Imagen de Portada

Banded Square Root Matrix Factorization for Differentially Private Model Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kalinin, Nikita P., Lampert, Christoph
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

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)

Normalized Square Root: Sharper Matrix Factorization Bounds for Differentially Private Continual Counting
por: Henzinger, Monika, et al.
Publicado: (2025)

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

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
por: Schuchardt, Jan, et al.
Publicado: (2026)

Differentially Private Federated $k$-Means Clustering with Server-Side Data
por: Scott, Jonathan, et al.
Publicado: (2025)

Scaling up the Banded Matrix Factorization Mechanism for Differentially Private ML
por: McKenna, Ryan
Publicado: (2024)

Differentially Private Training of Mixture of Experts Models
por: Tholoniat, Pierre, et al.
Publicado: (2024)

Training Differentially Private Models with Secure Multiparty Computation
por: Pentyala, Sikha, et al.
Publicado: (2022)

Differentially Private Diffusion Models
por: Dockhorn, Tim, et al.
Publicado: (2022)

Differentially Private Random Feature Model
por: Liao, Chunyang, et al.
Publicado: (2024)

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
por: Zhou, Yvonne, et al.
Publicado: (2024)

Optimal Differentially Private Model Training with Public Data
por: Lowy, Andrew, et al.
Publicado: (2023)

Releasing Differentially Private Event Logs Using Generative Models
por: Wangelik, Frederik, et al.
Publicado: (2025)

xMLP: Revolutionizing Private Inference with Exclusive Square Activation
por: Li, Jiajie, et al.
Publicado: (2024)

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
por: Brown, Gavin, et al.
Publicado: (2024)

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

Training Set Reconstruction from Differentially Private Forests: How Effective is DP?
por: Gorgé, Alice, et al.
Publicado: (2025)

HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training
por: Xu, Wen, et al.
Publicado: (2026)

DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing
por: Bienstock, Alexander, et al.
Publicado: (2024)

Efficient Differentially Private Fine-Tuning of Diffusion Models
por: Liu, Jing, et al.
Publicado: (2024)

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

Delving into Differentially Private Transformer
por: Ding, Youlong, et al.
Publicado: (2024)

Differentially Private Attention Computation
por: Gao, Yeqi, et al.
Publicado: (2023)

Privately Learning Decision Lists and a Differentially Private Winnow
por: Bun, Mark, et al.
Publicado: (2026)

Training Differentially Private Ad Prediction Models with Semi-Sensitive Features
por: Chua, Lynn, et al.
Publicado: (2024)

Pre-training Differentially Private Models with Limited Public Data
por: Bu, Zhiqi, et al.
Publicado: (2024)

DP-TLDM: Differentially Private Tabular Latent Diffusion Model
por: Zhu, Chaoyi, et al.
Publicado: (2024)

Differentially Private Subspace Fine-Tuning for Large Language Models
por: Zheng, Lele, et al.
Publicado: (2026)

Private and Communication-Efficient Federated Learning based on Differentially Private Sketches
por: Zhang, Meifan, et al.
Publicado: (2024)

Differentially Private Conditional Independence Testing
por: Kalemaj, Iden, et al.
Publicado: (2023)

Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning
por: Kalinin, Nikita P., et al.
Publicado: (2026)

Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systems
por: Perez, Iker, et al.
Publicado: (2024)

Noise-Aware Differentially Private Regression via Meta-Learning
por: Räisä, Ossi, et al.
Publicado: (2024)

Differentially Private Model Merging
por: Yin, Qichuan, et al.
Publicado: (2026)

Revisiting Differentially Private Hyper-parameter Tuning
por: Xiang, Zihang, et al.
Publicado: (2024)

Differentially Private Decentralized Learning with Random Walks
por: Cyffers, Edwige, et al.
Publicado: (2024)

Noise-Aware Differentially Private Variational Inference
por: Alrawajfeh, Talal, et al.
Publicado: (2024)

Differentially Private Domain Adaptation with Theoretical Guarantees
por: Bassily, Raef, et al.
Publicado: (2023)

Practical Differentially Private Hyperparameter Tuning with Subsampling
por: Koskela, Antti, et al.
Publicado: (2023)

Differentially Private Learners for Heterogeneous Treatment Effects
por: Schröder, Maresa, et al.
Publicado: (2025)