Image de couverture de livre

Can a Confident Prior Replace a Cold Posterior?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Marek, Martin, Paige, Brooks, Izmailov, Pavel
Format:	Preprint
Publié:	2024
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

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
par: Marek, Martin, et autres
Publié: (2026)

When Can LLMs Learn to Reason with Weak Supervision?
par: Rahman, Salman, et autres
Publié: (2026)

On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees
par: Zhang, Yijie
Publié: (2024)

Online Posterior Sampling with a Diffusion Prior
par: Kveton, Branislav, et autres
Publié: (2024)

Prior Distribution and Model Confidence
par: Kazanskii, Maksim, et autres
Publié: (2025)

SmilesT5: Domain-specific pretraining for molecular language models
par: Spence, Philip, et autres
Publié: (2025)

Time-varying Factor Augmented Vector Autoregression with Grouped Sparse Autoencoder
par: Luo, Yiyong, et autres
Publié: (2025)

AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
par: Liu, Chunan, et autres
Publié: (2024)

Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
par: Janati, Yazid, et autres
Publié: (2024)

On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
par: Kobialka, Julius, et autres
Publié: (2026)

Effects of Dropout on Performance in Long-range Graph Learning Tasks
par: Singh, Jasraj, et autres
Publié: (2025)

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
par: Mutti, Mirco, et autres
Publié: (2023)

From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
par: Finzi, Marc, et autres
Publié: (2026)

A study of EHVI vs fixed scalarization for molecule design
par: Yong, Anabel, et autres
Publié: (2025)

Moment Matching Denoising Gibbs Sampling
par: Zhang, Mingtian, et autres
Publié: (2023)

Gaussian Processes on Cellular Complexes
par: Alain, Mathieu, et autres
Publié: (2023)

Deep Kernel Posterior Learning under Infinite Variance Prior Weights
par: Loría, Jorge, et autres
Publié: (2024)

Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
par: Renaud, Marien, et autres
Publié: (2023)

Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise
par: Meng, Li, et autres
Publié: (2022)

Amortized Posterior Sampling with Diffusion Prior Distillation
par: Mammadov, Abbas, et autres
Publié: (2024)

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
par: Choi, Jeongwhan, et autres
Publié: (2026)

Reparameterization through Coverings and Topological Weight Priors
par: Beketov, Maxim, et autres
Publié: (2026)

Lifting Embodied World Models for Planning and Control
par: Wang, Alex N., et autres
Publié: (2026)

Closing the Train-Test Gap in World Models for Gradient-Based Planning
par: Parthasarathy, Arjun, et autres
Publié: (2025)

Dynamic Prior Thompson Sampling for Cold-Start Exploration in Recommender Systems
par: Zhao, Zhenyu, et autres
Publié: (2026)

With or Without Replacement? Improving Confidence in Fourier Imaging
par: Hoppe, Frederik, et autres
Publié: (2024)

Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
par: Son, Seongho, et autres
Publié: (2024)

Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
par: Mildner, Terje, et autres
Publié: (2025)

Convolutional Signal Propagation: A Simple Scalable Algorithm for Hypergraphs
par: Procházka, Pavel, et autres
Publié: (2024)

Latent Introspection: Models Can Detect Prior Concept Injections
par: Pearson-Vogel, Theia, et autres
Publié: (2026)

Language-Model Prior Overcomes Cold-Start Items
par: Wang, Shiyu, et autres
Publié: (2024)

Can Bayesian Neural Networks Make Confident Predictions?
par: Fisher, Katharine, et autres
Publié: (2025)

DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking
par: Wiemann, Matt L., et autres
Publié: (2026)

Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains
par: Shihab, Ibne Farabi, et autres
Publié: (2025)

Towards Healing the Blindness of Score Matching
par: Zhang, Mingtian, et autres
Publié: (2022)

Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
par: Xu, Jian, et autres
Publié: (2024)

Combining Priors with Experience: Confidence Calibration Based on Binomial Process Modeling
par: Dong, Jinzong, et autres
Publié: (2024)

Uncertainty Quantification for Prior-Data Fitted Networks using Martingale Posteriors
par: Nagler, Thomas, et autres
Publié: (2025)

Diffusive Gibbs Sampling
par: Chen, Wenlin, et autres
Publié: (2024)

Diffusion-Inspired Cold Start with Sufficient Prior in Computerized Adaptive Testing
par: Ma, Haiping, et autres
Publié: (2024)