Speaker
Hyunwoo Oh
Description
In lattice QCD, the precision of results is often hampered by the inherent uncertainty of stochastic methods. Recently, control variates methods have emerged as a promising solution for such noise. Traditional control variates have been used to mitigate this issue, but they rely on educated guesses, which can be limiting. In this talk, I will introduce a neural network approach to parametrize control variates, eliminating the need for guesswork. Using 1+1 dimensional scalar field theory as a testbed, I will demonstrate significant variance reduction, particularly in the strong coupling regime. Also, I will discuss applications of neural control variates on gauge theories.
Primary author
Hyunwoo Oh
