Copertina

Sparse Training of Neural Networks based on Multilevel Mirror Descent

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lunk, Yannick, Scott, Sebastian J., Bungert, Leon
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Numerical Analysis Optimization and Control 65K10, 68T05, 90C26 I.2.6; F.2.1; G.1.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Escaping Saddle Points via Curvature-Calibrated Perturbations: A Complete Analysis with Explicit Constants and Empirical Validation
di: Alpay, Faruk, et al.
Pubblicazione: (2025)

prunAdag: an adaptive pruning-aware gradient method
di: Porcelli, Margherita, et al.
Pubblicazione: (2025)

CAO: Curvature-Adaptive Optimization via Periodic Low-Rank Hessian Sketching
di: Du, Wenzhang
Pubblicazione: (2025)

Refining Graphical Neural Network Predictions Using Flow Matching for Optimal Power Flow with Constraint-Satisfaction Guarantee
di: Khanal, Kshitiz
Pubblicazione: (2025)

Stochastic Estimation of the Layer-wise Hessian Trace for Monitoring Neural-network Training
di: Bolshim, Maxim, et al.
Pubblicazione: (2026)

On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime
di: Jiang, Shuai, et al.
Pubblicazione: (2026)

FlowAdam: Implicit Regularization via Geometry-Aware Soft Momentum Injection
di: Singh, Devender, et al.
Pubblicazione: (2026)

Enhancing Model Based Derivative Free Optimization using Direct Search
di: Li, Zijun, et al.
Pubblicazione: (2026)

Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures
di: Bolshim, Maxim, et al.
Pubblicazione: (2026)

Multi-Objective Optimization with Desirability and Morris-Mitchell Criterion
di: Bartz-Beielstein, Thomas, et al.
Pubblicazione: (2025)

Deep Legendre Transform
di: Minabutdinov, Aleksey, et al.
Pubblicazione: (2025)

TOPSIS-like metaheuristic for LABS problem
di: Urbańczyk, Aleksandra, et al.
Pubblicazione: (2025)

Pseudoconvex Problems in Operational Decision Systems: Algorithms for Joint Learning and Optimization
di: Li, Zijun, et al.
Pubblicazione: (2026)

Local properties of neural networks through the lens of layer-wise Hessians
di: Bolshim, Maxim, et al.
Pubblicazione: (2025)

Setwise Coordinate Descent for Dual Asynchronous Decentralized Optimization
di: Costantini, Marina, et al.
Pubblicazione: (2025)

i-DEQ: A stable inertial deep equilibrium model for image restoration
di: Clerc, Antonin, et al.
Pubblicazione: (2026)

NeurOptimisation: The Spiking Way to Evolve
di: Cruz-Duarte, Jorge Mario, et al.
Pubblicazione: (2025)

Decentralized Optimization with Topology-Independent Communication
di: Lin, Ying, et al.
Pubblicazione: (2025)

Interior-Point Vanishing Problem in Semidefinite Relaxations for Neural Network Verification
di: Ueda, Ryota, et al.
Pubblicazione: (2025)

GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
di: Salishev, Sergey, et al.
Pubblicazione: (2025)

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

Atom dimension adaptation for infinite set dictionary learning
di: Băltoiu, Andra, et al.
Pubblicazione: (2024)

Efficient Training of Physics-enhanced Neural ODEs via Direct Collocation and Nonlinear Programming
di: Langenkamp, Linus, et al.
Pubblicazione: (2025)

Stochastic convergence of parallel asynchronous adaptive first-order methods
di: Gratton, Serge, et al.
Pubblicazione: (2026)

Multi-Objective Optimization and Hyperparameter Tuning With Desirability Functions
di: Bartz-Beielstein, Thomas
Pubblicazione: (2025)

Sequential, Parallel and Consecutive Hybrid Evolutionary-Swarm Optimization Metaheuristics
di: Urbańczyk, Piotr, et al.
Pubblicazione: (2025)

Anarchy in the swarm: Testing informed and uninformed diversity-enhancing mechanisms within PSO framework
di: Urbańczyk, Piotr, et al.
Pubblicazione: (2026)

Kourkoutas-Beta: A Sunspike-Driven Adam Optimizer with Desert Flair
di: Kassinos, Stavros C.
Pubblicazione: (2025)

NOVAK: Unified adaptive optimizer for deep neural networks
di: Kavun, Sergii
Pubblicazione: (2026)

The Non-Linearity Perturbation Threshold: Width Scaling and Landscape Bifurcations in Deep Learning
di: Alexander, Michael
Pubblicazione: (2026)

Socio-cognitive agent-oriented evolutionary algorithm with trust-based optimization
di: Urbańczyk, Aleksandra, et al.
Pubblicazione: (2025)

Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization
di: Vary, Simon, et al.
Pubblicazione: (2024)

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)

The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm
di: Amsel, Noah, et al.
Pubblicazione: (2025)

Data-induced multiscale losses and efficient multirate gradient descent schemes
di: He, Juncai, et al.
Pubblicazione: (2024)

A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad, Shampoo and Muo
di: Gratton, S., et al.
Pubblicazione: (2026)

ZetA: A Riemann Zeta-Scaled Extension of Adam for Deep Learning
di: BC, Samiksha
Pubblicazione: (2025)

Benchmarking Generative AI Against Bayesian Optimization for Constrained Multi-Objective Inverse Design
di: Awan, Muhammad Bilal, et al.
Pubblicazione: (2025)

SCAFDS: Edge-Feature Graph Attention for Interbank Fraud Detection with Attribution-Grounded SAR Generation
di: Uddin, Mohammad Nasir
Pubblicazione: (2026)

Reinterpreting EMML as Mirror Descent for Constrained Maximum Likelihood Estimation
di: Clerc, Antonin, et al.
Pubblicazione: (2026)