← Search

Jarrod Ryan McClean

2 accepted papers

2024

Exponential Quantum Communication Advantage in Distributed Inference and Learning

NeurIPS 2024poster

Training and inference with large machine learning models that far exceed the memory capacity of individual devices necessitates the design of distributed architectures, forcing one to contend with communication constraints. We present a framework for distributed computation over a quantum network…

Cited by 0SourcePDFScholar
2023

On quantum backpropagation, information reuse, and cheating measurement collapse

NeurIPS 2023spotlight

The success of modern deep learning hinges on the ability to train neural networks at scale. Through clever reuse of intermediate information, backpropagation facilitates training through gradient computation at a total cost roughly proportional to running the function, rather than incurring an addi…

Cited by 60SourcePDFScholar