Large language models (LLMs) can translate natural-language problem descriptions into optimization code, but the code is prone to silent failures: it executes and returns a solver-feasible solution while encoding a semantically incorrect formulation. On compositional problems, the resulting feasibility-correctness gap...
Junbo Jacob Lian, Yu-Jun Sun, Hui-Ling Chen et al.· arXiv.org· 9 citations· ⚡2
It is proved that PROBE is $\delta$-PAC and attains the known-correlation oracle sample complexity up to a constant multiplicative factor and a constant additive calibration cost and the guarantee extends to the $(\epsilon,\delta)$-PAC setting under minimal changes to the algorithm.
It is established that CGD converges to a neighborhood of the global optimum when the loss function exhibits sufficient strong convexity, and the derived bounds reveal a key insight: the strength of convexity in the loss function can compensate for the uncertainty introduced by decision-dependent effects.
Wenxuan Liu, Xiangting Liu, Maoqi Liu et al.· Production and operations ma...· 0 citations
To the authors' knowledge, AdmitOR is the first label-free admission mechanism designed around an explicitly calibrated false-discovery target, and the transfer failure identifies a necessary condition for extending it to wild streams.
Junbo Jacob Lian, Hui-Ling Chen, Hanzhang Qin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
