Michal Valko

Michal Valko, machine learning scientist in SequeL team at Inria

  machine learning, minimal feedback, online/sequential learning, graph-based methods, semi-supervised learning

News

News: new Two papers to ICML 2017. See you in Australia!
News: new I give an invited talk on June 14th, 2017 at Journées Scientifiques Inria 2017 in Nice, France.
News: new I give an invited talk on March 22nd, 2017 for Universität Potsdam at Amazon in Berlin.
News: new Spectral Bandits accepted for publication to JMLR.
News: Two papers to AISTATS 2017. See you in Florida!
News: I give an invited talk on December 21st, 2016 at Textkernel talks series in Amsterdam.
News: Starting October 3rd, 2016, I will be teaching a graduate course on Graphs in Machine Learning in MVA Master at ENS Cachan!
News: I gave an invited talk on September 22nd, 2016 at Theoretical Computer Science seminar in Bratislava.
News: My habilitation thesis, Bandits on graphs and structures, is now online.
News: TrailBlazer paper on sample-efficient Monte-Carlo planning accepted as oral presentation to NIPS 2016!

older news

Bio

Michal is a junior scientist in SequeL team at Inria Lille - Nord Europe, France, lead by Philippe Preux and Rémi Munos. He also teaches the course Graphs in Machine Learning at l'ENS Cachan. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. This means 1) reducing the “intelligence” that humans need to input into the system and 2) minimising the data that humans need spend inspecting, classifying, or “tuning” the algorithms. Another important feature of machine learning algorithms should be the ability to adapt to changing environments. That is why he is working in domains that are able to deal with minimal feedback, such as bandit algorithms, semi-supervised learning, and anomaly detection. Most recently he has worked on sequential algorithms with structured decisions where exploiting the structure can lead to provably faster learning. In the past the common thread of Michal's work has been adaptive graph-based learning and its application to the real world applications such as recommender systems, medical error detection, and face recognition. His industrial collaborators include Adobe, Intel, Technicolor, and Microsoft Research. He received his PhD in 2011 from University of Pittsburgh under the supervision of Miloš Hauskrecht and after was a postdoc of Rémi Munos.

Collaborative Projects

previous projects

Students

  • Tomáš Kocák, 2013 - 2016, PhD student, with Rémi Munos
  • Guillaume Gautier, 2016, master student, École Normale Supérieure, Cachan, with Rémi Bardenet ↝ Inria/CNRS
  • Andrea Locatelli, 2015-2016, ENSAM/ENS Cachan, with Alexandra Carpentier ↝ Universität Potsdam
  • Akram Erraqabi, 2015, master student, École Polytechnique, Paris ↝ Université de Montréal
  • Souhail Toumdi, 2015 - 2016, master student, École Centrale de Lille, with Rémi Bardenet ↝ ENS Cachan/MVA
  • Akram Erraqabi, 2015, master student, École Polytechnique, Paris ↝ Université de Montréal
  • Mastane Achab, 2015, master student, École Polytechnique, Paris, with Gergely Neu ↝ l'ENS Cachan Paris ↝ Télécom ParisTech
  • Jean-Bastien Grill, 2014, master student, École Normale Supérieure, Paris, with Rémi Munos ↝ Inria
  • Alexandre Dubus, 2012-2013, master student, Université Lille1 - Sciences et Technologies ↝ Inria
  • Karim Jedda, 2012-2013, master student, École Centrale de Lille ↝ ProSiebenSat.1
  • Alexis Wehrli, 2012-2013, master student, École Centrale de Lille ↝ ERDF

Selected Publications

  • Daniele Calandriello, Alessandro Lazaric, Michal Valko: Second-order kernel online convex optimization with adaptive sketching, in International Conference on Machine Learning (ICML 2017) bibtex abstract abstract
  • Guillaume Gautier, Rémi Bardenet, Michal Valko: Zonotope hit-and-run for efficient sampling from projection DPPs, in International Conference on Machine Learning (ICML 2017) bibtex abstract abstract
  • Daniele Calandriello, Alessandro Lazaric, Michal Valko: Distributed sequential sampling for kernel matrix approximation, in International Conference on Artificial Intelligence and Statistics (AISTATS 2017) bibtex abstract abstract talk poster
  • Akram Erraqabi, Alessandro Lazaric, Michal Valko, Emma Brunskill, Yu-En Liu: Trading off rewards and errors in multi-armed bandits, in International Conference on Artificial Intelligence and Statistics (AISTATS 2017) bibtex abstract abstract poster,
  • Tomáš Kocák, Michal Valko, Rémi Munos, Branislav Kveton, Shipra Agrawal: Spectral Bandits, accepted for publication to Journal of Machine Learning Research (JMLR 2017)
  • Branislav Kveton, Zheng Wen, Azin Ashkan, Michal Valko: Learning to Act Greedily: Polymatroid Semi-Bandits, accepted for publication to Journal of Machine Learning Research (JMLR 2017) bibtex abstract abstract arXiv preprint
  • Michal Valko: Bandits on graphs and structures, habilitation thesis, École normale supérieure de Cachan (ENS Cachan 2016) bibtex abstract abstract
  • Jean-Bastien Grill, Michal Valko, Rémi Munos: Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning, in Neural Information Processing Systems (NIPS 2016) bibtex abstract abstract talk poster [full oral presentation - 1.8% acceptance rate]
  • Akram Erraqabi, Michal Valko, Alexandra Carpentier, Odalric-Ambrym Maillard: Pliable rejection sampling, in International Conference on Machine Learning (ICML 2016) bibtex abstract abstract talk poster
  • Mohammad Ghavamzadeh, Yaakov Engel, Michal Valko: Bayesian policy gradient and actor-critic algorithms, Journal of Machine Learning Research (JMLR 2016) bibtex abstract abstract code
  • Tomáš Kocák, Gergely Neu, Michal Valko: Online learning with noisy side observations, in International Conference on Artificial Intelligence and Statistics (AISTATS 2016) bibtex abstract abstract talk poster [full oral presentation - 6% acceptance rate]
  • Alexandra Carpentier, Michal Valko: Revealing graph bandits for maximizing local influence, in International Conference on Artificial Intelligence and Statistics (AISTATS 2016) bibtex abstract abstract poster
  • Jean-Bastien Grill, Michal Valko, Rémi Munos: Black-box optimization of noisy functions with unknown smoothness, in Neural Information Processing Systems (NIPS 2015) bibtex abstract abstract code, code in R poster
  • Alexandra Carpentier, Michal Valko: Simple regret for infinitely many armed bandits, in International Conference on Machine Learning (ICML 2015) bibtex abstract abstract talk poster arXiv
  • Tomáš Kocák, Gergely Neu, Michal Valko, Rémi Munos: Efficient Learning by Implicit Exploration in Bandit Problems with Side Observations, in Neural Information Processing Systems (NIPS 2014) bibtex abstract abstracttalk poster
  • Alexandra Carpentier, Michal Valko: Extreme Bandits, in Neural Information Processing Systems (NIPS 2014) bibtex abstract abstractposter
  • Gergely Neu, Michal Valko: Online Combinatorial Optimization with Stochastic Decision Sets and Adversarial Losses, in Neural Information Processing Systems (NIPS 2014) bibtex abstract abstracttalk poster
  • Michal Valko, Rémi Munos, Branislav Kveton, Tomáš Kocák: Spectral Bandits for Smooth Graph Functions, in International Conference on Machine Learning (ICML 2014) bibtex abstract abstractslides poster
  • Michal Valko, Branislav Kveton, Ling Huang, Daniel Ting: Online Semi-Supervised Learning on Quantized Graphs in Uncertainty in Artificial Intelligence (UAI 2010) bibtex abstract abstract Video: Adaptation, Video: OfficeSpace, spotlight poster
  • Milos Hauskrecht, Michal Valko, Shyam Visweswaram, Iyad Batal, Gilles Clermont, Gregory Cooper: Conditional Outlier Detection for Clinical Alerting in Annual American Medical Informatics Association conference (AMIA 2010) bibtex abstract abstract [Homer Warner Best Paper Award]

Contact

  • Inria Lille - Nord Europe, equipe SequeL (bureau: A05)
  • Parc Scientifique de la Haute Borne
  • 40 avenue Halley
  • 59650 Villeneuve d'Ascq, France
  • office phone: +33 3 59 57 7801


13-May-2017