Imagen de Portada

Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dhahri, Rayen, Immer, Alexander, Charpentier, Betrand, Günnemann, Stephan, Fortuin, Vincent
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improving Neural Additive Models with Bayesian Principles
por: Bouchiat, Kouroche, et al.
Publicado: (2023)

Quant-Trim in Practice: Improved Cross-Platform Low-Bit Deployment on Edge NPUs
por: Dhahri, Rayen, et al.
Publicado: (2025)

Occam's Razor is Only as Sharp as Your ELBO
por: Harvey, Ethan, et al.
Publicado: (2026)

A Geometric Modeling of Occam's Razor in Deep Learning
por: Sun, Ke, et al.
Publicado: (2019)

Joint Model and Data Sparsification via the Marginal Likelihood
por: Timans, Alexander, et al.
Publicado: (2026)

Amortising Inference and Meta-Learning Priors in Neural Networks
por: Rochussen, Tommy, et al.
Publicado: (2026)

Incorporating Unlabelled Data into Bayesian Neural Networks
por: Sharma, Mrinank, et al.
Publicado: (2023)

In-Context Occam's Razor: How Transformers Prefer Simpler Hypotheses on the Fly
por: Deora, Puneesh, et al.
Publicado: (2025)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
por: Ibrahim, Mark, et al.
Publicado: (2024)

Sparse Gaussian Neural Processes
por: Rochussen, Tommy, et al.
Publicado: (2025)

Stein Variational Newton Neural Network Ensembles
por: Flöge, Klemens, et al.
Publicado: (2024)

Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization
por: Riegler, Ben, et al.
Publicado: (2026)

Adversarial Attacks on Graph Neural Networks via Meta Learning
por: Zügner, Daniel, et al.
Publicado: (2019)

Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation
por: Paul, Richard D., et al.
Publicado: (2024)

Energy-based Epistemic Uncertainty for Graph Neural Networks
por: Fuchsgruber, Dominik, et al.
Publicado: (2024)

Generative Modeling with Bayesian Sample Inference
por: Lienen, Marten, et al.
Publicado: (2025)

On Representing Electronic Wave Functions with Sign Equivariant Neural Networks
por: Gao, Nicholas, et al.
Publicado: (2024)

Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance
por: Fuchsgruber, Dominik, et al.
Publicado: (2024)

Structurally Prune Anything: Any Architecture, Any Framework, Any Time
por: Wang, Xun, et al.
Publicado: (2024)

Uncertainty for Active Learning on Graphs
por: Fuchsgruber, Dominik, et al.
Publicado: (2024)

Spatio-Spectral Graph Neural Networks
por: Geisler, Simon, et al.
Publicado: (2024)

GemNet: Universal Directional Graph Neural Networks for Molecules
por: Gasteiger, Johannes, et al.
Publicado: (2021)

Can Transformers Learn Full Bayesian Inference in Context?
por: Reuter, Arik, et al.
Publicado: (2025)

On the Effect of Regularization on Nonparametric Mean-Variance Regression
por: Wong-Toi, Eliot, et al.
Publicado: (2025)

Understanding Pathologies of Deep Heteroskedastic Regression
por: Wong-Toi, Eliot, et al.
Publicado: (2023)

Discrete Bayesian Sample Inference for Graph Generation
por: Petersen, Ole, et al.
Publicado: (2025)

Exact Certification of (Graph) Neural Networks Against Label Poisoning
por: Sabanayagam, Mahalakshmi, et al.
Publicado: (2024)

Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation
por: Sommer, Johanna, et al.
Publicado: (2025)

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
por: Eschenhagen, Runa, et al.
Publicado: (2023)

Learning on a Razor's Edge: Identifiability and Singularity of Polynomial Neural Networks
por: Shahverdi, Vahid, et al.
Publicado: (2025)

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
por: Gosch, Lukas, et al.
Publicado: (2024)

Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations
por: Gao, Nicholas, et al.
Publicado: (2024)

ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
por: Kmicikiewicz, Michal, et al.
Publicado: (2025)

Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
por: Scholten, Yan, et al.
Publicado: (2023)

Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
por: Mohgaonkar, Ajinkya, et al.
Publicado: (2026)

Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
por: Regol, Florence, et al.
Publicado: (2024)

Marginal Pseudo-Likelihood Learning of Markov Network structures
por: Pensar, Johan, et al.
Publicado: (2014)

Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
por: Scholten, Yan, et al.
Publicado: (2024)

Occam Gradient Descent
por: Kausik, B. N.
Publicado: (2024)

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
por: Cinquin, Tristan, et al.
Publicado: (2024)