activity
20172021
most citedGlobally Optimal Gradient Descent for a ConvNet with Gaussian Inputs

77 citations · 118 across the 3 of their papers we have counts for

collaborators

9 papers

cs.LG20215 cited

A Theoretical Analysis of Fine-tuning with Linear Teachers

Gal Shachaf, Alon Brutzkus, Amir Globerson

Fine-tuning is a common practice in deep learning, achieving excellent generalization results on downstream tasks using relatively little training data. Although widely used in pra…

cs.LG2021

Towards Understanding Learning in Neural Networks with Linear Teachers

Roei Sarussi, Alon Brutzkus, Amir Globerson

Can a neural network minimizing cross-entropy learn linearly separable data? Despite progress in the theory of deep learning, this question remains unsolved. Here we prove that SGD…

cs.LG2020

An Optimization and Generalization Analysis for Max-Pooling Networks

Alon Brutzkus, Amir Globerson

Max-Pooling operations are a core component of deep learning architectures. In particular, they are part of most convolutional architectures used in machine vision, since pooling i…

cs.LG2019

On the Optimality of Trees Generated by ID3

Alon Brutzkus, Amit Daniely, Eran Malach

Since its inception in the 1980s, ID3 has become one of the most successful and widely used algorithms for learning decision trees. However, its theoretical properties remain poorl…

cs.LG2019

ID3 Learns Juntas for Smoothed Product Distributions

Alon Brutzkus, Amit Daniely, Eran Malach

In recent years, there are many attempts to understand popular heuristics. An example of such a heuristic algorithm is the ID3 algorithm for learning decision trees. This algorithm…

cs.LG2018

Low Latency Privacy Preserving Inference

Alon Brutzkus, Oren Elisha, Ran Gilad-Bachrach

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphi…