About
Discord Stateoftheart AI
GitHub

Publications

20

Cited by

1029

Levent Sagun

machine learningdeep learningprobabilitystatistical physicsenergy landscapes
Facebook

United States

Papers and Citations

1 - 50
Entropy-sgd: Biasing gradient descent into wide valleys
2016
Levent Sagun
Carlo Baldassi
Anna Choromanska
+6
Cited by 399
Empirical analysis of the hessian of over-parametrized neural networks
2017
Leon Bottou
Levent Sagun
V. Uğur G�ney
+2
Cited by 168
Searchqa: A new q&a dataset augmented with context from a search engine
2017
Levent Sagun
Kyunghyun Cho
V. Uğur G�ney
+3
Cited by 167
Eigenvalues of the hessian in deep learning: Singularity and beyond
2016
Levent Sagun
Leon Bottou
Y LeCun
Cited by 84
Scaling description of generalization with number of parameters in deep learning
2020
Stéphane d'Ascoli
Levent Sagun
Arthur Jacot
+6
Cited by 81
Jamming transition as a paradigm to understand the loss landscape of deep neural networks
2019
Giulio Biroli
Matthieu Wyart
Mario Geiger
+6
Cited by 74
A tail-index analysis of stochastic gradient noise in deep neural networks
2019
Mert Gürbüzbalaban
Levent Sagun
Umut Simsekli
+1
Cited by 72
Comparing dynamics: Deep neural networks versus glassy systems
2018
Marco Baity-Jesi
Yann LeCun
Mario Geiger
+6
Cited by 63
Energy landscapes for machine learning
2017
Levent Sagun
Andy Ballard
Stefano Martiniani
+4
Cited by 61
A jamming transition from under-to over-parametrization affects generalization in deep learning
2019
Matthieu Wyart
Giulio Biroli
Stéphane d'Ascoli
+6
Cited by 57
Explorations on high dimensional landscapes
2014
Gerard BEN AROUS
V. Uğur G�ney
Levent Sagun
+1
Cited by 52
A jamming transition from under-to over-parametrization affects loss landscape and generalization
2018
Levent Sagun
Mario Geiger
Stéphane d'Ascoli
+3
Cited by 42
Singularity of the hessian in deep learning
2016
Levent Sagun
Leon Bottou
Yann LeCun
Cited by 42
Early predictability of asylum court decisions
2017
H Şirin
Levent Sagun
Matthew Dunn
+1
Cited by 22
Triple descent and the two kinds of overfitting: Where & why do they appear?
2020
Giulio Biroli
Stéphane d'Ascoli
Levent Sagun
Cited by 14
Universal halting times in optimization and machine learning
2015
Levent Sagun
Thomas Trogdon
Yann LeCun
Cited by 9
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
2019
Joan Bruna
Giulio Biroli
Stéphane d'Ascoli
+1
Cited by 8
Universality in halting time and its applications in optimization
2015
Thomas Trogdon
Levent Sagun
Yann LeCun
Cited by 4
Easing non-convex optimization with neural networks
2018
David Lopez-Paz
Levent Sagun
Cited by 3
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks
2019
Gaël Richard
Umut Şimşekli
Thanh Huy Nguyen
+4
Cited by 2
Neural Relational Autoregression for High-Resolution COVID-19 Forecasting
M Le
Maximilian Nickel
Mark Ibrahim
+2
Cited by
More data or more parameters? Investigating the effect of data structure on generalization
2021
Giulio Biroli
Levent Sagun
Marylou Gabrié
+1
Cited by
Explorations on High Dimensional Landscapes: Spin Glasses and Deep Learning
2017
Levent Sagun
Cited by
Post-Workshop Report on, Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver
2020
N Rostemzadeh
SS Mannelli
Levent Sagun
+2
Cited by
Universality in halting time
2016
Thomas Trogdon
Levent Sagun
Yann LeCun
Cited by