Yilin Xie, Shiqiang Zhang, Joel Paulson, and Calvin Tsay investigate mixed-integer programming (MIP) as a paradigm for global acquisition function optimization in Bayesian optimization, noting that most existing algorithms use sampling- or gradient-based methods that do not provably converge to global optima.

Authors

• Person: Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche Organization: AISTATS
  Track: Poster Session 3 - aistats 2026

Sources

• Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS via serper

Referenced by nodes (1)

• mixed-integer linear programming concept