The paper introduces a new Gaussian Process kernel, GP‑Perm, that incorporates permutation invariance for Bayesian Optimization tasks involving well placement in Carbon Capture and Storage (CCS) projects. It compares sets via a stable divergence between their empirical representations and can be combined with standard kernels for additional inputs. The authors also explore a Deep Kernel Learning model using a Deep Sets architecture as a learned invariant baseline, evaluating both approaches on eight use cases, including seven synthetic benchmarks and a realistic CCS case study in the Johansen formation.
By Sofianos Panagiotis Fotias, Vassilis Gaganis
arXiv:2606. 02179v1 Announce Type: cross Abstract: Surrogate models for topology optimization (TO) exhibit highly variable out-of-distribution (OOD) generalization under distribution shifts such as changing loads or boundary conditions, yet the source of this variability remains unclear.
By Mohammad Rashed, Duarte F. Valoroso Madeira, Babak Gholami, Caglar Guerbuez, Yunjia Yang, Nils Thuerey
arXiv:2507. 13263v4 Announce Type: replace-cross Abstract: Bayesian Optimization (BO) is a powerful tool for black-box optimization, but its application to high-dimensional permutation spaces is severely limited by the challenge of defining scalable representations.
By Zikai Xie, Linjiang Chen
The paper introduces a differentiable optimization layer for electricity‑market clearing, enabling gradient‑based planning of large data centers. By treating market clearing as a differentiable process, the authors can propagate planning costs back through cleared prices, validating gradients against finite differences. Applied to a 50 MW load allocation problem across six candidate buses in two synthetic networks, gradient optimization nearly matches exhaustive enumeration, with small objective gaps and a noted systematic error near site‑closure thresholds.
By Luca Mungo, Maarten P. Scholl, Arnau Quera-Bofarull
arXiv:2608. 03045v1 Announce Type: new Abstract: We consider grey-box optimization problems where the decision variables naturally partition into black-box variables (as arguments to an expensive black-box function) and white-box variables, governed by a set of explicit, closed-form equations that also depend on the output of the black-box function.
By Joshua E. Hammond, Tyler A. Soderstrom, Brian A. Korgel, Michael Baldea
arXiv:2609.13396v1 Announce Type: new
Abstract: Multi-objective Bayesian optimisation (MOBO) is a sample-efficient approach for optimising expensive black-box functions with multiple objectives. In M...
By Chao Jiang, Yueling Huang, Miqing Li