Cover Image

Gaussian Pre-Activations in Neural Networks: Myth or Reality?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wolinski, Pierre, Arbel, Julyan
Format:	Preprint
Published:	2022
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Gathering and Exploiting Higher-Order Information when Training Large Structured Models
by: Wolinski, Pierre
Published: (2023)

Logarithmic Regret for Unconstrained Submodular Maximization Stochastic Bandit
by: Zhou, Julien, et al.
Published: (2024)

Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits
by: Zhou, Julien, et al.
Published: (2024)

Simulation-based inference of yeast centromeres
by: Touron, Eloïse, et al.
Published: (2025)

$\textit{BlockFormer}$ : Transformer-based inference from interaction maps
by: Touron, Eloïse, et al.
Published: (2026)

Error analysis of a compositional score-based algorithm for simulation-based inference
by: Touron, Camille, et al.
Published: (2025)

Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference
by: Touron, Camille, et al.
Published: (2026)

Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection
by: Yahiaoui, Mohamed Bahi, et al.
Published: (2026)

An Equivalence between Bayesian Priors and Penalties in Variational Inference
by: Wolinski, Pierre, et al.
Published: (2020)

Natural Variational Annealing for Multimodal Optimization
by: LeMinh, Tâm, et al.
Published: (2025)

Bayesian inference with sources of uncertainty: from confidence modelling to sparse estimation
by: Rosa, Rafael Mouallem, et al.
Published: (2026)

Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization
by: Refael, Yehonathan, et al.
Published: (2022)

Causal Discovery from Time Series with Hybrids of Constraint-Based and Noise-Based Algorithms
by: Bystrova, Daria, et al.
Published: (2023)

Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes
by: Bergna, Richard, et al.
Published: (2025)

Optimal sub-Gaussian variance proxy for truncated Gaussian and exponential random variables
by: Barreto, Mathias, et al.
Published: (2024)

Revisiting the Equivalence of Bayesian Neural Networks and Gaussian Processes: On the Importance of Learning Activations
by: Sendera, Marcin, et al.
Published: (2024)

Optimal sub-Gaussian variance proxy for 3-mass distributions
by: Atouani, Soufiane, et al.
Published: (2025)

Region Seeding via Pre-Activation Regularization: A Geometric View of Piecewise Affine Neural Networks
by: Wei, Yi, et al.
Published: (2026)

Just rotate it! Uncertainty estimation in closed-source models via multiple queries
by: Pitas, Konstantinos, et al.
Published: (2024)

Semiring Activation in Neural Networks
by: Smets, Bart M. N., et al.
Published: (2024)

Deep Reinforcement Learning for System-on-Chip: Myths and Realities
by: Sung, Tegg Taekyong, et al.
Published: (2022)

EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Networks
by: Arbel, Michael, et al.
Published: (2025)

Learning Neural Networks with Sparse Activations
by: Awasthi, Pranjal, et al.
Published: (2024)

MLXP: A Framework for Conducting Replicable Experiments in Python
by: Arbel, Michael, et al.
Published: (2024)

Flow Matching for Robust Simulation-Based Inference under Model Misspecification
by: Ruhlmann, Pierre-Louis, et al.
Published: (2025)

Functional Bilevel Optimization for Machine Learning
by: Petrulionyte, Ieva, et al.
Published: (2024)

Contextual Bandit Optimization with Pre-Trained Neural Networks
by: Terekhov, Mikhail
Published: (2025)

Pre-Defined Sparse Neural Networks with Hardware Acceleration
by: Dey, Sourya, et al.
Published: (2018)

Seeking Interpretability and Explainability in Binary Activated Neural Networks
by: Leblanc, Benjamin, et al.
Published: (2022)

Deep Neural Network Initialization with Sparsity Inducing Activations
by: Price, Ilan, et al.
Published: (2024)

Approximation Capabilities of Feedforward Neural Networks with GELU Activations
by: Yakovlev, Konstantin, et al.
Published: (2025)

1-Lipschitz Neural Networks are more expressive with N-Activations
by: Prach, Bernd, et al.
Published: (2023)

Inverted Activations: Reducing Memory Footprint in Neural Network Training
by: Novikov, Georgii, et al.
Published: (2024)

Analyzing the Neural Tangent Kernel of Periodically Activated Coordinate Networks
by: Saratchandran, Hemanth, et al.
Published: (2024)

Ray-Tracing for Conditionally Activated Neural Networks
by: Gallicchio, Claudio, et al.
Published: (2025)

PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks
by: Ge, Qingqing, et al.
Published: (2023)

Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations
by: Dashtbayaz, Nima Hosseini, et al.
Published: (2024)

Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns
by: Peng, Yameng, et al.
Published: (2026)

Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
by: Chen, Wenlin, et al.
Published: (2023)

Extension of Symmetrized Neural Network Operators with Fractional and Mixed Activation Functions
by: Santos, Rômulo Damasclin Chaves dos, et al.
Published: (2025)