Unbiased Top-$k$ Estimation for On-Policy Distillation
Tail-Corrected Top-$k$ On-Policy Distillation (TT-OPD) is proposed, which preserves the advantages of TK-OPD, including rich distributional supervision and low computational cost, while providing an unbiased estimator of the gradient of the reverse KL divergence.
Lin-Jian Meng, Si-Yuan Gan, Yu-Hang Li et al.
· 0 citations