Image de couverture de livre

Soft-Label Training Preserves Epistemic Uncertainty

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Singh, Agamdeep, Tiwari, Ashish, Hasanbeig, Hosein, Gupta, Priyanshu
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications
par: Wang, Jun, et autres
Publié: (2023)

ConDABench: Interactive Evaluation of Language Models for Data Analysis
par: Dutta, Avik, et autres
Publié: (2025)

Quantifying Epistemic Uncertainty in Diffusion Models
par: Gupta, Aditi, et autres
Publié: (2026)

Epistemic Uncertainty for Test-Time Discovery
par: Riaz, Kainat, et autres
Publié: (2026)

Decomposing Epistemic Uncertainty for Causal Decision Making
par: Rahman, Md Musfiqur, et autres
Publié: (2026)

Ensured: Explanations for Decreasing the Epistemic Uncertainty in Predictions
par: Löfström, Helena, et autres
Publié: (2024)

On the Epistemic Uncertainty of Overparametrized Neural Networks
par: Rügamer, David
Publié: (2026)

On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation
par: Galozy, Alexander
Publié: (2026)

An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
par: Pavlovic, Maja, et autres
Publié: (2026)

UniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification
par: Kharbanda, Siddhant, et autres
Publié: (2024)

Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
par: Jürgens, Mira, et autres
Publié: (2024)

A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks
par: Mandal, Saptarshi, et autres
Publié: (2024)

From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence
par: Wang, Tianyang, et autres
Publié: (2025)

Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs
par: Eksen, Feyza, et autres
Publié: (2025)

Credal Concept Bottleneck Models: Structural Separation of Epistemic and Aleatoric Uncertainty
par: Mukherjee, Tanmoy, et autres
Publié: (2026)

Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
par: Song, Haoze, et autres
Publié: (2026)

Extending Epistemic Uncertainty Beyond Parameters Would Assist in Designing Reliable LLMs
par: Nguyen-Hien, T. Duy, et autres
Publié: (2025)

HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model
par: Van Katwyk, Peter, et autres
Publié: (2025)

Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation
par: Park, Seonghyeon, et autres
Publié: (2026)

Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspective
par: Jain, Anchit, et autres
Publié: (2025)

Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators
par: Berry, Lucas, et autres
Publié: (2023)

Consistently Informative Soft-Label Temperature for Knowledge Distillation
par: Luong, Hoang-Chau, et autres
Publié: (2026)

CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model
par: Xu, Xinran, et autres
Publié: (2026)

Disentangling Aleatoric and Epistemic Uncertainty in Physics-Informed Neural Networks. Application to Insulation Material Degradation Prognostics
par: Ramirez, Ibai, et autres
Publié: (2026)

Cardinality-Preserving Attention Channels for Graph Transformers in Molecular Property Prediction
par: Gupta, Abhijit
Publié: (2026)

Improving Label Error Detection and Elimination with Uncertainty Quantification
par: Jakubik, Johannes, et autres
Publié: (2024)

It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
par: Guo, Kevin H., et autres
Publié: (2026)

A Full DAG Score-Based Algorithm for Learning Causal Bayesian Networks with Latent Confounders
par: Gonzales, Christophe, et autres
Publié: (2024)

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention
par: Koebler, Alexander, et autres
Publié: (2025)

Epistemic Uncertainty-aware Recommendation Systems via Bayesian Deep Ensemble Learning
par: Cheraghi, Radin, et autres
Publié: (2025)

Soft-Label Integration for Robust Toxicity Classification
par: Cheng, Zelei, et autres
Publié: (2024)

Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order
par: Gupta, Prakhar, et autres
Publié: (2025)

ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models
par: Li, Mingda, et autres
Publié: (2025)

Perceptual Quality-based Model Training under Annotator Label Uncertainty
par: Zhou, Chen, et autres
Publié: (2024)

From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
par: Jenane, Azza, et autres
Publié: (2026)

Improving EEG Signal Classification Accuracy Using Wasserstein Generative Adversarial Networks
par: Park, Joshua, et autres
Publié: (2024)

Adversarial Training for Defense Against Label Poisoning Attacks
par: Bal, Melis Ilayda, et autres
Publié: (2025)

Epistemically-guided forward-backward exploration
par: Urpí, Núria Armengol, et autres
Publié: (2025)

Epistemic Monte Carlo Tree Search
par: Oren, Yaniv, et autres
Publié: (2022)

Geometric-Averaged Preference Optimization for Soft Preference Labels
par: Furuta, Hiroki, et autres
Publié: (2024)