2025)

Progressive Power Homotopy for Non-convex Optimization
di: Xu, Chen
Pubblicazione: (2026)

The Güler-type acceleration for proximal gradient, linearized augmented Lagrangian and linearized alternating direction method of multipliers
di: Zhou, Bin, et al.
Pubblicazione: (2025)

Some Remarks on the Optimal Level of Randomization in Global Optimization
di: Theodosopoulos, Ted
Pubblicazione: (2004)

Distributed Computing for Huge-Scale Aggregative Convex Programming
di: Tao, Luoyi
Pubblicazione: (2026)

Convergence of iterates and improved rates for accelerated augmented Lagrangian methods for linearly constrained convex optimization
di: He, Xin, et al.
Pubblicazione: (2026)

Data Augmentation and Regularization for Learning Group Equivariance
di: Nordenfors, Oskar, et al.
Pubblicazione: (2025)

Optimization Dynamics of Equivariant and Augmented Neural Networks
di: Nordenfors, Oskar, et al.
Pubblicazione: (2023)

How to beat a Bayesian adversary
di: Ding, Zihan, et al.
Pubblicazione: (2024)

Convergence of Markov Chains for Constant Step-size Stochastic Gradient Descent with Separable Functions
di: Shirokoff, David, et al.
Pubblicazione: (2024)

A Learning Stability Profile for Finite-Dimensional Learning Dynamics
di: Katende, Ronald
Pubblicazione: (2025)

Residual Multi-Fidelity Neural Network Computing
di: Davis, Owen, et al.
Pubblicazione: (2023)

General Constrained Matrix Optimization
di: Garner, Casey, et al.
Pubblicazione: (2024)

Spectrally Constrained Optimization
di: Garner, Casey, et al.
Pubblicazione: (2023)

A Stochastic Objective-Function-Free Adaptive Regularization Method with Optimal Complexity
di: Gratton, Serge, et al.
Pubblicazione: (2024)

Iteration complexity of the Difference-of-Convex Algorithm for unconstrained optimization: a simple proof
di: Gratton, Serge, et al.
Pubblicazione: (2026)

Fast Stochastic Second-Order Adagrad for Nonconvex Bound-Constrained Optimization
di: Bellavia, S., et al.
Pubblicazione: (2025)

Phase space integrity in neural network models of Hamiltonian dynamics: A Lagrangian descriptor approach
di: Hasmi, Abrari Noor, et al.
Pubblicazione: (2026)

Examples of slow convergence for adaptive regularization optimization methods are not isolated
di: Toint, Philippe L.
Pubblicazione: (2024)

Refining asymptotic complexity bounds for nonconvex optimization methods, including why steepest descent is $o(ε^{-2})$ rather than $\mathcal{O}(ε^{-2})$
di: Gratton, Serge, et al.
Pubblicazione: (2024)

Sum-of-Gaussians tensor neural networks for high-dimensional Schrödinger equation
di: Zhou, Qi, et al.
Pubblicazione: (2025)

A Speed Restart Scheme for a Dynamical System with Hessian-Driven Damping and Three Constant Coefficients
di: Guo, Huiyuan, et al.
Pubblicazione: (2024)

System stabilization with policy optimization on unstable latent manifolds
di: Werner, Steffen W. R., et al.
Pubblicazione: (2024)

Stochastic trace estimation for parameter-dependent matrices applied to spectral density approximation
di: Matti, Fabio, et al.
Pubblicazione: (2025)

Deep Learning without Global Optimization by Random Fourier Neural Networks
di: Davis, Owen, et al.
Pubblicazione: (2024)

Learning time-scales in two-layers neural networks
di: Berthier, Raphaël, et al.
Pubblicazione: (2023)

Learning to Integrate
di: Ernst, Oliver G., et al.
Pubblicazione: (2025)

An Analysis of Optimizer Choice on Energy Efficiency and Performance in Neural Network Training
di: Almog, Tom
Pubblicazione: (2025)

Convexity of Optimization Curves: Local Sharp Thresholds, Robustness Impossibility, and New Counterexamples
di: Hieu, Le Duc
Pubblicazione: (2025)

Fast operator learning for mapping correlations
di: Khoo, Yuehaw, et al.
Pubblicazione: (2025)

Convergence, design and training of continuous-time dropout as a random batch method
di: Álvarez-López, Antonio, et al.
Pubblicazione: (2025)

Fast Maxwell Solvers Based on Exact Discrete Eigen-Decompositions I. Two-Dimensional Case
di: Wang, Lixiu, et al.
Pubblicazione: (2025)

Distributed Computing for Huge-Scale Linear Programming
di: Tao, Luoyi
Pubblicazione: (2024)

Accelerated Natural Gradient Method for Parametric Manifold Optimization
di: Li, Chenyi, et al.
Pubblicazione: (2025)

A Heuristic Alternating Direction Method of Multipliers Framework for Distributed and Centralized Tree-Constrained Optimization: Applications to Hop-Constrained Spanning Tree Multicommodity Flow Design
di: Mokhtari, Yacine
Pubblicazione: (2025)

Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes
di: Müller, Johannes, et al.
Pubblicazione: (2024)

Distributed Gradient-Regularized Newton Method: Scheduled Consensus and O(epsilon^{-1}) Global Iteration Complexity
di: Hu, Wei, et al.
Pubblicazione: (2026)

Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime
di: Chizat, Lénaïc, et al.
Pubblicazione: (2025)