2022 - 2023

Past Talks

[See Calendar in the frontpage for the updated information]

• Date : 02 August, 2023
  Speaker :  Odalric-Ambrym Maillard (Inria Lille)
  Title : "Information-based Regret Minimization in Markov Decision Processes"

• Date : 26 July, 2023
  Speaker :  Olivier Catoni (CNRS)

• Date : 20 June, 2023
  Speaker :  Amartya Sanyal (MPI Tubingen)
  Title : "From Theory to Practice: Making Semi-Private Learning Effective for Real-World Applications"

• Date : 19 June, 2023
  Speaker :  Tim van Erven (UvA)
  Title : "Robust Online Convex Optimization in the Presence of Outliers"

• Date : 12 April, 2023
  Speaker :  Julian Zimmert (Google Research)
  Title : "A Blackbox Approach to Best of Both Worlds in Bandits and Beyond"

• Date : 27 February, 2023
  Speaker :  Amartya Sanyal (MPI Tubingen)
  Title : "Trustworthy Machine Learning under statistical limitations"

• Date : 08 February, 2023
  Speaker :  Mladen Kolar (University of Chicago, Booth School of Business)
  Title : "An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians"

• Date : 27 January, 2023
  Speaker :  Gabor Lugosi (Pompeu Fabra University)
  Title : "Learning the structure of graphical models by covariance queries"

• Date : 26 January, 2023
  Speaker :  Emilie Kaufmann (Inria Lille)
  Title : "Non-parametric exploration in multi-armed bandits"

• Date : 07 November, 2022
  Speaker : Vladimir Dvorkin (MIT)
  Title : "Differential Privacy Meets Stochastic Programming"

• Date : 24 October, 2022
  Speaker : Aviv Rosenberg (Sibylla)
  Title : "Delay and Cooperation in Reinforcement Learning"

• Date : 10 October, 2022
  Speaker : Yi-Shan Wu (DIKU)
  Title : "Split-kl and PAC-Bayes-split-kl Inequalities"

• Date : 03 October, 2022
  Speaker : Saeed Masoudian (DIKU)
  Title : "A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback"

• Date : 05 September, 2022
  Speaker : Bruno Loureiro (EPFL)
  Title : "Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks"

• Date : 19 August, 2022
  Speaker : Stefan Bauer (KTH)
  Title : "Towards Learning Causal Representations & Interactive Benchmarks"