Papers

Most of my publications can be found on my Google scholar profile, below they are classified by themes.

Sampling/Optimization over measures

  • C. Chazal, A. Korba, F. Bach. Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence. Advances in Neural Information Processing Systems (NeurIPS), 2024.
    [paper]
  • C. Bonet, T. Uscidda, A. David, P-C. Aubin-Frankowski, A. Korba. Mirror and Preconditioned Gradient Descent in Wasserstein Space. Advances in Neural Information Processing Systems (NeurIPS), 2024.
    [paper]
  • P. Marion, A. Korba, P. Bartlett, M. Blondel, V. De Bortoli, A. Doucet, F. Llinares-López, C. Paquette, Quentin Berthet. Implicit Diffusion: Efficient Optimization through Stochastic Sampling. Submitted, 2024.
    [paper]
  • T. Huix, A. Korba, A. Durmus, E. Moulines. Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians. International Conference of Machine Learning (ICML), 2024.
    [paper]
  • N. Chopin, F. Crucinio , A. Korba. A connection between Tempering and Entropic Mirror Descent. International Conference of Machine Learning (ICML), 2024.
    [paper]
  • L. Li, Q. Liu, A. Korba, M. Yurochkin, J. Solomon. Sampling with Mollified Interaction Energy Descent. International Conference on Learning Representations (ICLR), 2023.
    [paper]
  • L. Xu, A. Korba, D. Slepcev. Accurate Quantization of Measures via Interacting Particle-based Optimization. International Conference of Machine Learning (ICML), 2022.
    [paper]
  • T. Huix, S. Majewski, A. Durmus, E. Moulines, A. Korba. Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study. Submitted, 2022.
    [paper]
  • P-C. Aubin-Frankowski, A. Korba, F. Léger. Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM. Advances in Neural Information Processing Systems (NeurIPS), 2022.
    [paper]
  • A. Korba, F. Portier. Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff. In Artificial Intelligence and Statistics (AISTATS), 2022. Accepted for Oral presentation (top 10%).
    [paper][poster][slides][video]
  • A. Korba, P.-C. Aubin-Frankowski, S. Majewski, P. Ablin. Kernel Stein Discrepancy Descent. In International Conference of Machine Learning (ICML) 2021. Accepted for Long Oral presentation (top 15%).
    [paper][poster][slides][video]
  • A. Korba, A. Salim, M. Arbel, G. Luise, A. Gretton. A Non-Asymptotic Analysis for Stein Variational Gradient Descent. In Advances in Neural Information Processing Systems (NeurIPS) 2020.
    [paper][poster]
  • A. Salim, A. Korba, G. Luise. Wasserstein Proximal Gradient. In Advances in Neural Information Processing Systems (NeurIPS) 2020.
    [paper][poster]
  • M. Arbel, A. Korba, A. Salim , A.Gretton. Maximum Mean Discrepancy Gradient flow. In Advances in Neural Information Processing Systems (NeurIPS) 2019.
    [paper][code]

Off-Policy Learning and Evaluation

  • I. Aouali, V-E. Brunel, D. Rohde, A. Korba. Bayesian Off-Policy Evaluation and Learning for Large Action Spaces . Submitted, 2024.
    [paper]
  • I. Aouali, V-E. Brunel, D. Rohde, A. Korba. Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling. Uncertainty in Artificial Intelligence, 2024.
    [paper]
  • I. Aouali, V-E. Brunel, D. Rohde, A. Korba. Exponential Smoothing for Off-Policy Learning. In International Conference of Machine Learning (ICML) 2023.
    [paper][supplementary material]

Causality

  • A. Mastouri, Y. Zhu, L. Gultchin, A. Korba, R. Silva, M. J. Kusner, A. Gretton, K. Muandet. Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction. In International Conference of Machine Learning (ICML) 2021.
    [paper]

Ranking

During my PhD, I studied how to analyze preference data in the form of total orders/permutations or pairwise comparisons, and how to handle statistical problems related to such data, including ranking aggregation, distribution estimation, and prediction. Here is the final version of the manuscript and the slides; and below a list of publications.

  • M. Achab (*), A. Korba (*), S. Clémençon. Dimensionality Reduction for (Bucket) Ranking: A Mass Transportation Approach. In Algorithmic Learning Theory (ALT) 2019. (* :) equal contribution
    [paper][code]
  • A. Korba, A. Garcia, F. D'Alché-Buc. A Structured Prediction Approach for Label Ranking. In
    Advances in Neural Information Processing Systems (NeurIPS) 2018.
    [paper][code][poster]
  • S. Clémençon, A. Korba. On Aggregation in Ranking Median Regression. In European Symposium on Artificial Neural Networks (ESANN) 2018.
    [paper]
  • S. Clémençon, A. Korba, E. Sibony. Ranking Median Regression: Learning to Order through Local Consensus. In Algorithmic Learning Theory (ALT) 2018.
    [Arxiv long version ] [ALT short version]
  • A. Korba, S. Clémençon, E. Sibony. A Learning Theory of Ranking Aggregation. In Artificial Intelligence and Statistics (AISTATS) 2017.
    [paper] [poster]
  • Y. Jiao, A. Korba, E. Sibony. Controlling the distance to a Kemeny consensus without computing it. In International Conference on Machine Learning (ICML) 2016.
    [paper] [poster]