AINeutralarXiv – CS AI · 15h ago6/10
🧠
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
Researchers propose Credit-Assigned Policy Gradient (CA-PG), a new machine learning technique that solves the variance problem in training early-stage rankers for two-stage retrieval systems. By computing gradients with respect to individual item selection probability rather than entire candidate sets, CA-PG enables scalable end-to-end training of search and recommendation systems.