Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Eran Malach

Eran Malach

Proving the Lottery Ticket Hypothesis: Pruning is All You Need

Feb 03, 2020
Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir

Access Paper or Ask Questions

Learning Boolean Circuits with Neural Networks

Oct 25, 2019
Eran Malach, Shai Shalev-Shwartz

Figure 1 for Learning Boolean Circuits with Neural Networks

Figure 2 for Learning Boolean Circuits with Neural Networks

Access Paper or Ask Questions

On the Optimality of Trees Generated by ID3

Jul 11, 2019
Alon Brutzkus, Amit Daniely, Eran Malach

Figure 1 for On the Optimality of Trees Generated by ID3

Figure 2 for On the Optimality of Trees Generated by ID3

Figure 3 for On the Optimality of Trees Generated by ID3

Access Paper or Ask Questions

ID3 Learns Juntas for Smoothed Product Distributions

Jun 20, 2019
Alon Brutzkus, Amit Daniely, Eran Malach

Access Paper or Ask Questions

Is Deeper Better only when Shallow is Good?

Mar 08, 2019
Eran Malach, Shai Shalev-Shwartz

Figure 1 for Is Deeper Better only when Shallow is Good?

Figure 2 for Is Deeper Better only when Shallow is Good?

Figure 3 for Is Deeper Better only when Shallow is Good?

Figure 4 for Is Deeper Better only when Shallow is Good?

Access Paper or Ask Questions

A Provably Correct Algorithm for Deep Learning that Actually Works

Jun 24, 2018
Eran Malach, Shai Shalev-Shwartz

Figure 1 for A Provably Correct Algorithm for Deep Learning that Actually Works

Figure 2 for A Provably Correct Algorithm for Deep Learning that Actually Works

Figure 3 for A Provably Correct Algorithm for Deep Learning that Actually Works

Figure 4 for A Provably Correct Algorithm for Deep Learning that Actually Works

Access Paper or Ask Questions

Decoupling "when to update" from "how to update"

Mar 26, 2018
Eran Malach, Shai Shalev-Shwartz

Figure 1 for Decoupling "when to update" from "how to update"

Figure 2 for Decoupling "when to update" from "how to update"

Figure 3 for Decoupling "when to update" from "how to update"

Figure 4 for Decoupling "when to update" from "how to update"

Access Paper or Ask Questions

SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data

Oct 27, 2017
Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz

Figure 1 for SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data

Access Paper or Ask Questions