Web page of Jamal Atif

• Trustworthy machine learning: robustness to adversarial attacks, privacy-preserving models
• Explainable AI
• Structured and compact representations
• Health-oriented applications

Please check out the MILES topics for a complete description

• Université Paris-Dauphine, PSL Research University, CNRS, UMR[7243] LAMSADE, 75016 Paris, France.

• e-mail: jamal.atif (at) dauphine.fr
• phone: +33 1 44 05 44 09
• postal address:
  • Place du Maréchal de Lattre de Tassigny, 75 775 Paris Cedex 16, France.
  • Direction: here

• Ikko Yamane, Florian Yger, Jamal Atif, Masashi Sugiyama Uplift Modeling from Separate Labels. NIPS 2018 Category: Machine Learning.

• Rafael Pinot, Anne Morvan, Florian Yger, Cedric Gouy-Pailler, Jamal Atif. Graph-based Clustering under Differential Privacy. UAI 2018 Category: Machine Learning.

• Marc Aiguier, Jamal Atif, Isabelle Bloch, Céline Hudelot. Belief Revision, Minimal Change and Relaxation: A General Framework based on Satisfaction Systems, and Applications to Description Logics.arXiv preprint arXiv:1502.02298. to appear in Artificial Intelligence Journal. Category: Artificial Intelligence, Logics, Knowledge representation and Reasoning.

• Anne Morvan, Antoine Souloumiac, Cédric Gouy-Pailler, Jamal Atif. Streaming Binary Sketching based on Subspace Tracking and Diagonal Uniformization. IEEE ICASSP 2018 Category: Machine Learning.

• Fabien Labernia, Bruno Zanuttini, Brice Mayag, Florian Yger, and Jamal Atif. Online learning of acyclic conditional preference networks from noisy data. IEEE ICDM 2017. Category: Machine Learning.

• Fabien Labernia, Florian Yger, Brice Mayag, and Jamal Atif. Query-based learning of acyclic conditional preference networks from contradictory preferences. EURO Journal on Decision Processes, 2017. Category: Machine Learning

• Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Francois Fagan, Cedric Gouy-Pailler, Anne Morvan, Nouri Sakr, Tamas Sarlos, Jamal Atif. Structured adaptive and random spinners for fast machine learning computations. arXiv preprint arXiv:1610.06209, 2016. Work with Google NYC. Accepted at AISTAT 2017. Category: Machine Learning

• Yoann Isaac, Quentin Barthélemy, Cédric Gouy-Pailler, Michèle Sebag, Jamal Atif. Multi-dimensional signal approximation with sparse structured priors using split Bregman iterations, Signal Processing, 2017, vol. 130, p. 389-402. Category: Machine Learning

• Timothée Evain, Xavier Ripoche, J. Atif et Isabelle Bloch. Semi-automatic teeth segmentation in cone-beam computed tomography by graph-cut with statistical shape prior. IEEE International Symposium on Biomedical Imaging, Melbourne, Australia, 2017. Category: Machine Learning, image processing, medical imaging

• Marc Aiguier, Jamal Atif, Isabelle Bloch, Céline Hudelot. A finite basis theorem for the description logic ALC. arXiv preprint arXiv:1502.07634, 2016. Submitted to Information Processing Letters. Category: Artificial Intelligence, Logics

• Isabelle Bloch and Jamal Atif. Defining and computing Hausdorff distances between distributions on the real line and on the circle: link between optimal transport and morphological dilations, Mathematical Morphology-Theory and Applications, 2016, vol. 1, no 1, p. 79-99.

- Tutorial at IJCAI 2016