Follow
Alon Brutzkus
Alon Brutzkus
Verified email at mail.tau.ac.il - Homepage
Title
Cited by
Cited by
Year
Globally optimal gradient descent for a convnet with gaussian inputs
A Brutzkus, A Globerson
International conference on machine learning, 605-614, 2017
3232017
SGD learns over-parameterized networks that provably generalize on linearly separable data
A Brutzkus, A Globerson, E Malach, S Shalev-Shwartz
arXiv preprint arXiv:1710.10174, 2017
2732017
Low latency privacy preserving inference
A Brutzkus, R Gilad-Bachrach, O Elisha
International Conference on Machine Learning, 812-821, 2019
2322019
Why do larger models generalize better? A theoretical perspective via the XOR problem
A Brutzkus, A Globerson
International Conference on Machine Learning, 822-830, 2019
812019
A theoretical analysis of fine-tuning with linear teachers
G Shachaf, A Brutzkus, A Globerson
Advances in Neural Information Processing Systems 34, 15382-15394, 2021
202021
ID3 learns juntas for smoothed product distributions
A Brutzkus, A Daniely, E Malach
Conference on Learning Theory, 902-915, 2020
202020
Towards understanding learning in neural networks with linear teachers
R Sarussi, A Brutzkus, A Globerson
International Conference on Machine Learning, 9313-9322, 2021
192021
An Optimization and Generalization Analysis for Max-Pooling Networks
A Brutzkus, A Globerson
arXiv preprint arXiv:2002.09781, 2020
13*2020
On the optimality of trees generated by id3
A Brutzkus, A Daniely, E Malach
arXiv preprint arXiv:1907.05444, 2019
132019
Detecting domain name system (DNS) tunneling based on DNS logs and network data
A Brutzkus, R Levin
US Patent 10,412,107, 2019
122019
Efficient learning of CNNs using patch based features
A Brutzkus, A Globerson, E Malach, AR Netser, S Shalev-Schwartz
International Conference on Machine Learning, 2336-2356, 2022
52022
On the inductive bias of neural networks for learning read-once dnfs
I Bronstein, A Brutzkus, A Globerson
Uncertainty in Artificial Intelligence, 255-265, 2022
32022
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
2024
Truth tellers and liars with fewer questions
G Braunschvig, A Brutzkus, D Peleg, A Sealfon
Discrete Mathematics 338 (8), 1310-1316, 2015
2015
Supplementary Material: A Theoretical Analysis of Fine-tuning with Linear Teachers
G Shachaf, A Brutzkus, A Globerson
The system can't perform the operation now. Try again later.
Articles 1–15