Example: confidence
Non-Convex Optimization - Cornell University
•Known to be NP-complete. •How do we encode this as an optimization problem? Subset sum as non-convex optimization •Let a 1,a 2, …, a n be the input integers •Let x 1, x 2 ... P T 1 t=0 1 t+1. Using our randomly chosen output •So the expected value of the gradient at this point is Let z T = w t with probability 1 H T (t+1),whereH t ...
Download Non-Convex Optimization - Cornell University
Information
Domain:
Source:
Link to this page: