Sledovat
Mor Shpigel Nacson
Mor Shpigel Nacson
PhD Student, Technion
E-mailová adresa ověřena na: campus.technion.ac.il
Název
Citace
Citace
Rok
The implicit bias of gradient descent on separable data
D Soudry, E Hoffer, MS Nacson, S Gunasekar, N Srebro
Journal of Machine Learning Research 19 (70), 1-57, 2018
10452018
Convergence of gradient descent on separable data
MS Nacson, J Lee, S Gunasekar, PHP Savarese, N Srebro, D Soudry
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
1792019
Stochastic gradient descent on separable data: Exact convergence with a fixed learning rate
MS Nacson, N Srebro, D Soudry
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
1132019
On the implicit bias of initialization shape: Beyond infinitesimal mirror descent
S Azulay, E Moroshko, MS Nacson, BE Woodworth, N Srebro, ...
International Conference on Machine Learning, 468-477, 2021
902021
Lexicographic and depth-sensitive margins in homogeneous and non-homogeneous deep models
MS Nacson, S Gunasekar, J Lee, N Srebro, D Soudry
International Conference on Machine Learning, 4683-4692, 2019
832019
Implicit bias of the step size in linear diagonal neural networks
MS Nacson, K Ravichandran, N Srebro, D Soudry
International Conference on Machine Learning, 16270-16295, 2022
522022
TAEN: temporal aware embedding network for few-shot action recognition
R Ben-Ari, MS Nacson, O Azulai, U Barzelay, D Rotman
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
312021
At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?
N Giladi, MS Nacson, E Hoffer, D Soudry
arXiv preprint arXiv:1909.12340, 2019
202019
Gradient descent monotonically decreases the sharpness of gradient flow solutions in scalar networks and beyond
I Kreisler, MS Nacson, D Soudry, Y Carmon
International Conference on Machine Learning, 17684-17744, 2023
152023
The implicit bias of minima stability in multivariate shallow relu networks
MS Nacson, R Mulayoff, G Ongie, T Michaeli, D Soudry
arXiv preprint arXiv:2306.17499, 2023
82023
How uniform random weights induce non-uniform bias: Typical interpolating neural networks generalize with narrow teachers
G Buzaglo, I Harel, MS Nacson, A Brutzkus, N Srebro, D Soudry
arXiv preprint arXiv:2402.06323, 2024
32024
Action recognition using limited data
R Ben-Ari, O Azulai, U Barzelay, MS Nacson
US Patent App. 17/219,322, 2022
22022
How Learning Rate and Delay Affect Minima Selection in Asynchronous Training of Neural Networks
N Giladi, MS Nacson, E Hoffer, D Soudry
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–13