Skip to content
Miles - Machine Intellligence and Learning Systems
Contact: alexandre.allauzen@dauphine.psl.eu
  • About MILES
  • News
  • People
  • Publications
  • Open positions
  • Collaborations

New MILES paper in TMLR

Posted on 2025-01-112025-04-08 by croyer

The paper Differentially Private Gradient Flow based on the Sliced Wasserstein Distance, authored by Ilana Sebag, Muni Sreenivas Pydi, Jean-Yves Franceschi (Criteo AI Lab), Alain Rakotomamonjy (Criteo AI Lab), Mike Gartrell (Sigma Nova), Jamal Atif and Alexandre Allauzen, has been accepted in Transactions on Machine Learning Research.

Congratulations!

Posted in Non classé
Post navigation
MILES@EMNLP 2024 →
← New MILES paper in TMLR

Recent papers

  • A characterization of positive spanning sets with ties to strongly edge-connected digraphs
  • Lattice Climber Attack: Adversarial attacks for randomized mixtures of classifiers
  • Gathering and Exploiting Higher-Order Information when Training Large Structured Models

Recent posts

  • MILES@ICML 2025
  • MILES@AISTATS 2025
  • MILES@ICLR 2025
  • New MILES paper in TMLR

Latest publications

  • A characterization of positive spanning sets with ties to strongly edge-connected digraphs
  • Lattice Climber Attack: Adversarial attacks for randomized mixtures of classifiers
  • Gathering and Exploiting Higher-Order Information when Training Large Structured Models
  • On the MIA Vulnerability Gap Between Private GANs and Diffusion Models
  • What Makes Large Language Models Reason In (Multi-Turn) Code Generation?
  • Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory
  • Gaussian Pre-Activations in Neural Networks: Myth or Reality?
Theme by Out the Box
Project-team Miles, LAMSADE, Université Paris Dauphine. Place du Maréchal de Lattre de Tassigny, 75 775 PARIS CEDEX 16, FRANCE