Cover Image

Deep Ensembles Secretly Perform Empirical Bayes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Loaiza-Ganem, Gabriel, Villecroze, Valentin, Wang, Yixin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Last Layer Empirical Bayes
by: Villecroze, Valentin, et al.
Published: (2025)

Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
by: Vouitsis, Noël, et al.
Published: (2024)

Data-Efficient Multimodal Fusion on a Single GPU
by: Vouitsis, Noël, et al.
Published: (2023)

On Convolutions, Intrinsic Dimension, and Diffusion Models
by: Leung, Kin Kwan, et al.
Published: (2025)

Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections
by: Loaiza-Ganem, Gabriel, et al.
Published: (2024)

Conf-Gen: Conformal Uncertainty Quantification for Generative Models
by: Loaiza-Ganem, Gabriel, et al.
Published: (2026)

The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE
by: Chernov, Andrei, et al.
Published: (2025)

A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
by: Kamkari, Hamidreza, et al.
Published: (2024)

Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems
by: Ross, Brendan Leigh, et al.
Published: (2025)

The Disparate Benefits of Deep Ensembles
by: Schweighofer, Kajetan, et al.
Published: (2024)

A Geometric Explanation of the Likelihood OOD Detection Paradox
by: Kamkari, Hamidreza, et al.
Published: (2024)

Generalization Performance of Ensemble Clustering: From Theory to Algorithm
by: Zhang, Xu, et al.
Published: (2025)

Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
by: Mohan, Adithya, et al.
Published: (2025)

Best-of-$\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling
by: Komiyama, Junpei, et al.
Published: (2025)

Deep MMD Gradient Flow without adversarial training
by: Galashov, Alexandre, et al.
Published: (2024)

Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts
by: Xiong, Xinlei, et al.
Published: (2025)

LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning
by: Choi, Changryeol, et al.
Published: (2026)

Decision Predicate Graphs: Enhancing Interpretability in Tree Ensembles
by: Arrighi, Leonardo, et al.
Published: (2024)

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
by: Luo, Beier, et al.
Published: (2025)

Modeling and Performance Analysis for Semantic Communications Based on Empirical Results
by: Ma, Shuai, et al.
Published: (2025)

Performance of Small Language Model Pretraining on FABRIC: An Empirical Study
by: Rao, Praveen
Published: (2026)

Kron-LoRA: Hybrid Kronecker-LoRA Adapters for Scalable, Sustainable Fine-tuning
by: Shen, Yixin
Published: (2025)

Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework
by: He, Shuangshuang, et al.
Published: (2025)

Representation Convergence: Mutual Distillation is Secretly a Form of Regularization
by: Xie, Zhengpeng, et al.
Published: (2025)

Secret mixtures of experts inside your LLM
by: Boix-Adsera, Enric
Published: (2025)

GRPO is Secretly a Process Reward Model
by: Sullivan, Michael, et al.
Published: (2025)

Year-over-Year Developments in Financial Fraud Detection via Deep Learning: A Systematic Literature Review
by: Chen, Yisong, et al.
Published: (2025)

An Explainable Ensemble Learning Framework for Crop Classification with Optimized Feature Pyramids and Deep Networks
by: Masud, Syed Rayhan, et al.
Published: (2026)

On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference
by: Zanger, Moritz A., et al.
Published: (2026)

Online Training and Pruning of Deep Reinforcement Learning Networks
by: Guenter, Valentin Frank Ingmar, et al.
Published: (2025)

EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization
by: Han, Kevin, et al.
Published: (2026)

Flora: Low-Rank Adapters Are Secretly Gradient Compressors
by: Hao, Yongchang, et al.
Published: (2024)

On the Practice of Deep Hierarchical Ensemble Network for Ad Conversion Rate Prediction
by: Zhuang, Jinfeng, et al.
Published: (2025)

Synthetic Data in Education: Empirical Insights from Traditional Resampling and Deep Generative Models
by: Chinodakufa, Tapiwa Amion, et al.
Published: (2026)

Credal Ensemble Distillation for Uncertainty Quantification
by: Wang, Kaizheng, et al.
Published: (2025)

GreenFactory: Ensembling Zero-Cost Proxies to Estimate Performance of Neural Networks
by: Cortês, Gabriel, et al.
Published: (2025)

Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Autospeculation
by: Hu, Hengyuan, et al.
Published: (2025)

Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspective
by: Jain, Anchit, et al.
Published: (2025)

Quantitative Analysis of Performance Drop in DeepSeek Model Quantization
by: Zhao, Enbo, et al.
Published: (2025)

Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters
by: Cazaux, Hugo, et al.
Published: (2026)