Copertina

Nonparametric Variational Differential Privacy via Embedding Parameter Clipping

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zein, Dina El, Kumar, Shashi, Henderson, James
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

Differential Privacy for Transformer Embeddings of Text with Nonparametric Variational Information Bottleneck
di: Zein, Dina El, et al.
Pubblicazione: (2026)

Nonparametric Automatic Differentiation Variational Inference with Spline Approximation
di: Shao, Yuda, et al.
Pubblicazione: (2024)

Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy
di: Islamov, Rustem, et al.
Pubblicazione: (2025)

When Gradient Clipping Becomes a Control Mechanism for Differential Privacy in Deep Learning
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

GeoClip: Geometry-Aware Clipping for Differentially Private SGD
di: Gilani, Atefeh, et al.
Pubblicazione: (2025)

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
di: Khah, Saleh Vatan, et al.
Pubblicazione: (2025)

Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics
di: Samota, Sandeep Kumar, et al.
Pubblicazione: (2026)

A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport
di: Kaloga, Yacouba, et al.
Pubblicazione: (2025)

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
di: Marshall, Noah, et al.
Pubblicazione: (2024)

Parameter-free Clipped Gradient Descent Meets Polyak
di: Takezawa, Yuki, et al.
Pubblicazione: (2024)

LLMs are Bayesian, In Expectation, Not in Realization
di: Chlon, Leon, et al.
Pubblicazione: (2025)

Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding
di: Wei, Yuecen, et al.
Pubblicazione: (2023)

Privacy-Preserving Graph Embedding based on Local Differential Privacy
di: Li, Zening, et al.
Pubblicazione: (2023)

MOCK: an Algorithm for Learning Nonparametric Differential Equations via Multivariate Occupation Kernel Functions
di: Rielly, Victor, et al.
Pubblicazione: (2023)

Variational Neural Stochastic Differential Equations with Change Points
di: El-Laham, Yousef, et al.
Pubblicazione: (2024)

The Privacy Price of Tail-Risk Learning: Effective Tail Sample Size in Differentially Private CVaR Optimization
di: Mansouri, El Mustapha
Pubblicazione: (2026)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
di: Zhang, Xinwei, et al.
Pubblicazione: (2023)

Robust Stochastic Optimization via Gradient Quantile Clipping
di: Merad, Ibrahim, et al.
Pubblicazione: (2023)

Efficient Private SCO for Heavy-Tailed Data via Averaged Clipping
di: Jin, Chenhan, et al.
Pubblicazione: (2022)

Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts
di: Wang, James, et al.
Pubblicazione: (2026)

Adaptive Clipping for Privacy-Preserving Few-Shot Learning: Enhancing Generalization with Limited Data
di: Ranaweera, Kanishka, et al.
Pubblicazione: (2025)

Structure-Preference Enabled Graph Embedding Generation under Differential Privacy
di: Zhang, Sen, et al.
Pubblicazione: (2025)

SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training
di: Soleymani, Dorsa, et al.
Pubblicazione: (2025)

Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
di: Yukhimchuk, Alexander, et al.
Pubblicazione: (2026)

Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraints
di: Auddy, Arnab, et al.
Pubblicazione: (2024)

PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping
di: Huang, Nai-Chieh, et al.
Pubblicazione: (2023)

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
di: Zhang, Bonan, et al.
Pubblicazione: (2025)

Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling
di: Sharma, Gaurang, et al.
Pubblicazione: (2026)

Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models
di: Park, Jaesung R., et al.
Pubblicazione: (2025)

Forward Learning with Differential Privacy
di: Feng, Mingqian, et al.
Pubblicazione: (2025)

Robust and Fast Training via Per-Sample Clipping
di: Nobile, Davide, et al.
Pubblicazione: (2026)

Joint Embedding Variational Bayes
di: Oji, Amin, et al.
Pubblicazione: (2026)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
di: Şimşekli, Umut, et al.
Pubblicazione: (2024)

Parameter Inference via Differentiable Diffusion Bridge Importance Sampling
di: Boserup, Nicklas, et al.
Pubblicazione: (2024)

The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
di: Lev, Omri, et al.
Pubblicazione: (2025)

Privacy-Preserving Conformal Prediction Under Local Differential Privacy
di: Penso, Coby, et al.
Pubblicazione: (2025)

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers and Gradient Clipping
di: Pelikan, Martin, et al.
Pubblicazione: (2023)

Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints
di: Cai, T. Tony, et al.
Pubblicazione: (2024)

Wasserstein Differential Privacy
di: Yang, Chengyi, et al.
Pubblicazione: (2024)

Differentially Private Nonparametric Confidence Intervals Under Minimal Distributional Assumptions
di: Shoham, Tomer, et al.
Pubblicazione: (2025)