Mila > Mila researchers contributed ten publications at the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS)
2 Sep 2020

Mila researchers contributed ten publications at the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS)

/

While COVID-19 has forced conferences and events around the world to go virtual, members of the Mila ecosystem continue to successfully contribute their research and expertise in the field. We are proud to announce that ten publications were accepted and presented at the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), which was held online from August 26-28.

The AISTATS conference is an interdisciplinary gathering of researchers stemming from the fields of computer science, artificial intelligence, machine learning and statistics. The scope of accepted papers from Mila members encompassed areas of machine learning, optimization and control, and data structures and algorithms. Please see below for the complete list of accepted publications:

  1. Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
    Si Yi Meng, Sharan Vaswani, Issam Hadj Laradji, Mark Schmidt, Simon Lacoste-Julien
    https://arxiv.org/abs/1910.04920
  2. Accelerating Smooth Games by Manipulating Spectral Shapes
    Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel
    https://arxiv.org/abs/2001.00602
  3. Old Dog Learns New Tricks: Randomized UCB for Bandit Problems
    Sharan Vaswani, Abbas Mehrabian, Audrey Durand, Branislav Kveton
    https://arxiv.org/abs/1910.04928
  4. GAIT: A Geometric Approach to Information Theory
    Jose D Gallego Posada, Ankit Vani, Max Schwarzer, Simon Lacoste-Julien
    https://arxiv.org/abs/1906.08325
  5. Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
    Tianyu Li, Bogdan Mazoure, Doina Precup, Guillaume Rabusseau
    https://arxiv.org/abs/1911.05010
  6. A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games
    Waïss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel
    https://arxiv.org/abs/1906.05945
  7. Tensorized Random Projections
    Beheshteh T Rakhshan, Guillaume Rabusseau
    https://arxiv.org/abs/2003.05101
  8. On the interplay between noise and curvature and its effect on optimization and generalization
    Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer, Pierre-Antoine Manzagol, Yoshua Bengio, Nicolas Le Roux
    https://arxiv.org/abs/1906.07774
  9. Stochastic Neural Network with Kronecker Flow
    Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron Courville
    https://arxiv.org/abs/1906.04282
  10. Value Preserving State-Action Abstractions
    David Abel, Nathan Umbanhowar, Khimya Khetarpal, Dilip Arumugam, Doina Precup, Michael L. Littman
    https://david-abel.github.io/papers/aistats2020_vpsa-full.pdf

AISTATS 2021 will be tentatively held next year in San Diego, California, from April 13-15.

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }