الباحثون

Wyatt Mackey

المنشورات 2

نسخة أولية وصول مفتوح

ORACLE: Optimizer-Relative Alignment for Constrained LEarning

Utkarsh Grover, Wyatt Mackey, Kaixun Hua وآخرون · 2026

Constraint handling methods typically intervene before the optimizer acts, by modifying the objective or the gradient. Yet momentum, adaptive scaling, and structured preconditioning can substantially reshape that signal before it becomes a parameter update. We formulate optimizer relative constrained learning, where co …

نسخة أولية وصول مفتوح

DePICT: Decision-Preserving Interface for Constrained Downstream Tasks

A constrained optimization problem may involve a parameter in its objective and active constraints, yet the final decision may remain insensitive to small changes in that parameter. This raises a fundamental question: which inputs does a decision making system truly depend on? Building on this question, we introduce De …

المؤلفون المشاركون