
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
We study the relative power of learning with gradient descent on differe...
read it

The Connection Between Approximation, Depth Separation and Learnability in Neural Networks
Several recent works have shown separation results between deep neural n...
read it

Computational Separation Between Convolutional and FullyConnected Networks
Convolutional neural networks (CNN) exhibit unmatched performance in a m...
read it

When Hardness of Approximation Meets Hardness of Learning
A supervised learning algorithm has access to a distribution of labeled ...
read it

Learning Parities with Neural Networks
In recent years we see a rapidly growing line of research which shows le...
read it

Proving the Lottery Ticket Hypothesis: Pruning is All You Need
The lottery ticket hypothesis (Frankle and Carbin, 2018), states that a ...
read it

Learning Boolean Circuits with Neural Networks
Training neuralnetworks is computationally hard. However, in practice t...
read it

On the Optimality of Trees Generated by ID3
Since its inception in the 1980s, ID3 has become one of the most success...
read it

ID3 Learns Juntas for Smoothed Product Distributions
In recent years, there are many attempts to understand popular heuristic...
read it

Decoupling Gating from Linearity
ReLU neuralnetworks have been in the focus of many recent theoretical w...
read it

Is Deeper Better only when Shallow is Good?
Understanding the power of depth in feedforward neural networks is an o...
read it

A Provably Correct Algorithm for Deep Learning that Actually Works
We describe a layerbylayer algorithm for training deep convolutional n...
read it
Eran Malach
is this you? claim profile