We have 3 of 18 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Coupled Calibration and Learning (CCL) is proposed, an LLM distillation algorithm that couples teacher calibration with student updates through token-level branching, using reward feedback only on source questions.
The result shows that standard double machine learning can overstate the intrinsic difficulty of target estimation and provides a target-specific principle for learner selection: approximation error and stochastic complexity must be jointly balanced across the two nuisance learners rather than optimized separately.
The framework separates optimizer design into gradient prediction and online preconditioner selection, providing a principled perspective on how adaptive optimization methods may be understood through static regret and applied in nonconvex optimization.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
