Steven Wu
@zstevenwu
Computer science prof at Carnegie Mellon @SCSatCMU. Researcher in algorithms and machine learning.
加入 August 2010
833 正在關注 2.9K 粉絲
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.
顯示更多
