Papers

• Addressing bias in online selection with limited budget of comparisons
  Z. Benomar, E. Chzhen, N. Schreuder, V. Perchet
  Preprint 2023

• Fair learning with Wasserstein barycenters for non-decomposable performance measures
  S. Gaucher, N. Schreuder, E. Chzhen
  AISTATS 2023

• A minimax framework for quantifying risk-fairness trade-off in regression
  E. Chzhen, N. Schreuder
  Annals of Statistics 2022

• A gradient estimator via L1-randomization for online zero-order optimization with two point feedback
  A. Akhavan, E. Chzhen, M. Pontil, A. Tsybakov
  NeurIPS 2022 (spotlight, code)

• A unified approach to fair online learning via Blackwell approachability
  E. Chzhen, C. Giraud, G. Stoltz
  NeurIPS 2021 (spotlight)

• Set-valued classification -- overview via a unified framework
  E. Chzhen, C. Denis, M. Hebiri, T, Lorieul
  Preprint 2021

• Classification with abstention but without disparities
  N. Schreuder, E. Chzhen
  UAI 2021 (spotlight, code)

• Minimax semi-supervised set-valued approach to multi-class classification
  E. Chzhen, C. Denis, M. Hebiri
  Bernoulli 2021 (code)

• Optimal Rates for Nonparametric F-Score Binary Classification via Post-Processing
  E. Chzhen
  Mathematical Methods of Statistics 2021

• An example of prediction which complies with Demographic Parity and equalizes group-wise risks in the context of regression
  E. Chzhen, N. Schreuder
  AFCI at NeurIPS 2020

• Fair regression with wasserstein barycenters
  E. Chzhen, C. Denis, M. Hebiri, L. Oneto, M. Pontil
  NeurIPS 2020 (code)

• Fair Regression via Plug-in Estimator and Recalibration With Statistical Guarantees
  E. Chzhen, C. Denis, M. Hebiri, L. Oneto, M. Pontil
  NeurIPS 2020 (oral, code)

• Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
  E. Chzhen, C. Denis, M. Hebiri, L. Oneto, M. Pontil
  NeurIPS 2019

• On Lasso refitting strategies
  E. Chzhen, M. Hebiri, J. Salmon
  Bernoulli 2019

• Plug-in methods in classification
  E. Chzhen
  PhD manuscript 2019

• Classification of sparse binary vectors
  E. Chzhen
  Technical Report 2019

• On the benefits of output sparsity for multi-label classification
  E. Chzhen, C. Denis, M. Hebiri, J. Salmon
  Technical Report 2017