Tag
Researchers present a practical variance reduction framework combining post-stratification with CUPED for heavy-tailed monetization metrics in ranking experiments, deployed at ShareChat to achieve equivalent statistical confidence with 45% less traffic. The paper is accepted at SIGIR 2026.
Microsoft Research's latest newsletter highlights AgentPex, an open-source system for automated evaluation of agentic behaviors; new theoretical work on variance reduction for ranking systems; a call to shift from documents to repositories for human-agent collaboration; and a global challenge on AI value alignment.