Alert button
Picture for Ohad Shamir

Ohad Shamir

Alert button

Neural Networks with Small Weights and Depth-Separation Barriers

Jun 03, 2020
Gal Vardi, Ohad Shamir

Viaarxiv icon

The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks

Jun 01, 2020
Itay Safran, Gilad Yehudai, Ohad Shamir

Figure 1 for The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks
Figure 2 for The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks
Figure 3 for The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks
Viaarxiv icon

Can We Find Near-Approximately-Stationary Points of Nonsmooth Nonconvex Functions?

Mar 14, 2020
Ohad Shamir

Figure 1 for Can We Find Near-Approximately-Stationary Points of Nonsmooth Nonconvex Functions?
Figure 2 for Can We Find Near-Approximately-Stationary Points of Nonsmooth Nonconvex Functions?
Figure 3 for Can We Find Near-Approximately-Stationary Points of Nonsmooth Nonconvex Functions?
Viaarxiv icon

Is Local SGD Better than Minibatch SGD?

Feb 18, 2020
Blake Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro

Figure 1 for Is Local SGD Better than Minibatch SGD?
Figure 2 for Is Local SGD Better than Minibatch SGD?
Figure 3 for Is Local SGD Better than Minibatch SGD?
Viaarxiv icon

Learning a Single Neuron with Gradient Methods

Feb 11, 2020
Gilad Yehudai, Ohad Shamir

Figure 1 for Learning a Single Neuron with Gradient Methods
Figure 2 for Learning a Single Neuron with Gradient Methods
Viaarxiv icon

Proving the Lottery Ticket Hypothesis: Pruning is All You Need

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

Viaarxiv icon

The Complexity of Finding Stationary Points with Stochastic Gradient Descent

Oct 04, 2019
Yoel Drori, Ohad Shamir

Figure 1 for The Complexity of Finding Stationary Points with Stochastic Gradient Descent
Figure 2 for The Complexity of Finding Stationary Points with Stochastic Gradient Descent
Viaarxiv icon