4 papers
Information-Theoretic Guarantees for Recovering Low-Rank Tensors from Symmetric Rank-One Measurements
Eren C. Kızıldağ
In this paper, we investigate the sample complexity of recovering tensors with low symmetric rank from symmetric rank-one measurements. This setting is particularly motivated by th…
Algorithms and Barriers in the Symmetric Binary Perceptron Model
David Gamarnik, Eren C. Kızıldağ, Will Perkins +1
The symmetric binary perceptron () exhibits a dramatic statistical-to-computational gap: the densities at which known efficient algorithms find solutions are far belo…
Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomena
Matt Emschwiller, David Gamarnik, Eren C. Kızıldağ +1
In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of pa…
Stationary Points of Shallow Neural Networks with Quadratic Activation Function
David Gamarnik, Eren C. Kızıldağ, Ilias Zadik
We consider the teacher-student setting of learning shallow neural networks with quadratic activations and planted weight matrix , where is the wi…