- AI · arxiv/cs.LG · 8 min
Chain-of-Thought Supervision Eliminates Sample Complexity Growth
New theoretical analysis shows intermediate reasoning steps remove dependence on generation length, while end-to-end learning scales unpredictably with sequence depth.
April 21, 2026 Read → → - AI · arxiv/cs.LG · 8 min
Formalizing How Much Data Proves a Learning Model Right
Researchers formalize identifying information—the bits needed to confirm or reject a hypothesis—bridging information theory with practical sample complexity.
April 17, 2026 Read → →