AI Briefing#theory
The latest AI and developer news about #theory, with the original source and a short summary.
The latest AI and developer news about #theory, with the original source and a short summary.
A new theory paper demonstrates that under strategy specialization, every pass@1 improvement in RLVR strictly lowers success on some prompts, with a tight bound on the pass@k crossover.
The new DD method ensures asymptotic alignment between training and test errors at each iteration step.
A theoretical study reveals a structural blind spot in standard ERM and its worsening under PGD.
A concept called 'learning mechanics' has been proposed to explain the deep learning training process.