2020 - 2021

Past Talks

  • Date : 21 June, 2021
    Speaker
    : Aryeh Kontorovich (Ben-Gurion University)
    Title : "
    Functions with average smoothness: structure, algorithms, and learning" [paper]

  • Date : 14 June, 2021
    Speaker
    : Francesco Orabona (Boston University, Boston, MA)
    Title : "
    Parameter-free Stochastic Optimization of Variationally Coherent Functions" [paper]

  • Date : 7 June, 2021
    Speaker
    : Anders Jonsson (Universitat Pompeu Fabra)
    Title : "Planning in Markov Decision Processes with Gap-Dependent Sample Complexity" [
    paper]

  • Date : 10 May, 2021
    Speaker
    : Omar Rivasplata (University College London)
    Topic : "
    PAC-Bayes Analysis Beyond the Usual Bounds" [paper]

  • Date : 3 May, 2021
    Speaker : Yijie Zhang (University of Copenhagen)
    Topic : "On the Inconsistency of Bayesian Inference for Misspecified Neural Networks"
    [paper]

  • Date : 26 April, 2021
    Speaker : Yijie Zhang (University of Copenhagen)
    Topic : "Deep Coherent Exploration for Continuous Control"
    [paper]

  • Date : 19 April, 2021
    Speaker : Omar Darwiche Domingues (Inria Lille - Nord Europe)
    Topic : "A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces" [
    paper]

  • Date : 29 March, 2021
    Speaker : Mohammad Sadegh Talebi (University of Copenhagen)
    Topic : "Improved Exploration in Factored Average-Reward MDPs" [
    paper]

  • Date : 15 March, 2021
    Speaker : Nikita Zhivotovskiy (ETH, Zürich)
    Topic : "Distribution-Free Robust Linear Regression" [
    paper]

  • Date : 1 March, 2021
    Speaker : Saeed Masoudian (University of Copenhagen)
    Topic : "Improved Analysis of Robustness of the Tsallis-INF Algorithm to Adversarial Corruptions in Stochastic Multiarmed Bandits" [
    paper]

  • Date : 22 Feb, 2021
    Speaker : Chloé Rouyer (University of Copenhagen)
    Topic : "An Algorithm for Stochastic and Adversarial Bandits with Switching Costs" [
    paper]

  • Date : 15 Feb, 2021
    Speaker : Yi-Shan Wu (University of Copenhagen)
    Topic : "Prediction with Expert Advice with Branching Experts"