Mila > Team > Ioannis Mitliagkas

Ioannis Mitliagkas

Core Academic Member
Ioannis Mitliagkas
Assistant Professor, Université de Montréal, Canada CIFAR AI Chair

Ioannis Mitliagkas is an assistant professor in the Department of Computer Science and Operations Research (DIRO) at the University of Montreal. Before that, he was a Postdoctoral Scholar with the Department of Statistics and Computer Science at Stanford University. He obtained his Ph.D. from the Department of Electrical and Computer Engineering at the University of Texas at Austin. His research focuses on broad-scale statistical learning and inference problems, focusing on efficient broad-scale and distributed algorithms, and the tight theoretical and data-dependent guarantees and tuning complex systems.His recent work includes understanding and optimizing the scanning used in Gibbs sampling for inference, as well as understanding the interaction between optimization and the dynamics of large-scale learning systems.

Publications

2021-12

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Kartik Ahuja, Ethan Caballero, Dinghuai Zhang, Jean-Christophe Gagnon-Audet, Yoshua Bengio, Ioannis Mitliagkas and Irina Rish
NEURIPS 2021
(2021-12-06)
papers.nips.ccPDF
Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
Nicolas Loizou, Hugo Berard, Gauthier Gidel, Ioannis Mitliagkas and Simon Lacoste-Julien

2021-10

Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize
Ryan D'Orazio, Nicolas Loizou, Issam H. Laradji and Ioannis Mitliagkas
arXiv preprint arXiv:2110.15412
(2021-10-28)
dblp.uni-trier.dePDF
Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks.
Manuela Girotti, Ioannis Mitliagkas and Gauthier Gidel
arXiv preprint arXiv:2110.10815
(2021-10-20)
ui.adsabs.harvard.eduPDF

2021-09

Gotta Go Fast with Score-Based Generative Models
Alexia Jolicoeur-Martineau, Ke Li, Rémi Piché-Taillefer, Tal Kachman and Ioannis Mitliagkas
The Symbiosis of Deep Learning and Differential Equations
(2021-09-27)
openreview.net

2021-06

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Kartik Ahuja, Ethan Caballero, Dinghuai Zhang, Yoshua Bengio, Ioannis Mitliagkas and Irina Rish
arXiv: Learning
(2021-06-11)
ui.adsabs.harvard.eduPDF

2021-05

Gotta Go Fast When Generating Data with Score-Based Models.
Alexia Jolicoeur-Martineau, Ke Li, Rémi Piché-Taillefer, Tal Kachman and Ioannis Mitliagkas
arXiv: Learning
(2021-05-28)
ui.adsabs.harvard.eduPDF
Gradient penalty from a maximum margin perspective
Alexia Jolicoeur-Martineau and Ioannis Mitliagkas
arxiv:cs.LG
(2021-05-04)
openreview.netPDF
Adversarial score matching and improved sampling for image generation
Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Ioannis Mitliagkas and Remi Tachet des Combes
ICLR 2021
(2021-05-03)
www.microsoft.comPDF

2020-12

A Study of Condition Numbers for First-Order Optimization. (arXiv:2012.05782v1 [cs.LG])
Charles Guille-Escuret, Baptiste Goujaud, Manuela Girotti and Ioannis Mitliagkas
arXiv Computer Science
(2020-12-11)

2020-09

Adversarial score matching and improved sampling for image generation
Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Rémi Tachet des Combes and Ioannis Mitliagkas
arXiv preprint arXiv:2009.05475
(2020-09-11)
ui.adsabs.harvard.eduPDF

2020-07

Linear Lower Bounds and Conditioning of Differentiable Games
Adam Ibrahim, Waïss Azizian, Gauthier Gidel and Ioannis Mitliagkas

2020-06

A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games.
AISTATS 2020
(2020-06-03)
proceedings.mlr.pressPDF
Accelerating Smooth Games by Manipulating Spectral Shapes.
Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien and Gauthier Gidel

2020-01

A Study of Condition Numbers for First-Order Optimization.
Charles Guille-Escuret, Baptiste Goujaud, Manuela Girotti and Ioannis Mitliagkas

2019-11

Generalizing to unseen domains via distribution matching
Isabela Albuquerque, João Monteiro, Mohammad Darvishi, Tiago H. Falk and Ioannis Mitliagkas
arXiv preprint arXiv:1911.00804
(2019-11-03)
ui.adsabs.harvard.eduPDF
Adversarial target-invariant representation learning for domain generalization
Isabela Albuquerque, João Monteiro, Mohammad Darvishi, Tiago H. Falk and Ioannis Mitliagkas
(venue unknown)
(2019-11-03)
onikle.com

2019-10

Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs
Alexia Jolicoeur-Martineau and Ioannis Mitliagkas
arXiv preprint arXiv:1910.06922
(2019-10-15)
dblp.uni-trier.dePDF

2019-06

Lower Bounds and Conditioning of Differentiable Games.
Adam Ibrahim, Waïss Azizian, Gauthier Gidel and Ioannis Mitliagkas
(venue unknown)
(2019-06-17)
dblp.uni-trier.dePDF
A Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Games
Waïss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien and Gauthier Gidel
arXiv: Learning
(2019-06-13)
arxiv.org
A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games.
(venue unknown)
(2019-06-13)
dblp.uni-trier.dePDF

2019-05

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Alex Lamb, Jonathan Binas, Anirudh Goyal, Sandeep Subramanian, Ioannis Mitliagkas, Denis Kazakov, Yoshua Bengio and Michael C. Mozer
arXiv preprint arXiv:1905.11382
(2019-05-26)
ui.adsabs.harvard.eduPDF
Multi-objective training of Generative Adversarial Networks with multiple discriminators
Isabela Albuquerque, João Monteiro, Thang Doan, Breandan Considine, Tiago H. Falk and Ioannis Mitliagkas
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Alex Lamb, Jonathan Binas, Anirudh Goyal, Sandeep Subramanian, Ioannis Mitliagkas, Yoshua Bengio and Michael Mozer
ICML 2019
(2019-05-24)
proceedings.mlr.pressPDF
Manifold Mixup: Better Representations by Interpolating Hidden States
Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz and Yoshua Bengio
ICML 2019
(2019-05-24)
proceedings.mlr.pressPDF
In Support of Over-Parametrization in Deep Reinforcement Learning: an Empirical Study
Brady Neal and Ioannis Mitliagkas
(venue unknown)
(2019-05-17)
openreview.net

2019-04

Negative Momentum for Improved Game Dynamics
Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Gabriel Huang, Rémi Le Priol, Simon Lacoste-Julien and Ioannis Mitliagkas
AISTATS 2019
(2019-04-11)
proceedings.mlr.pressPDF

2019-03

MLSys: The New Frontier of Machine Learning Systems
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons... (49 more)
arXiv preprint arXiv:1904.03257
(2019-03-29)
ui.adsabs.harvard.eduPDF

2019-01

Reducing the variance in online optimization by transporting past gradients
Sébastien M. R. Arnold, Pierre-Antoine Manzagol, Reza Babanezhad, Ioannis Mitliagkas and Nicolas Le Roux

2018-10

A Modern Take on the Bias-Variance Tradeoff in Neural Networks
Brady Neal, Sarthak Mittal, Aristide Baratin, Vinayak Tantia, Matthew Scicluna, Simon Lacoste-Julien and Ioannis Mitliagkas
arXiv preprint arXiv:1810.08591
(2018-10-19)
ui.adsabs.harvard.eduPDF

2018-09

Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations
Alex Lamb, Jonathan Binas, Anirudh Goyal, Dmitriy Serdyuk, Sandeep Subramanian, Ioannis Mitliagkas and Yoshua Bengio
arXiv preprint arXiv:1804.02485
(2018-09-27)
ui.adsabs.harvard.eduPDF
h-detach: Modifying the LSTM Gradient Towards Better Optimization
Devansh Arpit, Bhargav Kanuparthi, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas and Yoshua Bengio
Manifold Mixup: Learning Better Representations by Interpolating Hidden States
Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Aaron Courville, Ioannis Mitliagkas and Yoshua Bengio
arXiv Machine Learning (Statistics)
(2018-09-27)
openreview.netPDF

2018-07

Negative Momentum for Improved Game Dynamics
Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Remi Lepriol, Gabriel Huang, Simon Lacoste-Julien and Ioannis Mitliagkas
arXiv preprint arXiv:1807.04740
(2018-07-12)
ui.adsabs.harvard.eduPDF

2018-06

Manifold Mixup: Better Representations by Interpolating Hidden States.
Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, Aaron Courville, David Lopez-Paz and Yoshua Bengio
arXiv: Machine Learning
(2018-06-13)
arxiv.orgPDF
Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer.
Vikas Verma, Alex Lamb, Christopher Beckham, Aaron C. Courville, Ioannis Mitliagkas and Yoshua Bengio
(venue unknown)
(2018-06-13)
dblp.uni-trier.dePDF

2018-03

Accelerated Stochastic Power Iteration
Peng Xu, Bryan D. He, Christopher De Sa, Ioannis Mitliagkas and Christopher Ré
AISTATS 2018
(2018-03-31)
proceedings.mlr.pressPDF

2018-02

YellowFin and the Art of Momentum Tuning
Jian Zhang, Ioannis Mitliagkas and Christopher Re
MLSys
(2018-02-15)
proceedings.mlsys.orgPDF
Learning Generative Models with Locally Disentangled Latent Factors
Brady Neal, Alex Lamb, Sherjil Ozair, Devon Hjelm, Aaron Courville, Yoshua Bengio and Ioannis Mitliagkas
(venue unknown)
(2018-02-15)
openreview.netPDF

2018-01

Learning Representations and Generative Models for 3D Point Clouds.
Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas and Leonidas J. Guibas

Publications collected and formatted using Paperoni