Výsledky vyhledávání - "Chitnis, Mona"

Report

pfl-research: simulation framework for accelerating research in Private Federated Learning

Autor: Granqvist, Filip, Song, Congzheng, Cahill, Áine, van Dalen, Rogier, Pelikan, Martin, Chan, Yi Sheng, Feng, Xiaojun, Krishnaswami, Natarajan, Jina, Vojta, Chitnis, Mona

Federated learning (FL) is an emerging machine learning (ML) training paradigm where clients own their data and collaborate to train a global model, without revealing any data to the server and other participants. Researchers commonly perform experim

Externí odkaz: http://arxiv.org/abs/2404.06430

Zobrazit plný text záznamu

Report

Momentum Approximation in Asynchronous Private Federated Learning

Autor: Yu, Tao, Song, Congzheng, Wang, Jianyu, Chitnis, Mona

Asynchronous protocols have been shown to improve the scalability of federated learning (FL) with a massive number of clients. Meanwhile, momentum-based methods can achieve the best model quality in synchronous FL. However, naively applying momentum

Externí odkaz: http://arxiv.org/abs/2402.09247

Zobrazit plný text záznamu

Report

Samplable Anonymous Aggregation for Private Federated Data Analysis

We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited in their u

Externí odkaz: http://arxiv.org/abs/2307.15017

Zobrazit plný text záznamu

Report

Population Expansion for Training Language Models with Private Federated Learning

Autor: Koga, Tatsuki, Song, Congzheng, Pelikan, Martin, Chitnis, Mona

Federated learning (FL) combined with differential privacy (DP) offers machine learning (ML) training with distributed devices and with a formal privacy guarantee. With a large population of devices, FL with DP produces a performant model in a timely

Externí odkaz: http://arxiv.org/abs/2307.07477

Zobrazit plný text záznamu