K
Kamyar Azizzadenesheli
Researcher at Purdue University
Publications - 108
Citations - 4373
Kamyar Azizzadenesheli is an academic researcher from Purdue University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 24, co-authored 73 publications receiving 2074 citations. Previous affiliations of Kamyar Azizzadenesheli include University of California, Irvine & California Institute of Technology.
Papers
More filters
Posted Content
Fourier Neural Operator for Parametric Partial Differential Equations
Zongyi Li,Nikola B. Kovachki,Kamyar Azizzadenesheli,Burigede Liu,Kaushik Bhattacharya,Andrew M. Stuart,Animashree Anandkumar +6 more
TL;DR: This work forms a new neural operator by parameterizing the integral kernel directly in Fourier space, allowing for an expressive and efficient architecture and shows state-of-the-art performance compared to existing neural network methodologies.
Proceedings Article
signSGD: Compressed Optimisation for Non-Convex Problems
TL;DR: SignSGD as mentioned in this paper uses majority vote to aggregate gradient signs from each worker enabling 1-bit compression of worker-server communication in both directions, which can achieve fast communication and fast convergence.
Posted Content
Stochastic Activation Pruning for Robust Adversarial Defense
Guneet S. Dhillon,Kamyar Azizzadenesheli,Zachary C. Lipton,Jeremy Bernstein,Jean Kossaifi,Aran Khanna,Animashree Anandkumar +6 more
TL;DR: In this paper, a stochastic activation pruning (SAP) strategy is proposed for adversarial defense against adversarial examples in deep learning networks, where a random subset of activations are pruned and the survivors are scaled up to compensate.
Posted Content
signSGD: Compressed Optimisation for Non-Convex Problems
TL;DR: SignSGD can get the best of both worlds: compressed gradients and SGD-level convergence rate, and the momentum counterpart of signSGD is able to match the accuracy and convergence speed of Adam on deep Imagenet models.
Proceedings Article
Neural Operator: Graph Kernel Network for Partial Differential Equations
Zongyi Li,Nikola B. Kovachki,Kamyar Azizzadenesheli,Burigede Liu,Kaushik Bhattacharya,Andrew M. Stuart,Animashree Anandkumar +6 more
TL;DR: The key innovation in this work is that a single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces.