Imagen de Portada

Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAX

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	König, Lukas, Kuhn, Manuel, Kappel, David, Subramoney, Anand
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dynamic sparsity in tree-structured feed-forward layers at scale
por: Sedghi, Reza, et al.
Publicado: (2026)

State-space models can learn in-context by gradient descent
por: Sushma, Neeraj Mohan, et al.
Publicado: (2024)

Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models
por: Schöne, Mark, et al.
Publicado: (2024)

Asynchronous Stochastic Gradient Descent with Decoupled Backpropagation and Layer-Wise Updates
por: Fokam, Cabrel Teguemne, et al.
Publicado: (2024)

Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models
por: Mukherji, Rishav, et al.
Publicado: (2024)

Open source Differentiable ODE Solving Infrastructure
por: Singh, Rakshit Kr., et al.
Publicado: (2024)

Probing Length Generalization in Mamba via Image Reconstruction
por: Rathjens, Jan, et al.
Publicado: (2026)

Exploring the limits of Hierarchical World Models in Reinforcement Learning
por: Schiewer, Robin, et al.
Publicado: (2024)

Utilizing dynamic sparsity on pretrained DETR
por: Sedghi, Reza, et al.
Publicado: (2025)

Language Modeling on a SpiNNaker 2 Neuromorphic Chip
por: Nazeer, Khaleelulla Khan, et al.
Publicado: (2023)

STREAM: A Universal State-Space Model for Sparse Geometric Data
por: Schöne, Mark, et al.
Publicado: (2024)

Fully data-driven inverse hyperelasticity with hyper-network neural ODE fields
por: Taç, Vahidullah, et al.
Publicado: (2025)

DrJAX: Scalable and Differentiable MapReduce Primitives in JAX
por: Rush, Keith, et al.
Publicado: (2024)

MPX: Mixed Precision Training for JAX
por: Gräfe, Alexander, et al.
Publicado: (2025)

JaxSGMC: Modular stochastic gradient MCMC in JAX
por: Thaler, Stephan, et al.
Publicado: (2025)

Automatic Functional Differentiation in JAX
por: Lin, Min
Publicado: (2023)

Optimization of the quantization of dense neural networks from an exact QUBO formulation
por: Subiñas, Sergio Muñiz, et al.
Publicado: (2025)

Training morphological neural networks with gradient descent: some theoretical insights
por: Blusseau, Samy
Publicado: (2024)

Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference
por: Mukherji, Rishav, et al.
Publicado: (2023)

Input-gradient space particle inference for neural network ensembles
por: Trinh, Trung, et al.
Publicado: (2023)

JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework
por: Toshev, Artur P., et al.
Publicado: (2024)

SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
por: Paulus, Anselm, et al.
Publicado: (2026)

Training toward significance with the decorrelated event classifier transformer neural network
por: Kim, Jaebak
Publicado: (2023)

Convergence of gradient flow for learning convolutional neural networks
por: Diederen, Jona-Maria, et al.
Publicado: (2026)

Energy stable neural network for gradient flow equations
por: Wu, Yue, et al.
Publicado: (2023)

A foundation for exact binarized morphological neural networks
por: Aouad, Theodore, et al.
Publicado: (2024)

BlackJAX: Composable Bayesian inference in JAX
por: Cabezas, Alberto, et al.
Publicado: (2024)

Correcting Auto-Differentiation in Neural-ODE Training
por: Xu, Yewei, et al.
Publicado: (2023)

Loss shaping enhances exact gradient learning with Eventprop in spiking neural networks
por: Nowotny, Thomas, et al.
Publicado: (2022)

Deep neural networks for choice analysis: Enhancing behavioral regularity with gradient regularization
por: Feng, Siqi, et al.
Publicado: (2024)

Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
por: Chen, Chuqi, et al.
Publicado: (2024)

Stable Attractors for Neural networks classification via Ordinary Differential Equations (SA-nODE)
por: Marino, Raffaele, et al.
Publicado: (2023)

A novel auxiliary equation neural networks method for exactly explicit solutions of nonlinear partial differential equations
por: Yuan, Shanhao, et al.
Publicado: (2025)

The duality structure gradient descent algorithm: analysis and applications to neural networks
por: Flynn, Thomas
Publicado: (2017)

Tracking large chemical reaction networks and rare events by neural networks
por: Weng, Jiayu, et al.
Publicado: (2025)

Solving engineering eigenvalue problems with neural networks using the Rayleigh quotient
por: Rowan, Conor, et al.
Publicado: (2025)

Training Hamiltonian neural networks without backpropagation
por: Rahma, Atamert, et al.
Publicado: (2024)

Recurrent neural networks: vanishing and exploding gradients are not the end of the story
por: Zucchet, Nicolas, et al.
Publicado: (2024)

New tools for comparing classical and neural ODE models for tumor growth
por: Blaom, Anthony D., et al.
Publicado: (2025)

Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
por: Vouitsis, Noël, et al.
Publicado: (2024)