Cover Image

How Does Unlabeled Data Provably Help Out-of-Distribution Detection?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Xuefeng, Fang, Zhen, Diakonikolas, Ilias, Li, Yixuan
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

When and How Does In-Distribution Label Help Out-of-Distribution Detection?
by: Du, Xuefeng, et al.
Published: (2024)

Distributionally Robust Optimization with Adversarial Data Contamination
by: Li, Shuyao, et al.
Published: (2025)

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
by: Du, Xuefeng, et al.
Published: (2024)

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
by: Bai, Haoyue, et al.
Published: (2023)

Out-of-Distribution Learning with Human Feedback
by: Bai, Haoyue, et al.
Published: (2024)

How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?
by: Ming, Yifei, et al.
Published: (2023)

Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
by: Li, Shuyao, et al.
Published: (2024)

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
by: Peng, Bo, et al.
Published: (2024)

Robustly Learning Monotone Generalized Linear Models via Data Augmentation
by: Zarifis, Nikos, et al.
Published: (2025)

A Median Perspective on Unlabeled Data for Out-of-Distribution Detection
by: Abbas, Momin, et al.
Published: (2025)

Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
by: Wang, Puqian, et al.
Published: (2024)

When and How Unlabeled Data Provably Improve In-Context Learning
by: Li, Yingcong, et al.
Published: (2025)

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
by: Oh, Changdae, et al.
Published: (2025)

VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
by: Du, Xuefeng, et al.
Published: (2024)

Robustly Learning Monotone Single-Index Models
by: Wang, Puqian, et al.
Published: (2025)

Out-Of-Distribution Detection with Diversification (Provably)
by: Yao, Haiyun, et al.
Published: (2024)

A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
by: Diakonikolas, Ilias, et al.
Published: (2025)

On the Learnability of Out-of-distribution Detection
by: Fang, Zhen, et al.
Published: (2024)

Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
by: Liu, Renpu, et al.
Published: (2026)

Statistical Query Lower Bounds for Smoothed Agnostic Learning
by: Diakonikolas, Ilias, et al.
Published: (2026)

Learning Intersections of Two Margin Halfspaces under Factorizable Distributions
by: Diakonikolas, Ilias, et al.
Published: (2025)

Out-Of-Domain Unlabeled Data Improves Generalization
by: Saberi, Amir Hossein, et al.
Published: (2023)

How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?
by: Sun, Ke, et al.
Published: (2022)

Replicable Distribution Testing
by: Diakonikolas, Ilias, et al.
Published: (2025)

Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
by: Azar, Eyar, et al.
Published: (2024)

Active Learning of General Halfspaces: Label Queries vs Membership Queries
by: Diakonikolas, Ilias, et al.
Published: (2024)

Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models
by: Diakonikolas, Ilias, et al.
Published: (2024)

Robustly Learning Single-Index Models via Alignment Sharpness
by: Zarifis, Nikos, et al.
Published: (2024)

How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysis
by: Dong, Yuxin, et al.
Published: (2024)

Reliable Learning of Halfspaces under Gaussian Marginals
by: Diakonikolas, Ilias, et al.
Published: (2024)

SoS Certifiability of Subgaussian Distributions and its Algorithmic Applications
by: Diakonikolas, Ilias, et al.
Published: (2024)

OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
by: Zhang, Jingyang, et al.
Published: (2023)

Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models
by: Cooper, John, et al.
Published: (2026)

Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
by: Diakonikolas, Ilias, et al.
Published: (2025)

Faster Algorithms for Agnostically Learning Disjunctions and their Implications
by: Diakonikolas, Ilias, et al.
Published: (2025)

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
by: Takahashi, Hiroshi, et al.
Published: (2024)

Generalized Out-of-Distribution Detection: A Survey
by: Yang, Jingkang, et al.
Published: (2021)

HYPO: Hyperspherical Out-of-Distribution Generalization
by: Bai, Haoyue, et al.
Published: (2024)

High-Dimensional Gaussian Mean Estimation under Realizable Contamination
by: Diakonikolas, Ilias, et al.
Published: (2026)

Kernel PCA for Out-of-Distribution Detection
by: Fang, Kun, et al.
Published: (2024)