How Jet Built a GPU-Powered Fulfillment Engine with F# and CUDA

Originally published at: How Jet Built a GPU-Powered Fulfillment Engine with F# and CUDA | NVIDIA Technical Blog

Have you ever looked at your shopping list and tried to optimize your trip based on things like distance to store, price, and number of items you can buy at each store? The quest for a smarter shopping cart is never-ending, and the complexity of finding even a sub-optimal solution to this problem can quickly…

This reminds me of portfolio optimisation with transaction costs in finance.

For that there is an efficient branch and bound solution I've built in the past based on this paper:

https://faculty.washington....

Not sure if there are equivalent obvious bounds in your case.

This is wonderful! I am geeking out. Thank you for posting the code snippets.

It seems this approach is trying to re-invent convex optimization.