Copertina

A new initialisation to Control Gradients in Sinusoidal Neural network

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Combette, Andrea, Venaille, Antoine, Pustelnik, Nelly
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Deep learning in the abyss: a stratified Physics Informed Neural Network for data assimilation
di: Limousin, Vadim, et al.
Pubblicazione: (2025)

Data driven weather forecasts trained and initialised directly from observations
di: McNally, Anthony, et al.
Pubblicazione: (2024)

Fast Training of Sinusoidal Neural Fields via Scaling Initialization
di: Yeom, Taesun, et al.
Pubblicazione: (2024)

Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks
di: Novello, Tiago, et al.
Pubblicazione: (2024)

Provable Benefits of Sinusoidal Activation for Modular Addition
di: Huang, Tianlong, et al.
Pubblicazione: (2025)

Restarted contractive operators to learn at equilibrium
di: Davy, Leo, et al.
Pubblicazione: (2025)

Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks
di: Gleyzer, Sergei, et al.
Pubblicazione: (2025)

Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
di: Wójcik, Bartosz, et al.
Pubblicazione: (2023)

GraphDOP: Towards skilful data-driven medium-range weather forecasts learnt and initialised directly from observations
di: Alexe, Mihai, et al.
Pubblicazione: (2024)

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding
di: Sun, Chuanhao, et al.
Pubblicazione: (2024)

Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks
di: Rußwurm, Marc, et al.
Pubblicazione: (2023)

Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
di: Giorlandino, Alessio, et al.
Pubblicazione: (2025)

Beyond Sinusoids: A Morlet Wavelet Framework for Transformer Positional Encoding
di: Zeris, Athanasios
Pubblicazione: (2026)

GradINN: Gradient Informed Neural Network
di: Aglietti, Filippo, et al.
Pubblicazione: (2024)

Autoencoder-Based Parameter Estimation for Superposed Multi-Component Damped Sinusoidal Signals
di: Iida, Momoka, et al.
Pubblicazione: (2026)

Disentangling discrete and continuous spectra of tidally forced internal waves in shear flow
di: Onuki, Yohei, et al.
Pubblicazione: (2025)

Explainable Neural Networks with Guarantees: A Sparse Estimation Approach
di: Ledent, Antoine, et al.
Pubblicazione: (2025)

Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning
di: Chung, Hsing-Huan, et al.
Pubblicazione: (2025)

On the Existence of Optimal Transport Gradient for Learning Generative Models
di: Houdard, Antoine, et al.
Pubblicazione: (2021)

Neural Sinkhorn Gradient Flow
di: Zhu, Huminhao, et al.
Pubblicazione: (2024)

A Lightweight and Gradient-Stable Neural Layer
di: Yu, Yueyao, et al.
Pubblicazione: (2021)

SineKAN: Kolmogorov-Arnold Networks Using Sinusoidal Activation Functions
di: Reinhardt, Eric A. F., et al.
Pubblicazione: (2024)

Sinusoidal Initialization, Time for a New Start
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2025)

Optimisation of Structured Neural Controller Based on Continuous-Time Policy Gradient
di: Cho, Namhoon, et al.
Pubblicazione: (2022)

Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport
di: Genans, Ferdinand, et al.
Pubblicazione: (2025)

Robust Neural Pruning with Gradient Sampling Optimization for Residual Neural Networks
di: Yun, Juyoung
Pubblicazione: (2023)

Efficient, Accurate and Stable Gradients for Neural ODEs
di: McCallum, Sam, et al.
Pubblicazione: (2024)

Adaptive Feedforward Gradient Estimation in Neural ODEs
di: Dabounou, Jaouad
Pubblicazione: (2024)

Lai Loss: A Novel Loss for Gradient Control
di: Lai, YuFei
Pubblicazione: (2024)

Linear Gradient Prediction with Control Variates
di: Ciosek, Kamil, et al.
Pubblicazione: (2025)

A Comparative Study of Machine Learning Algorithms for Stock Price Prediction Using Insider Trading Data
di: Chakravorty, Amitabh, et al.
Pubblicazione: (2025)

Generalization Bounds for Rank-sparse Neural Networks
di: Ledent, Antoine, et al.
Pubblicazione: (2025)

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
di: Cloud, Alex, et al.
Pubblicazione: (2024)

Explaining deep neural network models for electricity price forecasting with XAI
di: Pesenti, Antoine, et al.
Pubblicazione: (2025)

An Application of the Holonomic Gradient Method to the Neural Tangent Kernel
di: Sakoda, Akihiro, et al.
Pubblicazione: (2024)

Taming Gradient Oversmoothing and Expansion in Graph Neural Networks
di: Park, MoonJeong, et al.
Pubblicazione: (2024)

Functional Stochastic Gradient MCMC for Bayesian Neural Networks
di: Wu, Mengjing, et al.
Pubblicazione: (2024)

Stochastic Gradient Descent for Two-layer Neural Networks
di: Cao, Dinghao, et al.
Pubblicazione: (2024)

Variational Stochastic Gradient Descent for Deep Neural Networks
di: Chen, Haotian, et al.
Pubblicazione: (2024)

Gradient Rewiring for Editable Graph Neural Network Training
di: Jiang, Zhimeng, et al.
Pubblicazione: (2024)