Obserwuj
Ioannis (Yannis) Mitliagkas
Ioannis (Yannis) Mitliagkas
Assistant Professor at Mila, University of Montréal
Zweryfikowany adres z iro.umontreal.ca - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Learning Representations and Generative Models for 3D Point Clouds
P Achlioptas, O Diamanti, I Mitliagkas, L Guibas
International Conference on Machine Learning, 2018
8032018
Manifold mixup: Better representations by interpolating hidden states
V Verma, A Lamb, C Beckham, A Najafi, I Mitliagkas, A Courville, ...
arXiv preprint arXiv:1806.05236, 2018
5802018
Manifold mixup: Better representations by interpolating hidden states
V Verma, A Lamb, C Beckham, A Najafi, I Mitliagkas, A Courville, ...
arXiv preprint arXiv:1806.05236, 2018
5802018
Memory limited, streaming PCA
I Mitliagkas, C Caramanis, P Jain
Advances in neural information processing systems 26, 2013
1682013
Negative momentum for improved game dynamics
G Gidel, RA Hemmat, M Pezeshki, G Huang, R Lepriol, S Lacoste-Julien, ...
Artificial Intelligence and Statistics, 2019
1412019
Asynchrony begets momentum, with an application to deep learning
I Mitliagkas, C Zhang, S Hadjis, C Ré
2016 54th Annual Allerton Conference on Communication, Control, and …, 2016
1402016
A modern take on the bias-variance tradeoff in neural networks
B Neal, S Mittal, A Baratin, V Tantia, M Scicluna, S Lacoste-Julien, ...
arXiv preprint arXiv:1810.08591, 2018
1222018
Yellowfin and the art of momentum tuning
J Zhang, I Mitliagkas
SysML, 2019
982019
Deep learning at 15pf: supervised and semi-supervised classification for scientific data
T Kurth, J Zhang, N Satish, E Racah, I Mitliagkas, MMA Patwary, T Malas, ...
Proceedings of the International Conference for High Performance Computing …, 2017
862017
Representation learning and adversarial generation of 3D point clouds
P Achlioptas, O Diamanti, I Mitliagkas, L Guibas
arXiv preprint arXiv:1707.02392, 2017
842017
Joint power and admission control for ad-hoc and cognitive underlay networks: Convex approximation and distributed implementation
I Mitliagkas, ND Sidiropoulos, A Swami
IEEE Transactions on Wireless Communications 10 (12), 4110-4121, 2011
832011
Parallel SGD: When does averaging help?
J Zhang, C De Sa, I Mitliagkas, C Ré
arXiv preprint arXiv:1606.07365, 2016
792016
Manifold mixup: Learning better representations by interpolating hidden states
V Verma, A Lamb, C Beckham, A Najafi, A Courville, I Mitliagkas, ...
75*2018
A tight and unified analysis of gradient-based methods for a whole spectrum of differentiable games
W Azizian, I Mitliagkas, S Lacoste-Julien, G Gidel
International Conference on Artificial Intelligence and Statistics, 2863-2873, 2020
672020
Generalizing to unseen domains via distribution matching
I Albuquerque, J Monteiro, M Darvishi, TH Falk, I Mitliagkas
arXiv preprint arXiv:1911.00804, 2019
67*2019
Omnivore: An optimizer for multi-device deep learning on cpus and gpus
S Hadjis, C Zhang, I Mitliagkas, D Iter, C Ré
arXiv preprint arXiv:1606.04487, 2016
632016
Accelerated stochastic power iteration
P Xu, B He, C De Sa, I Mitliagkas, C Re
International Conference on Artificial Intelligence and Statistics, 58-67, 2018
612018
Fortified networks: Improving the robustness of deep networks by modeling the manifold of hidden representations
A Lamb, J Binas, A Goyal, D Serdyuk, S Subramanian, I Mitliagkas, ...
arXiv preprint arXiv:1804.02485, 2018
472018
Gotta go fast when generating data with score-based models
A Jolicoeur-Martineau, K Li, R Piché-Taillefer, T Kachman, I Mitliagkas
arXiv preprint arXiv:2105.14080, 2021
422021
Linear Lower Bounds and Conditioning of Differentiable Games
A Ibrahim, W Azizian, G Gidel, I Mitliagkas
arXiv preprint arXiv:1906.07300, 2019
412019
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20