no code implementations • 3 May 2023 • Ian Banta, Tianji Cai, Nathaniel Craig, Zhengkang Zhang
We develop a diagrammatic approach to effective field theories (EFTs) corresponding to deep neural networks at initialization, which dramatically simplifies computations of finite-width corrections to neuron statistics.
1 code implementation • 17 Feb 2021 • Tianji Cai, Junyi Cheng, Bernhard Schmitzer, Matthew Thorpe
Working with the local linearization and the corresponding embeddings allows for the advantages of the Euclidean setting, such as faster computations and a plethora of data analysis tools, whilst still enjoying approximately the descriptive power of the Hellinger--Kantorovich metric.
Optimization and Control
no code implementations • 19 Aug 2020 • Tianji Cai, Junyi Cheng, Katy Craig, Nathaniel Craig
We introduce an efficient framework for computing the distance between collider events using the tools of Linearized Optimal Transport (LOT).