Image de couverture de livre

Richer Bayesian Last Layers with Subsampled NTK Features

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Calvo-Ordoñez, Sergio, Plenk, Jonathan, Bergna, Richard, Cartea, Álvaro, Gal, Yarin, Hernández-Lobato, Jose Miguel, Ciosek, Kamil
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
par: Calvo-Ordoñez, Sergio, et autres
Publié: (2025)

The Neural Tangent Kernel for Classification
par: Plenk, Jonathan, et autres
Publié: (2026)

Activation-Space Uncertainty Quantification for Pretrained Networks
par: Bergna, Richard, et autres
Publié: (2026)

Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes
par: Bergna, Richard, et autres
Publié: (2025)

Weighted Conditional Flow Matching
par: Calvo-Ordonez, Sergio, et autres
Publié: (2025)

Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel
par: Calvo-Ordoñez, Sergio, et autres
Publié: (2024)

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations
par: Bergna, Richard, et autres
Publié: (2024)

Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors
par: Bergna, Richard, et autres
Publié: (2026)

A Bayesian Information-Theoretic Approach to Data Attribution
par: Tailor, Dharmesh, et autres
Publié: (2026)

Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy
par: Ciosek, Kamil, et autres
Publié: (2025)

Linear Gradient Prediction with Control Variates
par: Ciosek, Kamil, et autres
Publié: (2025)

The Minimax Rate of Second-Order Calibration
par: Ciosek, Kamil, et autres
Publié: (2026)

On the Importance of Uncertainty in Decision-Making with Large Language Models
par: Felicioni, Nicolò, et autres
Publié: (2024)

Feature Identification via the Empirical NTK
par: Lin, Jennifer
Publié: (2025)

Fast Adversarial Attacks with Gradient Prediction
par: Ciosek, Kamil, et autres
Publié: (2026)

Diagnosing and fixing common problems in Bayesian optimization for molecule design
par: Tripp, Austin, et autres
Publié: (2024)

Deep Bayesian Active Learning for Preference Modeling in Large Language Models
par: Melo, Luckeciano C., et autres
Publié: (2024)

Variational Bayesian Last Layers
par: Harrison, James, et autres
Publié: (2024)

How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features
par: Bombari, Simone, et autres
Publié: (2023)

Spectral Analysis of Molecular Kernels: When Richer Features Do Not Guarantee Better Generalization
par: Jamali, Asma, et autres
Publié: (2025)

Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL
par: Sergazinov, Renat, et autres
Publié: (2025)

Data Subsampling for Bayesian Neural Networks
par: Kawasaki, Eiji, et autres
Publié: (2022)

Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions
par: Kim, Hazel, et autres
Publié: (2024)

Simple Baselines are Competitive with Code Evolution
par: Gideoni, Yonatan, et autres
Publié: (2026)

The Benefits and Risks of Transductive Approaches for AI Fairness
par: Razzak, Muhammed, et autres
Publié: (2024)

Label-NTK Alignments and A Tighter Convergence Bound in the NTK Regime
par: Marreddy, Ruchirinkil, et autres
Publié: (2026)

When Embedding Models Meet: Procrustes Bounds and Applications
par: Maystre, Lucas, et autres
Publié: (2025)

Feature-Weighted Maximum Representative Subsampling
par: Hauptmann, Tony, et autres
Publié: (2026)

Do Multilingual LLMs Think In English?
par: Schut, Lisa, et autres
Publié: (2025)

In-Context Learning Learns Label Relationships but Is Not Conventional Learning
par: Kossen, Jannik, et autres
Publié: (2023)

Partially Stochastic Infinitely Deep Bayesian Neural Networks
par: Calvo-Ordonez, Sergio, et autres
Publié: (2024)

RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
par: He, Jiajun, et autres
Publié: (2023)

Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
par: Melo, Luckeciano C., et autres
Publié: (2025)

Temporal-Difference Variational Continual Learning
par: Melo, Luckeciano C., et autres
Publié: (2024)

On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective
par: Wenger, Jonathan, et autres
Publié: (2023)

Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
par: Hameed, Humza Wajid, et autres
Publié: (2024)

Training NTK to Generalize with KARE
par: Schwab, Johannes, et autres
Publié: (2025)

Multivariate Bayesian Last Layer for Regression with Uncertainty Quantification and Decomposition
par: Wang, Han, et autres
Publié: (2024)

Bayesian Optimization via Continual Variational Last Layer Training
par: Brunzema, Paul, et autres
Publié: (2024)

Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
par: Bhagat, Kirti, et autres
Publié: (2024)