About
Hi! I am a post-doctoral researcher at the Technion, hosted by Prof. Daniel Soudry. I completed my PhD at Tel-Aviv University under the supervision of Prof. Amir Globerson.
My main research interests are in machine learning, statistics, optimization and algorithms.
Publications
On the Inductive Bias of Neural Networks for Learning Read-once DNFs
Ido Bronstein, Alon Brutzkus, Amir Globerson
UAI 2022
Efficient Learning of CNNs using Patch Based Features
Alon Brutzkus, Amir Globerson, Eran Malach, Alon Regev Netzer, Shai Shalev-Shwartz
ICML 2022
A Theoretical Analysis of Fine-tuning with Linear Teachers
Gal Shachaf, Alon Brutzkus, Amir Globerson
NeurIPS 2021
Towards Understanding Learning in Neural Networks with Linear Teachers
Roei Sarussi, Alon Brutzkus, Amir Globerson
ICML 2021
An Optimization and Generalization Analysis for Max-Pooling Networks
Alon Brutzkus, Amir Globerson
UAI 2021
ID3 Learns Juntas for Smoothed Product Distributions
Alon Brutzkus, Amit Daniely, Eran Malach
COLT 2020
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem
Alon Brutzkus, Amir Globerson
ICML 2019
SGD Learns Overparameterized Networks that Provably Generalize on Linearly Separable Data
Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz
ICLR 2018
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
Alon Brutzkus, Amir Globerson
ICML 2017
Truth tellers and Liars with Fewer Questions
Gilad Braunschvig, Alon Brutzkus, David Peleg, Adam Sealfon
Discrete Mathematics 2015
Preprints
On the Optimality of Practical Size Trees Learned by ID3
Alon Brutzkus, Eran Malach, Amit Daniely