Workshop on Functional Inference and Machine Intelligence

The Workshop on Functional Inference and Machine Intelligence (FIMI) is an international workshop on machine learning and statistics, with a particular focus on theoretical and algorithmic aspects. It consists of invited talks and poster sessions, with topics including (but not limited):

  • Kernel Methods and Gaussian Processes in Machine Learning
  • Mathematical Analysis of Deep Learning
  • Probabilistic Machine Learning

The workshop will be held at EURECOM, Sophia Antipolis, France, from 17-19 February 2020.

List of talks

Title Speaker
Kernel tests of goodness-of-fit using Stein’s method Arthur Gretton (University College London)
Simulator Calibration under Covariate Shift with Kernels Motonobu Kanagawa (EURECOM)
Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings Dino Sejdinovic (University of Oxford)
Learning Conditional Moment Restrictions with Kernels Krikamol Muandet (MPI for Intelligent Systems)
Learning Invariances using the Marginal Likelihood Mark van der Wilk (Imperial College London)
Fast Discovery of Pairwise Interactions in High Dimensions using Bayes Tamara Broderick (Massachusetts Institute of Technology)
Random Feature Expansions for Deep Gaussian Processes Maurizio Filippone (EURECOM)
Fair and Explainable algorithmic decision making Isabel Valera (MPI for Intelligent Systems)
Data interpolation and statistical optimality Alexandre Tsybakov (CREST)
Statistical inference on M-estimators by high-dimensional Gaussian approximation Masaaki Imaizumi (The Institute of Statistical Mathematics)
Fast learning rate of neural tangent kernel learning and nonconvex optimization by infinite dimensional Langevin dynamics in RKHS Taiji Suzuki (The University of Tokyo)
Kernelized Wasserstein Natural Gradient Michael Arbel (University College London)
Smoothness and Stability in Learning GANs Kenji Fukumizu (The Institute of Statistical Mathematics / Preferred Networks)

The full program is available on the FIMI website.