Copertina

When Determinants Are Not Enough: Private Rare Switching

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Zhou, Xingyu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Sample Complexity of Differentially Private Policy Optimization
di: He, Yi, et al.
Pubblicazione: (2025)

Towards Differentially Private Reinforcement Learning with General Function Approximation
di: He, Yi, et al.
Pubblicazione: (2026)

Improved Bounds for Private and Robust Alignment
di: Weng, Wenqian, et al.
Pubblicazione: (2025)

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
di: Zamboni, Riccardo, et al.
Pubblicazione: (2024)

A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
di: Zhou, Xingyu, et al.
Pubblicazione: (2025)

Differentially Private Linear Bandits with Partial Distributed Feedback
di: Li, Fengjiao, et al.
Pubblicazione: (2022)

When One Point Is Not Enough: Addressing Ambiguous Instances in Dimensionality Reduction by Splitting
di: van der Hoorn, Diede P. M., et al.
Pubblicazione: (2026)

Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment
di: Zhou, Xingyu, et al.
Pubblicazione: (2025)

When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior
di: Zhang, Chengyuan, et al.
Pubblicazione: (2025)

When Less is Enough: Efficient Inference via Collaborative Reasoning
di: Chen, Yilei, et al.
Pubblicazione: (2026)

When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
di: Peng, Ningkang, et al.
Pubblicazione: (2026)

CaRT: Teaching LLM Agents to Know When They Know Enough
di: Liu, Grace, et al.
Pubblicazione: (2025)

When Latent Geometry Is Not Enough: Draft-Conditioned Latent Refinement for Non-Autoregressive Text Generation
di: Zhang, De Shuai
Pubblicazione: (2026)

When to Switch, Not Just What: Transition Quality Prediction in Clash Royale
di: Heo, Heeyun, et al.
Pubblicazione: (2026)

TURBOTEST: Learning When Less is Enough through Early Termination of Internet Speed Tests
di: Manda, Haarika, et al.
Pubblicazione: (2025)

Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning
di: Tava, Chris
Pubblicazione: (2025)

When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
di: Ascarate, Alejandro, et al.
Pubblicazione: (2026)

Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare
di: Zhou, Juexiao, et al.
Pubblicazione: (2023)

When Is Rank-1 Enough? Geometry-Guided Initialization for Parameter-Efficient Fine-Tuning
di: Zhao, Haoran, et al.
Pubblicazione: (2026)

The Challenger: When Do New Data Sources Justify Switching Machine Learning Models?
di: Digalakis Jr, Vassilis, et al.
Pubblicazione: (2025)

Probabilistic Scores of Classifiers, Calibration is not Enough
di: Machado, Agathe Fernandes, et al.
Pubblicazione: (2024)

Transformers are Expressive, But Are They Expressive Enough for Regression?
di: Nath, Swaroop, et al.
Pubblicazione: (2024)

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
di: Gao, Changyu, et al.
Pubblicazione: (2024)

Differentially Private Federated Learning without Noise Addition: When is it Possible?
di: Zhang, Jiang, et al.
Pubblicazione: (2024)

Screening Is Enough
di: Nakanishi, Ken M.
Pubblicazione: (2026)

When Test-Time Guidance Is Enough: Fast Image and Video Editing with Diffusion Guidance
di: Ghorbel, Ahmed, et al.
Pubblicazione: (2026)

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs
di: Zagribelnyy, Bogdan, et al.
Pubblicazione: (2026)

Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
di: Freiesleben, Timo, et al.
Pubblicazione: (2026)

On the Universality of Transformer Architectures; How Much Attention Is Enough?
di: Abbasi, Amirreza, et al.
Pubblicazione: (2025)

When Is Inductive Inference Possible?
di: Lu, Zhou
Pubblicazione: (2023)

Softmax is not Enough (for Adaptive Conformal Classification)
di: Attar, Navid Akhavan, et al.
Pubblicazione: (2026)

Good-Enough LLM Obfuscation (GELO)
di: Belikov, Anatoly, et al.
Pubblicazione: (2026)

Is AI Robust Enough for Scientific Research?
di: Zhang, Jun-Jie, et al.
Pubblicazione: (2024)

Is Bellman Equation Enough for Learning Control?
di: You, Haoxiang, et al.
Pubblicazione: (2025)

Why Channel-Centric Models are not Enough to Predict End-to-End Performance in Private 5G: A Measurement Campaign and Case Study
di: Jörgensen, Nils
Pubblicazione: (2026)

Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction
di: Meynent, Léo, et al.
Pubblicazione: (2025)

When the Small-Loss Trick is Not Enough: Multi-Label Image Classification with Noisy Labels Applied to CCTV Sewer Inspections
di: Chelouche, Keryan, et al.
Pubblicazione: (2024)

AdaSwitch: An Adaptive Switching Meta-Algorithm for Learning-Augmented Bounded-Influence Problems
di: Chen, Xi, et al.
Pubblicazione: (2025)

Trivial Graph Features and Classical Learning are Enough to Detect Random Anomalies
di: Latapy, Matthieu, et al.
Pubblicazione: (2026)

Linear Attention is Enough in Spatial-Temporal Forecasting
di: Ning, Xinyu
Pubblicazione: (2024)