Imagen de Portada

Bayesian Double Descent

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Polson, Nick, Sokolov, Vadim
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computation
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generative Bayesian Computation as a Scalable Alternative to Gaussian Process Surrogates
por: Polson, Nick, et al.
Publicado: (2026)

Generative Bayesian Hyperparameter Tuning
por: Lopes, Hedibert, et al.
Publicado: (2025)

Generative Bayesian Computation for Maximum Expected Utility
por: Polson, Nick, et al.
Publicado: (2024)

Fast Compute for ML Optimization
por: Polson, Nick, et al.
Publicado: (2026)

Generative Modeling: A Review
por: Nareklishvili, Maria, et al.
Publicado: (2024)

Horseshoe Mixtures-of-Experts (HS-MoE)
por: Polson, Nick, et al.
Publicado: (2026)

Kolmogorov GAM Networks are all you need!
por: Polson, Sarah, et al.
Publicado: (2025)

Generative Quantile Bayesian Prediction
por: Nareklishvili, Maria, et al.
Publicado: (2025)

$MC^2$ Mixed Integer and Linear Programming
por: Polson, Nick, et al.
Publicado: (2025)

Counting $N$ Queens
por: Polson, Nick, et al.
Publicado: (2024)

Bell's Inequality, Causal Bounds, and Quantum Bayesian Computation: A Unified Framework
por: Polson, Nick, et al.
Publicado: (2026)

Bayesian Methods for the Navier-Stokes Equations
por: Polson, Nicholas, et al.
Publicado: (2026)

Generative AI for Bayesian Computation
por: Polson, Nicholas G., et al.
Publicado: (2023)

Bayesian Global-Local Regularization
por: Datta, Jyotishka, et al.
Publicado: (2025)

Horseshoe Priors and MDP
por: Polson, Nick, et al.
Publicado: (2026)

Some Bayesian Perspectives on Clinical Trials
por: Sokolova, Alexandra, et al.
Publicado: (2026)

Negative Probability
por: Polson, Nick, et al.
Publicado: (2024)

Synthetic Priors
por: Polson, Nick, et al.
Publicado: (2026)

Fast Compute via MC Boosting
por: Polson, Sarah, et al.
Publicado: (2026)

Photons = Tokens: The Physics of AI and the Economics of Knowledge
por: Litowitz, Alec, et al.
Publicado: (2026)

Kramnik vs Nakamura: A Chess Scandal
por: Maharaj, Shiva, et al.
Publicado: (2024)

Understanding the Double Descent Phenomenon in Deep Learning
por: Lafon, Marc, et al.
Publicado: (2024)

Double-Bayesian Learning
por: Jaeger, Stefan
Publicado: (2024)

Manipulating Sparse Double Descent
por: Zhang, Ya Shi
Publicado: (2024)

Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features
por: Caprio, Michele, et al.
Publicado: (2026)

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
por: Iwase, Shun, et al.
Publicado: (2025)

Dropout Drops Double Descent
por: Yang, Tian-Le, et al.
Publicado: (2023)

Double Descent and Other Interpolation Phenomena in GANs
por: Luzi, Lorenzo, et al.
Publicado: (2021)

On the Lipschitz Constant of Deep Networks and Double Descent
por: Gamba, Matteo, et al.
Publicado: (2023)

A New Look at Bayesian Testing
por: Datta, Jyotishka, et al.
Publicado: (2026)

Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting
por: Kubo, Tomoki, et al.
Publicado: (2026)

On Uniform, Bayesian, and PAC-Bayesian Deep Ensembles
por: Hauptvogel, Nick, et al.
Publicado: (2024)

On The Presence of Double-Descent in Deep Reinforcement Learning
por: Veselý, Viktor, et al.
Publicado: (2025)

Class-wise Activation Unravelling the Engima of Deep Double Descent
por: Gu, Yufei
Publicado: (2024)

Generative AI for Validating Physics Laws
por: Nareklishvili, Maria, et al.
Publicado: (2025)

Generative Causal Inference
por: Nareklishvili, Maria, et al.
Publicado: (2023)

Training Neural Networks with Optimal Double-Bayesian Learning
por: Bui, Vy, et al.
Publicado: (2026)

Can Gradient Descent Simulate Prompting?
por: Zhang, Eric, et al.
Publicado: (2025)

In-context Learning and Gradient Descent Revisited
por: Deutch, Gilad, et al.
Publicado: (2023)

Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression
por: Trukhina, Natalia, et al.
Publicado: (2026)