Customers who liked this Recommendation Engine may also like its Dequantization

Re:Customers who liked this Recommendation Engine may also l... by lainga on Thursday July 12, 2018 @07:06PM (#17519350)

A fantastic result, and a nice story behind it. Per the abstract of Tang's paper, the current best results are linear in m and n.

[ Parent | on HN ]

Re:Customers who liked this Recommendation Engine may also l... by titanomachy on Friday July 13, 2018 @02:22AM (#17520881)

Prof Aaronson said the best upper bound they have so far is O(log(n)^33)... to give that more meaning, O(log(n)^33) grows faster than O(n) until about n = 10^15, so "not practical" is a bit of an understatement!

I still get why this is an interesting result, though. And if Scott thinks that lower bounds are achievable he is probably right.

[ Parent | on HN ]

Re:Customers who liked this Recommendation Engine may also l... by paradroid on Friday July 13, 2018 @09:25AM (#17522720)

10^15 is not that big. We could construct and compute on sparse matrices that large today.

[ Parent | on HN ]

Re:Customers who liked this Recommendation Engine may also l... by rspeer on Friday July 13, 2018 @11:19AM (#17523651)

I'm glad to know where the crossover point is, and yeah, hearing that it's around 10^15 tells me it's just a few orders of magnitude of improvement away from being a practical machine learning tool.

[ Parent | on HN ]