Image de couverture de livre

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Brown, Gavin, Dvijotham, Krishnamurthy, Evans, Georgina, Liu, Daogao, Smith, Adam, Thakurta, Abhradeep
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
par: Choquette-Choo, Christopher A., et autres
Publié: (2023)

On Design Principles for Private Adaptive Optimizers
par: Ganesh, Arun, et autres
Publié: (2025)

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
par: Dvijotham, Krishnamurthy, et autres
Publié: (2024)

Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
par: Liu, Hongbin, et autres
Publié: (2024)

Correlated Noise Mechanisms for Differentially Private Learning
par: Pillutla, Krishna, et autres
Publié: (2025)

Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
par: Birrell, Jeremiah, et autres
Publié: (2024)

Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches
par: Choquette-Choo, Christopher A., et autres
Publié: (2024)

Differentially Private Stream Processing at Scale
par: Zhang, Bing, et autres
Publié: (2023)

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
par: Vinod, Vishnu, et autres
Publié: (2025)

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach
par: Ganesh, Arun, et autres
Publié: (2025)

Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
par: Shejwalkar, Virat, et autres
Publié: (2022)

Near Exact Privacy Amplification for Matrix Mechanisms
par: Choquette-Choo, Christopher A., et autres
Publié: (2024)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
par: Steinke, Thomas, et autres
Publié: (2024)

The Power of Sampling: Dimension-free Risk Bounds in Private ERM
par: Lee, Yin Tat, et autres
Publié: (2021)

Privacy Amplification for Matrix Mechanisms
par: Choquette-Choo, Christopher A., et autres
Publié: (2023)

Tighter Bounds for Local Differentially Private Core Decomposition and Densest Subgraph
par: Henzinger, Monika, et autres
Publié: (2024)

Private Geometric Median in Nearly-Linear Time
par: Kumar, Syamantak, et autres
Publié: (2025)

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
par: Brown, Gavin, et autres
Publié: (2024)

Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
par: Lowy, Andrew, et autres
Publié: (2025)

Tighter Risk Bounds for Mixtures of Experts
par: Akretche, Wissam, et autres
Publié: (2024)

Analyzing the Differentially Private Theil-Sen Estimator for Simple Linear Regression
par: Sarathy, Jayshree, et autres
Publié: (2022)

Adaptive Batch Size for Privately Finding Second-Order Stationary Points
par: Liu, Daogao, et autres
Publié: (2024)

Learning with Locally Private Examples by Inverse Weierstrass Private Stochastic Gradient Descent
par: Dufraiche, Jean, et autres
Publié: (2026)

Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
par: Kornowski, Guy, et autres
Publié: (2024)

Preserving Expert-Level Privacy in Offline Reinforcement Learning
par: Sharma, Navodita, et autres
Publié: (2024)

Faster Algorithms for User-Level Private Stochastic Convex Optimization
par: Lowy, Andrew, et autres
Publié: (2024)

Training Large ASR Encoders with Differential Privacy
par: Chauhan, Geeticka, et autres
Publié: (2024)

Adapting AlphaEvolve to Optimize Fully Homomorphic Encryption on TPUs
par: Gorantala, Shruthi, et autres
Publié: (2026)

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
par: Shpilevskiy, Frederick, et autres
Publié: (2025)

Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
par: Asi, Hilal, et autres
Publié: (2024)

Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
par: Choudhary, Sarthak, et autres
Publié: (2025)

Private Linear Regression with Differential Privacy and PAC Privacy
par: Yang, Hillary, et autres
Publié: (2024)

The Relative Gaussian Mechanism and its Application to Private Gradient Descent
par: Hendrikx, Hadrien, et autres
Publié: (2023)

Tighter Privacy Analysis for Truncated Poisson Sampling
par: Ganesh, Arun
Publié: (2025)

Subset-Based Instance Optimality in Private Estimation
par: Dick, Travis, et autres
Publié: (2023)

Differentially Private Sparse Linear Regression with Heavy-tailed Responses
par: Tian, Xizhi, et autres
Publié: (2025)

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
par: Yu, Da, et autres
Publié: (2022)

Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
par: Bhagwatkar, Rishika, et autres
Publié: (2025)

Private Online Learning via Lazy Algorithms
par: Asi, Hilal, et autres
Publié: (2024)

Expressive Losses for Verified Robustness via Convex Combinations
par: De Palma, Alessandro, et autres
Publié: (2023)