Cover Image

On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Qiaoyue, Zhiyanov, Alain, Lécuyer, Mathias
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

PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
by: Kazmi, Mishaal, et al.
Published: (2024)

Optimal Rates for Pure $\varepsilon$-Differentially Private Stochastic Convex Optimization with Heavy Tails
by: Lowy, Andrew
Published: (2026)

Provable Benefit of Sign Descent: A Minimal Model Under Heavy-Tailed Class Imbalance
by: Yadav, Robin, et al.
Published: (2025)

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
by: Kunstner, Frederik, et al.
Published: (2024)

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
by: Shpilevskiy, Frederick, et al.
Published: (2025)

Asynchronous Heavy-Tailed Optimization
by: Sun, Junfei, et al.
Published: (2026)

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

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

Training and Evaluating Causal Forecasting Models for Time-Series
by: Crasson, Thomas, et al.
Published: (2024)

Stochastic Bilevel Optimization with Heavy-Tailed Noise
by: Liu, Zhuanghua, et al.
Published: (2025)

Differentially Private Prototypes for Imbalanced Transfer Learning
by: Wahdany, Dariush, et al.
Published: (2024)

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

Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
by: Asi, Hilal, et al.
Published: (2024)

Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
by: Bouayed, Aymene Mohammed, et al.
Published: (2025)

DP-aware AdaLN-Zero: Taming Conditioning-Induced Heavy-Tailed Gradients in Differentially Private Diffusion
by: Huang, Tao, et al.
Published: (2026)

Efficient Distributed Optimization under Heavy-Tailed Noise
by: Lee, Su Hyeong, et al.
Published: (2025)

Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
by: Chen, Hongxu, et al.
Published: (2026)

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

Rényi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincaré Inequalities
by: Dupuis, Benjamin, et al.
Published: (2025)

Federated Stochastic Minimax Optimization under Heavy-Tailed Noises
by: Zhang, Xinwen, et al.
Published: (2025)

Graffin: Stand for Tails in Imbalanced Node Classification
by: Qi, Xiaorui, et al.
Published: (2024)

Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
by: Zhang, Jiaming, et al.
Published: (2026)

Heavy-Tailed Diffusion Models
by: Pandey, Kushagra, et al.
Published: (2024)

Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
by: Sander, Tom, et al.
Published: (2024)

Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates
by: Zhao, Puning, et al.
Published: (2024)

Differentially Private Sparse Linear Regression with Heavy-tailed Responses
by: Tian, Xizhi, et al.
Published: (2025)

Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises
by: Zhu, Tianxi, et al.
Published: (2025)

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

Heavy-Tailed Principal Component Analysis
by: Sayde, Mario, et al.
Published: (2026)

Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
by: Kaushik, Chiraag, et al.
Published: (2024)

Online Sensitivity Optimization in Differentially Private Learning
by: Galli, Filippo, et al.
Published: (2023)

Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
by: Hu, Bingshan, et al.
Published: (2025)

Efficient and Adaptive Posterior Sampling Algorithms for Bandits
by: Hu, Bingshan, et al.
Published: (2024)

Near-Optimal Decentralized Stochastic Nonconvex Optimization with Heavy-Tailed Noise
by: Wang, Menglian, et al.
Published: (2026)

Optimal Asynchronous Stochastic Nonconvex Optimization under Heavy-Tailed Noise
by: Wu, Yidong, et al.
Published: (2026)

Differentially Private Optimization with Sparse Gradients
by: Ghazi, Badih, et al.
Published: (2024)

Multi-Class Imbalanced Learning with Support Vector Machines via Differential Evolution
by: Zhang, Zhong-Liang, et al.
Published: (2025)

Improving GBDT Performance on Imbalanced Datasets: An Empirical Study of Class-Balanced Loss Functions
by: Luo, Jiaqi, et al.
Published: (2024)

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
by: Lyu, Saiyue, et al.
Published: (2024)

Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise
by: Yu, Dingzhi, et al.
Published: (2026)