paper-with-me

Papers

In-Context Learning for Latent Space Bayesian Optimization

2026-06-08 · Tuan A. Vu, Harri Lähdesmäki, Julien Martinelli arxiv

Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins. In parallel, tabular foundation models such as TabPFN and TabICL now achieve state-of-the-art regression performance and are increasingly used as BO surrogates. Because their Bayesian behavior is induced by large synthetic pretraining collections, the composition of this pretraining distribution is crucial. LSBO creates a distinctive mismatch: the induced map from latent code to objective value differs markedly from the regression tasks used to train current in-context models. We address this mismatch by complementing the pretraining stage of tabular foundation model surrogates with synthetic optimization tasks defined on the latent space of a molecular VAE. The continued-pretraining objective features a regularizer that anchors the model to the original checkpoint, preserving its broad regression prior while avoiding overspecialization to the adaptation tasks. On held-out molecular optimization benchmarks, the resulting model achieves strong performance, supporting the relevance of LSBO-specific adaptation for in-context surrogates.

📄 PDF Abstract BibTeX arXiv:2606.09664

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Local Latent Space Bayesian Optimization over Structured Inputs

2022-01-28 · Natalie Maus, Haydn T. Jones, Juston S. Moore, Matt J. Kusner 외

Bayesian optimization over the latent spaces of deep autoencoder models (DAEs) has recently emerged as a promising new approach for optimizing challenging black-box functions over structured, discrete, hard-to-enumerate …

Bayesian Optimization

Advancing Bayesian Optimization via Learning Correlated Latent Space

2023-10-31 · NeurIPS 2023 11 · Seunghun Lee, Jaewon Chu, Sihyeon Kim, Juyeon Ko 외

Bayesian optimization is a powerful method for optimizing black-box functions with limited function evaluations. Recent works have shown that optimization in a latent space through deep generative models such as variatio…

Bayesian Optimization

Joint Composite Latent Space Bayesian Optimization

2023-11-03 · Natalie Maus, Zhiyuan Jerry Lin, Maximilian Balandat, Eytan Bakshy

Bayesian Optimization (BO) is a technique for sample-efficient black-box optimization that employs probabilistic models to identify promising input locations for evaluation. When dealing with composite-structured functio…

Bayesian Optimization

Learning Representation for Bayesian Optimization with Collision-free Regularization

2022-03-16 · Fengxue Zhang, Brian Nord, Yuxin Chen

Bayesian optimization has been challenged by datasets with large-scale, high-dimensional, and non-stationary characteristics, which are common in real-world scenarios. Recent works attempt to handle such input by applyin…

Bayesian Optimization

Time-Aware Latent Space Bayesian Optimization

2026-03-01 · Tuan A. Vu, Julien Martinelli, Harri Lähdesmäki arxiv

Latent-space Bayesian optimization (LSBO) extends Bayesian optimization to structured domains, such as molecular design, by searching in the continuous latent space of a generative model. However, most LSBO methods assum…