Cover Image

Rényi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincaré Inequalities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dupuis, Benjamin, Gürbüzbalaban, Mert, Şimşekli, Umut, Wang, Jian, Yildirim, Sinan, Zhu, Lingjiong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation
by: Dupuis, Benjamin, et al.
Published: (2024)

Heavy-Tail Phenomenon in Decentralized SGD
by: Gurbuzbalaban, Mert, et al.
Published: (2022)

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
by: Dang, Thanh, et al.
Published: (2025)

Variational Inference for Lévy Process-Driven SDEs via Neural Tilting
by: Kindap, Yaman, et al.
Published: (2026)

Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling
by: Gürbüzbalaban, Mert, et al.
Published: (2022)

Heavy-Tailed Diffusion with Denoising Lévy Probabilistic Models
by: Shariatian, Dario, et al.
Published: (2024)

Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets
by: Dupuis, Benjamin, et al.
Published: (2024)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
by: Wan, Yijun, et al.
Published: (2023)

Generalization Bounds for Markov Algorithms through Entropy Flow Computations
by: Dupuis, Benjamin, et al.
Published: (2025)

Generalized EXTRA stochastic gradient Langevin dynamics
by: Gurbuzbalaban, Mert, et al.
Published: (2024)

Anchored Langevin Algorithms
by: Gurbuzbalaban, Mert, et al.
Published: (2025)

Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
by: Dupuis, Benjamin, et al.
Published: (2025)

High-Order Langevin Monte Carlo Algorithms
by: Dang, Thanh, et al.
Published: (2025)

Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
by: Andreeva, Rayna, et al.
Published: (2024)

DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks
by: Bajwa, Waheed U., et al.
Published: (2025)

MCMC for Bayesian estimation of Differential Privacy from Membership Inference Attacks
by: Yildirim, Ceren, et al.
Published: (2025)

Tighter Generalisation Bounds via Interpolation
by: Viallard, Paul, et al.
Published: (2024)

Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds
by: Tuci, Mario, et al.
Published: (2025)

Differentially Private Online Bayesian Estimation With Adaptive Truncation
by: Yıldırım, Sinan
Published: (2023)

A PAC-Bayesian Link Between Generalisation and Flat Minima
by: Haddouche, Maxime, et al.
Published: (2024)

Bayesian Frequency Estimation Under Local Differential Privacy With an Adaptive Randomized Response Mechanism
by: Aydin, Soner, et al.
Published: (2024)

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

Accelerated Gradient Methods with Biased Gradient Estimates: Risk Sensitivity, High-Probability Guarantees, and Large Deviation Bounds
by: Gürbüzbalaban, Mert, et al.
Published: (2025)

Latent-Augmented Discrete Diffusion Models
by: Shariatian, Dario, et al.
Published: (2025)

Piecewise deterministic generative models
by: Bertazzi, Andrea, et al.
Published: (2024)

Sampling non-log-concave densities via Hessian-free high-resolution dynamics
by: Wang, Xiaoyu, et al.
Published: (2026)

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

Generalization at the Edge of Stability
by: Tuci, Mario, et al.
Published: (2026)

RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
by: Fang, Cheng, et al.
Published: (2025)

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
by: Schaipp, Fabian, et al.
Published: (2025)

On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance
by: Tang, Qiaoyue, et al.
Published: (2025)

Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances
by: Gao, Xuefeng, et al.
Published: (2024)

Geometric Renyi Differential Privacy: Ricci Curvature Characterized by Heat Diffusion Mechanisms
by: Chang, Xiaotian, et al.
Published: (2026)

On the Interaction of Compressibility and Adversarial Robustness
by: Barsbey, Melih, et al.
Published: (2025)

Tracking the Median of Gradients with a Stochastic Proximal Point Method
by: Schaipp, Fabian, et al.
Published: (2024)

Tail Annealing for Heavy-Tailed Flow Matching
by: Pachebat, Jean
Published: (2026)

Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation
by: Hyrup, Tobias, et al.
Published: (2025)

Regime-Switching Langevin Monte Carlo Algorithms
by: Wang, Xiaoyu, et al.
Published: (2025)

Models of Heavy-Tailed Mechanistic Universality
by: Hodgkinson, Liam, et al.
Published: (2025)