Cover Image

Can a Confident Prior Replace a Cold Posterior?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Marek, Martin, Paige, Brooks, Izmailov, Pavel
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
by: Marek, Martin, et al.
Published: (2026)

When Can LLMs Learn to Reason with Weak Supervision?
by: Rahman, Salman, et al.
Published: (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
by: Zhang, Yijie
Published: (2024)

Online Posterior Sampling with a Diffusion Prior
by: Kveton, Branislav, et al.
Published: (2024)

Prior Distribution and Model Confidence
by: Kazanskii, Maksim, et al.
Published: (2025)

SmilesT5: Domain-specific pretraining for molecular language models
by: Spence, Philip, et al.
Published: (2025)

Time-varying Factor Augmented Vector Autoregression with Grouped Sparse Autoencoder
by: Luo, Yiyong, et al.
Published: (2025)

AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
by: Liu, Chunan, et al.
Published: (2024)

Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
by: Janati, Yazid, et al.
Published: (2024)

On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
by: Kobialka, Julius, et al.
Published: (2026)

Effects of Dropout on Performance in Long-range Graph Learning Tasks
by: Singh, Jasraj, et al.
Published: (2025)

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
by: Mutti, Mirco, et al.
Published: (2023)

From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
by: Finzi, Marc, et al.
Published: (2026)

A study of EHVI vs fixed scalarization for molecule design
by: Yong, Anabel, et al.
Published: (2025)

Moment Matching Denoising Gibbs Sampling
by: Zhang, Mingtian, et al.
Published: (2023)

Gaussian Processes on Cellular Complexes
by: Alain, Mathieu, et al.
Published: (2023)

Deep Kernel Posterior Learning under Infinite Variance Prior Weights
by: Loría, Jorge, et al.
Published: (2024)

Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
by: Renaud, Marien, et al.
Published: (2023)

Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise
by: Meng, Li, et al.
Published: (2022)

Amortized Posterior Sampling with Diffusion Prior Distillation
by: Mammadov, Abbas, et al.
Published: (2024)

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
by: Choi, Jeongwhan, et al.
Published: (2026)

Reparameterization through Coverings and Topological Weight Priors
by: Beketov, Maxim, et al.
Published: (2026)

Lifting Embodied World Models for Planning and Control
by: Wang, Alex N., et al.
Published: (2026)

Closing the Train-Test Gap in World Models for Gradient-Based Planning
by: Parthasarathy, Arjun, et al.
Published: (2025)

Dynamic Prior Thompson Sampling for Cold-Start Exploration in Recommender Systems
by: Zhao, Zhenyu, et al.
Published: (2026)

With or Without Replacement? Improving Confidence in Fourier Imaging
by: Hoppe, Frederik, et al.
Published: (2024)

Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
by: Son, Seongho, et al.
Published: (2024)

Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
by: Mildner, Terje, et al.
Published: (2025)

Convolutional Signal Propagation: A Simple Scalable Algorithm for Hypergraphs
by: Procházka, Pavel, et al.
Published: (2024)

Latent Introspection: Models Can Detect Prior Concept Injections
by: Pearson-Vogel, Theia, et al.
Published: (2026)

Language-Model Prior Overcomes Cold-Start Items
by: Wang, Shiyu, et al.
Published: (2024)

Can Bayesian Neural Networks Make Confident Predictions?
by: Fisher, Katharine, et al.
Published: (2025)

DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking
by: Wiemann, Matt L., et al.
Published: (2026)

Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains
by: Shihab, Ibne Farabi, et al.
Published: (2025)

Towards Healing the Blindness of Score Matching
by: Zhang, Mingtian, et al.
Published: (2022)

Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
by: Xu, Jian, et al.
Published: (2024)

Combining Priors with Experience: Confidence Calibration Based on Binomial Process Modeling
by: Dong, Jinzong, et al.
Published: (2024)

Uncertainty Quantification for Prior-Data Fitted Networks using Martingale Posteriors
by: Nagler, Thomas, et al.
Published: (2025)

Diffusive Gibbs Sampling
by: Chen, Wenlin, et al.
Published: (2024)

Diffusion-Inspired Cold Start with Sufficient Prior in Computerized Adaptive Testing
by: Ma, Haiping, et al.
Published: (2024)