Search Results for author: Marc Tommasi

Found 17 papers, 4 papers with code

Improved Stability and Generalization Analysis of the Decentralized SGD Algorithm

no code implementations5 Jun 2023 Batiste Le Bars, Aurélien Bellet, Marc Tommasi

This paper presents a new generalization error analysis for the Decentralized Stochastic Gradient Descent (D-SGD) algorithm based on algorithmic stability.

Generalization Bounds

Collaborative Algorithms for Online Personalized Mean Estimation

1 code implementation24 Aug 2022 Mahsa Asadi, Aurélien Bellet, Odalric-Ambrym Maillard, Marc Tommasi

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.

Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data

no code implementations9 Apr 2022 Batiste Le Bars, Aurélien Bellet, Marc Tommasi, Erick Lavoie, Anne-Marie Kermarrec

One of the key challenges in decentralized and federated learning is to design algorithms that efficiently deal with highly heterogeneous data distributions across agents.

Federated Learning

Differentially Private Speaker Anonymization

no code implementations23 Feb 2022 Ali Shahin Shamsabadi, Brij Mohan Lal Srivastava, Aurélien Bellet, Nathalie Vauquier, Emmanuel Vincent, Mohamed Maouche, Marc Tommasi, Nicolas Papernot

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.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition

no code implementations7 Nov 2021 Salima Mdhaffar, Jean-François Bonastre, Marc Tommasi, Natalia Tomashenko, Yannick Estève

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.

Speaker Verification speech-recognition +1

Privacy attacks for automatic speech recognition acoustic models in a federated learning framework

no code implementations6 Nov 2021 Natalia Tomashenko, Salima Mdhaffar, Marc Tommasi, Yannick Estève, Jean-François Bonastre

This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Differentially Private Coordinate Descent for Composite Empirical Risk Minimization

no code implementations22 Oct 2021 Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi

In this paper, we propose Differentially Private proximal Coordinate Descent (DP-CD), a new method to solve composite DP-ERM problems.

Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?

no code implementations12 Nov 2019 Brij Mohan Lal Srivastava, Aurélien Bellet, Marc Tommasi, Emmanuel Vincent

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.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs

1 code implementation24 Jan 2019 Valentina Zantedeschi, Aurélien Bellet, Marc Tommasi

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.

Personalized and Private Peer-to-Peer Machine Learning

no code implementations23 May 2017 Aurélien Bellet, Rachid Guerraoui, Mahsa Taziki, Marc Tommasi

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.

BIG-bench Machine Learning

Decentralized Collaborative Learning of Personalized Models over Networks

no code implementations17 Oct 2016 Paul Vanhaesebrouck, Aurélien Bellet, Marc Tommasi

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.

Fiedler Random Fields: A Large-Scale Spectral Approach to Statistical Network Modeling

no code implementations NeurIPS 2012 Antonino Freno, Mikaela Keller, Marc Tommasi

Statistical models for networks have been typically committed to strong prior assumptions concerning the form of the modeled distributions.

Cannot find the paper you are looking for? You can Submit a new open access paper.