Copertina

On Design Principles for Private Adaptive Optimizers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ganesh, Arun, McMahan, Brendan, Thakurta, Abhradeep
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

An Inversion Theorem for Buffered Linear Toeplitz (BLT) Matrices and Applications to Streaming Differential Privacy
di: McMahan, H. Brendan, et al.
Pubblicazione: (2025)

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

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

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

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

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

One-shot Empirical Privacy Estimation for Federated Learning
di: Andrew, Galen, et al.
Pubblicazione: (2023)

Fine-Tuning Large Language Models with User-Level Differential Privacy
di: Charles, Zachary, et al.
Pubblicazione: (2024)

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

Federated Learning in Practice: Reflections and Projections
di: Daly, Katharine, et al.
Pubblicazione: (2024)

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

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

Optimal Attack and Defense for Reinforcement Learning
di: McMahan, Jeremy, et al.
Pubblicazione: (2023)

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

Inception: Efficiently Computable Misinformation Attacks on Markov Games
di: McMahan, Jeremy, et al.
Pubblicazione: (2024)

Confidential Federated Computations
di: Eichner, Hubert, et al.
Pubblicazione: (2024)

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

Data Poisoning to Fake a Nash Equilibrium in Markov Games
di: Wu, Young, et al.
Pubblicazione: (2023)

Differentially Private Stream Processing at Scale
di: Zhang, Bing, et al.
Pubblicazione: (2023)

Optimized Tradeoffs for Private Prediction with Majority Ensembling
di: Jiang, Shuli, et al.
Pubblicazione: (2024)

Adaptively Private Next-Token Prediction of Large Language Models
di: Flemings, James, et al.
Pubblicazione: (2024)

Private Rate-Constrained Optimization with Applications to Fair Learning
di: Yaghini, Mohammad, et al.
Pubblicazione: (2025)

Differentially Private Optimization for Non-Decomposable Objective Functions
di: Kong, Weiwei, et al.
Pubblicazione: (2023)

ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterations
di: Ling, Xinpeng, et al.
Pubblicazione: (2023)

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
di: Panda, Ashwinee, et al.
Pubblicazione: (2022)

The Data Minimization Principle in Machine Learning
di: Ganesh, Prakhar, et al.
Pubblicazione: (2024)

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
di: Ponomareva, Natalia, et al.
Pubblicazione: (2025)

It's My Data Too: Private ML for Datasets with Multi-User Training Examples
di: Ganesh, Arun, et al.
Pubblicazione: (2025)

AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing
di: Zhou, Tong, et al.
Pubblicazione: (2024)

Output Perturbation for Differentially Private Convex Optimization: Faster and More General
di: Lowy, Andrew, et al.
Pubblicazione: (2021)

On the Gradient Complexity of Private Optimization with Private Oracles
di: Menart, Michael, et al.
Pubblicazione: (2025)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
di: Zhang, Xinwei, et al.
Pubblicazione: (2024)

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
di: Zhang, Xinwei, et al.
Pubblicazione: (2024)