Imagen de Portada

Soft-Label Training Preserves Epistemic Uncertainty

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Singh, Agamdeep, Tiwari, Ashish, Hasanbeig, Hosein, Gupta, Priyanshu
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications
por: Wang, Jun, et al.
Publicado: (2023)

ConDABench: Interactive Evaluation of Language Models for Data Analysis
por: Dutta, Avik, et al.
Publicado: (2025)

Quantifying Epistemic Uncertainty in Diffusion Models
por: Gupta, Aditi, et al.
Publicado: (2026)

Epistemic Uncertainty for Test-Time Discovery
por: Riaz, Kainat, et al.
Publicado: (2026)

Decomposing Epistemic Uncertainty for Causal Decision Making
por: Rahman, Md Musfiqur, et al.
Publicado: (2026)

Ensured: Explanations for Decreasing the Epistemic Uncertainty in Predictions
por: Löfström, Helena, et al.
Publicado: (2024)

On the Epistemic Uncertainty of Overparametrized Neural Networks
por: Rügamer, David
Publicado: (2026)

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

An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
por: Pavlovic, Maja, et al.
Publicado: (2026)

UniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification
por: Kharbanda, Siddhant, et al.
Publicado: (2024)

Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
por: Jürgens, Mira, et al.
Publicado: (2024)

A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks
por: Mandal, Saptarshi, et al.
Publicado: (2024)

From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence
por: Wang, Tianyang, et al.
Publicado: (2025)

Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs
por: Eksen, Feyza, et al.
Publicado: (2025)

Credal Concept Bottleneck Models: Structural Separation of Epistemic and Aleatoric Uncertainty
por: Mukherjee, Tanmoy, et al.
Publicado: (2026)

Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
por: Song, Haoze, et al.
Publicado: (2026)

Extending Epistemic Uncertainty Beyond Parameters Would Assist in Designing Reliable LLMs
por: Nguyen-Hien, T. Duy, et al.
Publicado: (2025)

HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model
por: Van Katwyk, Peter, et al.
Publicado: (2025)

Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation
por: Park, Seonghyeon, et al.
Publicado: (2026)

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

Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators
por: Berry, Lucas, et al.
Publicado: (2023)

Consistently Informative Soft-Label Temperature for Knowledge Distillation
por: Luong, Hoang-Chau, et al.
Publicado: (2026)

CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model
por: Xu, Xinran, et al.
Publicado: (2026)

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

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

Improving Label Error Detection and Elimination with Uncertainty Quantification
por: Jakubik, Johannes, et al.
Publicado: (2024)

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

A Full DAG Score-Based Algorithm for Learning Causal Bayesian Networks with Latent Confounders
por: Gonzales, Christophe, et al.
Publicado: (2024)

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention
por: Koebler, Alexander, et al.
Publicado: (2025)

Epistemic Uncertainty-aware Recommendation Systems via Bayesian Deep Ensemble Learning
por: Cheraghi, Radin, et al.
Publicado: (2025)

Soft-Label Integration for Robust Toxicity Classification
por: Cheng, Zelei, et al.
Publicado: (2024)

Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order
por: Gupta, Prakhar, et al.
Publicado: (2025)

ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models
por: Li, Mingda, et al.
Publicado: (2025)

Perceptual Quality-based Model Training under Annotator Label Uncertainty
por: Zhou, Chen, et al.
Publicado: (2024)

From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
por: Jenane, Azza, et al.
Publicado: (2026)

Improving EEG Signal Classification Accuracy Using Wasserstein Generative Adversarial Networks
por: Park, Joshua, et al.
Publicado: (2024)

Adversarial Training for Defense Against Label Poisoning Attacks
por: Bal, Melis Ilayda, et al.
Publicado: (2025)

Epistemically-guided forward-backward exploration
por: Urpí, Núria Armengol, et al.
Publicado: (2025)

Epistemic Monte Carlo Tree Search
por: Oren, Yaniv, et al.
Publicado: (2022)

Geometric-Averaged Preference Optimization for Soft Preference Labels
por: Furuta, Hiroki, et al.
Publicado: (2024)