Imagen de Portada

Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Choquette-Choo, Christopher A., Ganesh, Arun, Thakurta, Abhradeep
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Privacy Amplification for Matrix Mechanisms
por: Choquette-Choo, Christopher A., et al.
Publicado: (2023)

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
por: Choquette-Choo, Christopher A., et al.
Publicado: (2023)

On Design Principles for Private Adaptive Optimizers
por: Ganesh, Arun, et al.
Publicado: (2025)

Near Exact Privacy Amplification for Matrix Mechanisms
por: Choquette-Choo, Christopher A., et al.
Publicado: (2024)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
por: Steinke, Thomas, et al.
Publicado: (2024)

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms
por: Ganesh, Arun
Publicado: (2024)

Correlated Noise Mechanisms for Differentially Private Learning
por: Pillutla, Krishna, et al.
Publicado: (2025)

Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
por: Shejwalkar, Virat, et al.
Publicado: (2022)

Training Large ASR Encoders with Differential Privacy
por: Chauhan, Geeticka, et al.
Publicado: (2024)

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
por: Vinod, Vishnu, et al.
Publicado: (2025)

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
por: Brown, Gavin, et al.
Publicado: (2024)

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach
por: Ganesh, Arun, et al.
Publicado: (2025)

Linear-Time User-Level DP-SCO via Robust Statistics
por: Ghazi, Badih, et al.
Publicado: (2025)

Preserving Expert-Level Privacy in Offline Reinforcement Learning
por: Sharma, Navodita, et al.
Publicado: (2024)

Privacy Auditing of Large Language Models
por: Panda, Ashwinee, et al.
Publicado: (2025)

Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
por: Liu, Hongbin, et al.
Publicado: (2024)

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
por: Dvijotham, Krishnamurthy, et al.
Publicado: (2024)

User Inference Attacks on Large Language Models
por: Kandpal, Nikhil, et al.
Publicado: (2023)

Privacy Side Channels in Machine Learning Systems
por: Debenedetti, Edoardo, et al.
Publicado: (2023)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
por: Wang, Liangyu, et al.
Publicado: (2025)

Poisoning Web-Scale Training Datasets is Practical
por: Carlini, Nicholas, et al.
Publicado: (2023)

Teach LLMs to Phish: Stealing Private Information from Language Models
por: Panda, Ashwinee, et al.
Publicado: (2024)

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
por: Dong, Andy, et al.
Publicado: (2026)

Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
por: Kalinin, Nikita P., et al.
Publicado: (2025)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
por: Nasr, Milad, et al.
Publicado: (2025)

DP-SGD with weight clipping
por: Barczewski, Antoine, et al.
Publicado: (2023)

Scaling Laws for Differentially Private Language Models
por: McKenna, Ryan, et al.
Publicado: (2025)

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
por: Sha, Haichao, et al.
Publicado: (2026)

Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
por: Mohammady, Meisam, et al.
Publicado: (2026)

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
por: Huang, Yangsibo, et al.
Publicado: (2025)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
por: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Publicado: (2024)

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
por: Chaudhari, Harsh, et al.
Publicado: (2024)

Lessons from Defending Gemini Against Indirect Prompt Injections
por: Shi, Chongyang, et al.
Publicado: (2025)

DP-KAN: Differentially Private Kolmogorov-Arnold Networks
por: Kalinin, Nikita P., et al.
Publicado: (2024)

R+R:Understanding Hyperparameter Effects in DP-SGD
por: Morsbach, Felix, et al.
Publicado: (2024)

DP-LDMs: Differentially Private Latent Diffusion Models
por: Liu, Michael F., et al.
Publicado: (2023)

Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
por: Räisä, Ossi, et al.
Publicado: (2024)

SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy
por: Nahid, Md Mahadi Hasan, et al.
Publicado: (2024)

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
por: Liu, Ken Ziyu, et al.
Publicado: (2025)

Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost
por: Pathegama, Madhura, et al.
Publicado: (2026)