In-Context Learning for Latent Space Bayesian Optimization

• URL: http://arxiv.org/abs/2606.09664v1
• Date: Mon, 08 Jun 2026 15:45:25 GMT
• Title: In-Context Learning for Latent Space Bayesian Optimization
• Abstract summary: latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins.<n>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.<n>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.
• Score: 8.943469192703875
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization [17.43522044331905]
  We propose SPADE (Support-Proximity Augmented Diffusion Estimation), a novel framework that reimagines forward surrogate modeling through the lens of conditional generative modeling.<n>We show that SPADE achieves state-of-the-art performance across Design-Bench tasks and an LLM data mixture optimization benchmark.
  arXiv  Detail & Related papers  (2026-05-11T21:09:28Z)
• Relation Reasoning with LLMs in Expensive Optimization [19.271995977675758]
  This paper proposes R2SAEA, a reinforcement-trained relation-based large language model (LLM) surrogate assisted evolutionary algorithm.<n>We cast relation-based surrogate modeling as an in-context pairwise reasoning task.<n> Experiments on single- and multi-objective benchmarks show improved relation prediction and state-of-the-art optimization performance.
  arXiv  Detail & Related papers  (2026-04-30T04:28:10Z)
• Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models [102.20309135516186]
  Cross-entropy (CE) training provides dense and scalable supervision for language models.<n>We introduce a feature-matching objective for language-model fine-tuning.<n>To optimize this objective efficiently, we propose energy-based fine-tuning.
  arXiv  Detail & Related papers  (2026-03-12T17:57:50Z)
• Task-free Adaptive Meta Black-box Optimization [55.461814601130044]
  We propose the Adaptive meta Black-box Optimization Model (ABOM), which performs online parameter adaptation using solely optimization data from the target task.<n>Unlike conventional metaBBO frameworks that decouple meta-training and optimization phases, ABOM introduces a closed-loop parameter learning mechanism, where parameterized evolutionary operators continuously self-update.<n>This paradigm shift enables zero-shot optimization: ABOM competitive performance on synthetic BBO benchmarks and realistic unmanned aerial vehicle path planning problems without any handcrafted training tasks.
  arXiv  Detail & Related papers  (2026-01-29T09:54:10Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• HiBBO: HiPPO-based Space Consistency for High-dimensional Bayesian Optimisation [23.518990631999884]
  HiBBO is a novel BO framework that introduces the space consistency into the latent space construction in VAE using HiPPO.<n> Experiments on highdimensional benchmark tasks demonstrate that HiBBO outperforms existing VAEBO methods in convergence speed and solution quality.
  arXiv  Detail & Related papers  (2025-10-10T03:22:10Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Latent Bayesian Optimization via Autoregressive Normalizing Flows [17.063294409131238]
  We propose a Normalizing Flow-based Bayesian Optimization (NF-BO) to solve the value discrepancy problem.<n>Our method demonstrates superior performance in molecule generation tasks, significantly outperforming both traditional and recent LBO approaches.
  arXiv  Detail & Related papers  (2025-04-21T06:36:09Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.