Steven Wu
@zstevenwu
Computer science prof at Carnegie Mellon @SCSatCMU. Researcher in algorithms and machine learning.
833 Following 2.9K Followers
I was always slow on Forward v.s. Reverse KL. Then I realized a mnemonic trick.
FOrward -> FOMO
Fear of missing out on some probability mass:
min_q KL(p || q) encourages mode coverage of p.
Reverse -> Retreat
Retreat to a high-density mode:
min_q KL(q || p) is mode seeking.
Show more
