Bid Optimization using Maximum Entropy Reinforcement Learning

no code implementations • 11 Oct 2021 • Mengjuan Liu, Jinyu Liu, Zhengning Hu, Yuchen Ge, Xuyun Nie

In this paper, we first utilize a widely accepted linear bidding function to compute every impression's base price and optimize it by a mutable adjustment factor derived from the RTB auction environment, to avoid optimizing every impression's bidding price directly.

reinforcement-learning Reinforcement Learning (RL)

Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation

no code implementations • 21 Apr 2021 • Zhong-Qiu Zhao, Yao Gao, Yuchen Ge, Weidong Tian

Experimental results on COCO and OCHuman keypoints datasets show that our proposed ODKD can improve the performance of different lightweight models by a large margin, and HRNet-W16 equipped with ODKD achieves state-of-the-art performance for lightweight human pose estimation.

Binarization Knowledge Distillation +2

Classification Attention for Chinese NER

no code implementations • 25 Sep 2019 • Yuchen Ge, FanYang, PeiYang

The character-based model, such as BERT, has achieved remarkable success in Chinese named entity recognition (NER).

Chinese Named Entity Recognition Classification +4