143 citations · 145 across the 8 of their papers we have counts for
7 papers · 1 filter
Unbiased Stochastic Optimization for Gaussian Processes on Finite Dimensional RKHS
Neta Shoham, Haim Avron
Current methods for stochastic hyperparameter learning in Gaussian Processes (GPs) rely on approximations, such as computing biased stochastic gradients or using inducing points in…
Flatness After All?
Neta Shoham, Liron Mor-Yosef, Haim Avron
Recent literature generalization in deep learning has examined the relationship between the curvature of the loss function at minima and generalization, mainly in the context of ov…
Scaling Neural Tangent Kernels via Sketching and Random Features
Amir Zandieh, Insu Han, Haim Avron +3
The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely-wide neural networks trained under least squares loss by gradient descent. Recent works also report that NT…
An Exploration into why Output Regularization Mitigates Label Noise
Neta Shoham, Tomer Avidor, Nadav Israel
Label noise presents a real challenge for supervised learning algorithms. Consequently, mitigating label noise has attracted immense research in recent years. Noise robust losses i…
Random Features for the Neural Tangent Kernel
Insu Han, Haim Avron, Neta Shoham +2
The Neural Tangent Kernel (NTK) has discovered connections between deep neural networks and kernel methods with insights of optimization and generalization. Motivated by this, rece…
Experimental Design for Overparameterized Learning with Application to Single Shot Deep Active Learning
Neta Shoham, Haim Avron
The impressive performance exhibited by modern machine learning models hinges on the ability to train such models on a very large amounts of labeled data. However, since access to…
Overcoming Forgetting in Federated Learning on Non-IID Data
Neta Shoham, Tomer Avidor, Aviv Keren +4
We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt…