Image de couverture de livre

DP-MicroAdam: Private and Frugal Algorithm for Training and Fine-tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hudişteanu, Mihaela, Kalinin, Nikita P., Cyffers, Edwige
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Setting $\varepsilon$ is not the Issue in Differential Privacy
par: Cyffers, Edwige
Publié: (2025)

Differentially Private Decentralized Learning with Random Walks
par: Cyffers, Edwige, et autres
Publié: (2024)

DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training
par: Kalinin, Nikita P., et autres
Publié: (2026)

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
par: Modoranu, Ionut-Vlad, et autres
Publié: (2024)

Limits of Personalizing Differential Privacy Budgets
par: Cyffers, Edwige, et autres
Publié: (2026)

DP-KAN: Differentially Private Kolmogorov-Arnold Networks
par: Kalinin, Nikita P., et autres
Publié: (2024)

Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy Machine Learning
par: Damie, Marc, et autres
Publié: (2025)

Learning Rate Scheduling with Matrix Factorization for Private Training
par: Kalinin, Nikita P., et autres
Publié: (2025)

Banded Square Root Matrix Factorization for Differentially Private Model Training
par: Kalinin, Nikita P., et autres
Publié: (2024)

Optimal Regularization for Performative Learning
par: Cyffers, Edwige, et autres
Publié: (2025)

Privacy Attacks in Decentralized Learning
par: Mrini, Abdellah El, et autres
Publié: (2024)

Optimal Classification under Performative Distribution Shift
par: Cyffers, Edwige, et autres
Publié: (2024)

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
par: Wang, Puyu, et autres
Publié: (2026)

Notes on Sampled Gaussian Mechanism
par: Kalinin, Nikita P.
Publié: (2024)

Binned Group Algebra Factorization for Differentially Private Continual Counting
par: Henzinger, Monika, et autres
Publié: (2025)

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
par: Cyffers, Edwige, et autres
Publié: (2022)

Frugal Algorithm Selection
par: Kuş, Erdem, et autres
Publié: (2024)

DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning
par: Chooi, Jay, et autres
Publié: (2025)

Can Muon Fine-tune Adam-Pretrained Models?
par: Qu, Xingyu, et autres
Publié: (2026)

Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization
par: Bellet, Aurélien, et autres
Publié: (2025)

Normalized Square Root: Sharper Matrix Factorization Bounds for Differentially Private Continual Counting
par: Henzinger, Monika, et autres
Publié: (2025)

DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models
par: Liu, Jin, et autres
Publié: (2026)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
par: Wang, Liangyu, et autres
Publié: (2025)

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
par: Mehmood, Haaris, et autres
Publié: (2026)

Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning
par: Kalinin, Nikita P., et autres
Publié: (2026)

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
par: Ke, Shuqi, et autres
Publié: (2024)

DP-Adam-AC: Privacy-preserving Fine-Tuning of Localizable Language Models Using Adam Optimization with Adaptive Clipping
par: Yang, Ruoxing
Publié: (2025)

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

LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
par: Lim, Juntaek, et autres
Publié: (2024)

Selective Pre-training for Private Fine-tuning
par: Yu, Da, et autres
Publié: (2023)

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
par: Schuchardt, Jan, et autres
Publié: (2026)

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
par: Sha, Haichao, et autres
Publié: (2026)

Training Set Reconstruction from Differentially Private Forests: How Effective is DP?
par: Gorgé, Alice, et autres
Publié: (2025)

Continual Release Moment Estimation with Differential Privacy
par: Kalinin, Nikita P., et autres
Publié: (2025)

DP-GPL: Differentially Private Graph Prompt Learning
par: Xu, Jing, et autres
Publié: (2025)

DP-HYPE: Distributed Differentially Private Hyperparameter Search
par: Liebenow, Johannes, et autres
Publié: (2025)

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
par: Gu, Zhaoyuan, et autres
Publié: (2026)

OneBatchPAM: A Fast and Frugal K-Medoids Algorithm
par: de Mathelin, Antoine, et autres
Publié: (2025)

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
par: Lebensold, Jonathan, et autres
Publié: (2024)

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning
par: Huang, Wei, et autres
Publié: (2026)