יום רביעי, 7 באוקטובר 2026 LIVE
AI־INFO

כתבה arXiv cs.LG ·

DePICT: Decision-Preserving Interface for Constrained Downstream Tasks

תקציר מקורי באנגליתarXiv:2610.03945v2 Announce Type: replace Abstract: 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 DePICT, a procedure for constructing decision preserving interfaces by ranking context directions according to the optimizer's solution sensitivity and aggregating them across an operating regime. We study this problem in a high dimensional setting where primitive context parameterizes a constrained task and the downstream agent observes only a selected subset of context directions. For locally regular constrained programs, we
קרא במקור המקורי