activity
20172026
most citedAsynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise

17 citations · 36 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization

Murat Bilgehan Ertan, Xiaochen Zhu, Phuong Ha Nguyen +2

We introduce PACZero, a family of PAC-private zeroth-order mechanisms for fine-tuning large language models that delivers usable utility at . This privacy regime…

cs.LG2023

Batch Clipping and Adaptive Layerwise Clipping for Differential Private Stochastic Gradient Descent

Toan N. Nguyen, Phuong Ha Nguyen, Lam M. Nguyen +1

Each round in Differential Private Stochastic Gradient Descent (DPSGD) transmits a sum of clipped gradients obfuscated with Gaussian noise to a central server which uses this to up…

cs.LG2023

Considerations on the Theory of Training Models with Differential Privacy

Marten van Dijk, Phuong Ha Nguyen

In federated learning collaborative learning takes place by a set of clients who each want to remain in control of how their local training data is used, in particular, how can eac…

cs.LG2022

Generalizing DP-SGD with Shuffling and Batch Clipping

Marten van Dijk, Phuong Ha Nguyen, Toan N. Nguyen +1

Classical differential private DP-SGD implements individual clipping with random subsampling, which forces a mini-batch SGD approach. We provide a general differential private algo…

cs.LG2021

Proactive DP: A Multple Target Optimization Framework for DP-SGD

Marten van Dijk, Nhuong V. Nguyen, Toan N. Nguyen +2

We introduce a multiple target optimization framework for DP-SGD referred to as pro-active DP. In contrast to traditional DP accountants, which are used to track the expenditure of…

cs.LG2020

Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizes

Marten van Dijk, Nhuong V. Nguyen, Toan N. Nguyen +3

Hogwild! implements asynchronous Stochastic Gradient Descent (SGD) where multiple threads in parallel access a common repository containing training data, perform SGD iterations an…