Hanie Sedghi

Research Scientist
Allen Institute for Artificial Intelligence

Beating Perils of Non-convexity: Guaranteed Training of Neural Networks using Tensor Methods

Neural networks have revolutionized performance across multiple domains such as computer vision and speech recognition. However, training a neural network is a highly non-convex problem and the conventional stochastic gradient descent can get stuck in spurious local optima. We propose a computationally efficient method for training neural networks that also has guaranteed risk bounds. It is based on tensor decomposition which is guaranteed to converge to the globally optimal solution under mild conditions. We explain how this framework can be leveraged to train feedforward and recurrent neural networks.

Hanie Sedghi is a Research Scientist at Allen Institute for Artificial Intelligence (AI2). Her research interests include large-scale machine learning, high-dimensional statistics and probabilistic models. More recently, she has been working on inference and learning in latent variable models. She has received her Ph.D. from University of Southern California with a minor in Mathematics in 2015. She was also a visiting researcher at University of California, Irvine working with professor Anandkumar during her Ph.D. She received her B.Sc. and M.Sc. degree from Sharif University of Technology, Tehran, Iran.

Buttontwitter Buttonlinkedin

As Featured In

Original
Original
Original
Original
Original
Original

Partners & Attendees

Intel.001
Nvidia.001
Graphcoreai.001
Ibm watson health 3.001
Facebook.001
Acc1.001
Rbc research.001
Twentybn.001
Forbes.001
Maluuba 2017.001
Mit tech review.001
Kd nuggets.001