This paper presents a new generalization error analysis for the Decentralized Stochastic Gradient Descent (D-SGD) algorithm based on algorithmic stability.
1 code implementation • 10 Oct 2022 • Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Teleńczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux
In this work, we propose a novel cross-silo dataset suite focused on healthcare, FLamby (Federated Learning AMple Benchmark of Your cross-silo strategies), to bridge the gap between theory and practice of cross-silo FL.
We study the case where some of the distributions have the same mean, and the agents are allowed to actively query information from other agents.
In this paper, we study differentially private empirical risk minimization (DP-ERM).
One of the key challenges in decentralized and federated learning is to design algorithms that efficiently deal with highly heterogeneous data distributions across agents.
We remove speaker information from these attributes by introducing differentially private feature extractors based on an autoencoder and an automatic speech recognizer, respectively, trained using noise layers.
The widespread of powerful personal devices capable of collecting voice of their users has opened the opportunity to build speaker adapted speech recognition system (ASR) or to participate to collaborative learning of ASR.
This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR).
In this paper, we propose Differentially Private proximal Coordinate Descent (DP-CD), a new method to solve composite DP-ERM problems.
The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker.
In this paper, we focus on the protection of speaker identity and study the extent to which users can be recognized based on the encoded representation of their speech as obtained by a deep encoder-decoder architecture trained for ASR.
In this paper, we investigate anonymization methods based on voice conversion.
We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator.
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements.
We consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective.
Statistical models for networks have been typically committed to strong prior assumptions concerning the form of the modeled distributions.