Suivre
Umut Simsekli
Umut Simsekli
INRIA - École Normale Supérieure
Adresse e-mail validée de inria.fr - Page d'accueil
Titre
Citée par
Citée par
Année
Generalized sliced wasserstein distances
S Kolouri, K Nadjahi, U Simsekli, R Badeau, G Rohde
Advances in neural information processing systems 32, 2019
3602019
A tail-index analysis of stochastic gradient noise in deep neural networks
U Simsekli, L Sagun, M Gurbuzbalaban
International Conference on Machine Learning, 5827-5837, 2019
2792019
Sliced-Wasserstein flows: Nonparametric generative modeling via optimal transport and diffusions
A Liutkus, U Simsekli, S Majewski, A Durmus, FR Stöter
International Conference on machine learning, 4104-4113, 2019
1522019
The heavy-tail phenomenon in SGD
M Gurbuzbalaban, U Simsekli, L Zhu
International Conference on Machine Learning, 3964-3975, 2021
1512021
Generalised coupled tensor factorisation
K Yılmaz, A Cemgil, U Simsekli
Advances in neural information processing systems 24, 2011
1282011
Statistical and topological properties of sliced probability divergences
K Nadjahi, A Durmus, L Chizat, S Kolouri, S Shahrampour, U Simsekli
Advances in Neural Information Processing Systems 33, 20802-20812, 2020
992020
Asymptotic guarantees for learning generative models with the sliced-Wasserstein distance
K Nadjahi, A Durmus, U Simsekli, R Badeau
Advances in Neural Information Processing Systems 32, 2019
802019
Stochastic Quasi-Newton Langevin Monte Carlo
U Simsekli, R Badeau, AT Cemgil, G Richard
International Conference on Machine Learning, 2016
782016
Explicit regularisation in gaussian noise injections
A Camuto, M Willetts, U Simsekli, SJ Roberts, CC Holmes
Advances in Neural Information Processing Systems 33, 16603-16614, 2020
722020
Hausdorff dimension, heavy tails, and generalization in neural networks
U Simsekli, O Sener, G Deligiannidis, MA Erdogdu
Advances in Neural Information Processing Systems 33, 5138-5151, 2020
70*2020
Intrinsic dimension, persistent homology and generalization in neural networks
T Birdal, A Lou, LJ Guibas, U Simsekli
Advances in neural information processing systems 34, 6776-6789, 2021
692021
A generative model for non-intrusive load monitoring in commercial buildings
S Henriet, U Şimşekli, B Fuentes, G Richard
Energy and Buildings 177, 268-278, 2018
662018
Learning the morphology of brain signals using alpha-stable convolutional sparse coding
M Jas, T Dupré la Tour, U Simsekli, A Gramfort
Advances in Neural Information Processing Systems 30, 2017
632017
Groove2groove: One-shot music style transfer with supervision from synthetic data
O Cífka, U Şimşekli, G Richard
IEEE/ACM Transactions on Audio, Speech, and Language Processing 28, 2638-2650, 2020
622020
First exit time analysis of stochastic gradient descent under heavy-tailed gradient noise
TH Nguyen, U Simsekli, M Gurbuzbalaban, G Richard
Advances in neural information processing systems 32, 2019
612019
Fractional underdamped langevin dynamics: Retargeting sgd with momentum under heavy-tailed gradient noise
U Simsekli, L Zhu, YW Teh, M Gurbuzbalaban
International conference on machine learning, 8970-8980, 2020
592020
Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte Carlo
U Şimşekli
International Conference on Machine Learning (ICML), 2017
582017
Relative positional encoding for transformers with linear complexity
A Liutkus, O Cıfka, SL Wu, U Simsekli, YH Yang, G Richard
International Conference on Machine Learning, 7067-7079, 2021
552021
On the heavy-tailed theory of stochastic gradient descent for deep neural networks
U Şimşekli, M Gürbüzbalaban, TH Nguyen, G Richard, L Sagun
arXiv preprint arXiv:1912.00018, 2019
52*2019
Alpha-stable matrix factorization
U Şimşekli, A Liutkus, AT Cemgil
IEEE Signal Processing Letters 22 (12), 2289-2293, 2015
512015
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20