Copertina

Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bar, Yarin, Shaer, Shalev, Romano, Yaniv
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Testing For Distribution Shifts with Conditional Conformal Test Martingales
di: Shaer, Shalev, et al.
Pubblicazione: (2026)

Prediction-Powered Semi-Supervised Learning with Online Power Tuning
di: Shoham, Noa, et al.
Pubblicazione: (2025)

Semi-Supervised Hypothesis Testing by Betting on Predictions
di: Tenzer, Yaniv, et al.
Pubblicazione: (2026)

Immediate Derivatives Suffice for Online Recurrent Adaptation
di: Merin, Aur Shalev
Pubblicazione: (2026)

Selective Safety Steering via Value-Filtered Decoding
di: Einbinder, Bat-Sheva, et al.
Pubblicazione: (2026)

Learning a Continue-Thinking Token for Enhanced Test-Time Scaling
di: Ringel, Liran, et al.
Pubblicazione: (2025)

Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
di: Tolochinsky, Elad, et al.
Pubblicazione: (2026)

Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting
di: Chen, Can, et al.
Pubblicazione: (2024)

I Bet You Did Not Mean That: Testing Semantic Importance via Betting
di: Teneggi, Jacopo, et al.
Pubblicazione: (2024)

Robust Conformal Prediction Using Privileged Information
di: Feldman, Shai, et al.
Pubblicazione: (2024)

How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
di: Feldman, Shai, et al.
Pubblicazione: (2026)

Synthetic-Powered Multiple Testing with FDR Control
di: Lee, Yonghoon, et al.
Pubblicazione: (2026)

Semi-Supervised Risk Control via Prediction-Powered Inference
di: Einbinder, Bat-Sheva, et al.
Pubblicazione: (2024)

Pivotal Auto-Encoder via Self-Normalizing ReLU
di: Goldenstein, Nelson, et al.
Pubblicazione: (2024)

The Evolution of Football Betting- A Machine Learning Approach to Match Outcome Forecasting and Bookmaker Odds Estimation
di: Mandadapu, Purnachandra
Pubblicazione: (2024)

Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
di: Davidov, Hen, et al.
Pubblicazione: (2025)

Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
di: Simeone, Osvaldo, et al.
Pubblicazione: (2025)

Early Time Classification with Accumulated Accuracy Gap Control
di: Ringel, Liran, et al.
Pubblicazione: (2024)

Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
di: Feldman, Shai, et al.
Pubblicazione: (2025)

Ranked Entropy Minimization for Continual Test-Time Adaptation
di: Han, Jisu, et al.
Pubblicazione: (2025)

Testing for Outliers with Conformal p-values
di: Bates, Stephen, et al.
Pubblicazione: (2021)

Robust Conformal Outlier Detection under Contaminated Reference Data
di: Bashari, Meshi, et al.
Pubblicazione: (2025)

Learning to Bet for Horizon-Aware Anytime-Valid Testing
di: Taga, Ege Onur, et al.
Pubblicazione: (2026)

Summary of the NOTSOFAR-1 Challenge: Highlights and Learnings
di: Abramovski, Igor, et al.
Pubblicazione: (2025)

Optimistic Interior Point Methods for Sequential Hypothesis Testing by Betting
di: Chen, Can, et al.
Pubblicazione: (2025)

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
di: Bar-Shalom, Guy, et al.
Pubblicazione: (2025)

Massive Redundancy in Gradient Transport Enables Sparse Online Learning
di: Merin, Aur Shalev
Pubblicazione: (2026)

Multi-Armed Sequential Hypothesis Testing by Betting
di: Sandoval, Ricardo J., et al.
Pubblicazione: (2026)

Bayesian Modeling and Estimation of Linear Time-Varying Systems using Neural Networks and Gaussian Processes
di: Shulman, Yaniv
Pubblicazione: (2025)

Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
di: Huang, Wei-Ping, et al.
Pubblicazione: (2026)

Statistically Truthful Auctions via Acceptance Rule
di: Lotan, Roy Maor, et al.
Pubblicazione: (2024)

Thwarting Cybersecurity Attacks with Explainable Concept Drift
di: Shaer, Ibrahim, et al.
Pubblicazione: (2024)

Calibration-Free EEG-based Driver Drowsiness Detection with Online Test-Time Adaptation
di: Jang, Geun-Deok, et al.
Pubblicazione: (2025)

Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
di: Lee, Jonghyun, et al.
Pubblicazione: (2024)

Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
di: Zhou, Xingzhi, et al.
Pubblicazione: (2024)

A Unified Framework for Simultaneous Parameter and Function Discovery in Differential Equations
di: Manor, Shalev, et al.
Pubblicazione: (2025)

STaR-Bets: Sequential Target-Recalculating Bets for Tighter Confidence Intervals
di: Voráček, Václav, et al.
Pubblicazione: (2025)

Test-Time Adaptation for LLM Agents via Environment Interaction
di: Chen, Arthur, et al.
Pubblicazione: (2025)

ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance
di: Shamsi, Afshar, et al.
Pubblicazione: (2024)

The Benefits and Risks of Transductive Approaches for AI Fairness
di: Razzak, Muhammed, et al.
Pubblicazione: (2024)