# End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes

arXiv: https://arxiv.org/abs/2305.15930 · HTML: https://mlsanity.com/paper/2305.15930/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 62 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/1611.04717/) (2016)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Stabilizing Transformers for Reinforcement Learning](https://mlsanity.com/paper/1910.06764/) (2019)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [Convolutional Conditional Neural Processes](https://mlsanity.com/paper/1910.13556/) (2019)
- [Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling](https://mlsanity.com/paper/2207.04179/) (2022)
- [HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO](https://mlsanity.com/paper/2109.06716/) (2021)
- [PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees](https://mlsanity.com/paper/2002.05551/) (2020)
- [Towards Learning Universal Hyperparameter Optimizers with Transformers](https://mlsanity.com/paper/2205.13320/) (2022)
- [HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML](https://mlsanity.com/paper/2106.06257/) (2021)
- [Few-Shot Bayesian Optimization with Deep Kernel Surrogates](https://mlsanity.com/paper/2101.07667/) (2021)
- [Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization](https://mlsanity.com/paper/1904.02642/) (2019)
- [Pre-trained Gaussian Processes for Bayesian Optimization](https://mlsanity.com/paper/2109.08215/) (2021)
- [Improving Generalization in Meta-learning via Task Augmentation](https://mlsanity.com/paper/2007.13040/) (2020)
- [Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning](https://mlsanity.com/paper/1909.12552/) (2019)
- [Data-efficient Domain Randomization with Bayesian Optimization](https://mlsanity.com/paper/2003.02471/) (2020)
- [OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis](https://mlsanity.com/paper/2110.11292/) (2021)
- [Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition](https://mlsanity.com/paper/1710.07324/) (2017)
- [Transfer Learning for Bayesian Optimization: A Survey](https://mlsanity.com/paper/2302.05927/) (2023)

## Built on by (most cited first, 30 of 32)

- [All-in-one simulation-based inference](https://mlsanity.com/paper/2404.09636/) (2024)
- [Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization](https://mlsanity.com/paper/2411.00625/) (2024)
- [FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch](https://mlsanity.com/paper/2406.04824/) (2024)
- [Amortized Bayesian Experimental Design for Decision-Making](https://mlsanity.com/paper/2411.02064/) (2024)
- [Evolve Cost-aware Acquisition Functions Using Large Language Models](https://mlsanity.com/paper/2404.16906/) (2024)
- [Reinforced In-Context Black-Box Optimization](https://mlsanity.com/paper/2402.17423/) (2024)
- [BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL](https://mlsanity.com/paper/2505.21974/) (2025)
- [PABBO: Preferential Amortized Black-Box Optimization](https://mlsanity.com/paper/2503.00924/) (2025)
- [ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition](https://mlsanity.com/paper/2506.07259/) (2025)
- [Machine Learning Insides OptVerse AI Solver: Design Principles and Applications](https://mlsanity.com/paper/2401.05960/) (2024)
- [Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings](https://mlsanity.com/paper/2506.07109/) (2025)
- [EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization](https://mlsanity.com/paper/2411.00171/) (2024)
- [In-Context Multi-Objective Optimization](https://mlsanity.com/paper/2512.11114/) (2025)
- [AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive](https://mlsanity.com/paper/2605.11518/) (2026)
- [None To Optima in Few Shots: Bayesian Optimization with MDP Priors](https://mlsanity.com/paper/2511.01006/) (2025)
- [MALIBO: Meta-learning for Likelihood-free Bayesian Optimization](https://mlsanity.com/paper/2307.03565/) (2023)
- [FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization](https://mlsanity.com/paper/2509.03244/) (2025)
- [In-Context Black-Box Optimization with Unreliable Feedback](https://mlsanity.com/paper/2605.06187/) (2026)
- [α-PFN: Fast Entropy Search via In-Context Learning](https://mlsanity.com/paper/2606.07134/) (2026)
- [Efficient Adaptive Data Acquisition via Pretrained Belief Representations](https://mlsanity.com/paper/2606.25197/) (2026)
- [R'enyi Neural Processes](https://mlsanity.com/paper/2405.15991/) (2024)
- [ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization](https://mlsanity.com/paper/2510.03051/) (2025)
- [SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization](https://mlsanity.com/paper/2510.25404/) (2025)
- [Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications](https://mlsanity.com/paper/2605.00068/) (2026)
- [Direct Regret Optimization in Bayesian Optimization](https://mlsanity.com/paper/2507.06529/) (2025)
- [Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings](https://mlsanity.com/paper/2601.06505/) (2026)
- [Amortising Inference and Meta-Learning Priors in Neural Networks](https://mlsanity.com/paper/2602.08782/) (2026)
- [Few-Shot Design Optimization by Exploiting Auxiliary Information](https://mlsanity.com/paper/2602.12112/) (2026)
- [BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH](https://mlsanity.com/paper/2604.12005/) (2026)
- [In-Context Learning for Latent Space Bayesian Optimization](https://mlsanity.com/paper/2606.09664/) (2026)

## Abstract (arXiv)

Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function independently, joint training of both components remains an open challenge. 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. Early on, we notice that training transformer-based neural processes from scratch with RL is challenging due to insufficient supervision, especially when rewards are sparse. We formalise this claim with a combinatorial analysis showing that the widely used notion of regret as a reward signal exhibits a logarithmic sparsity pattern in trajectory lengths. To tackle this problem, we augment the RL objective with an auxiliary task that guides part of the architecture to learn a valid probabilistic model as an inductive bias. We demonstrate that our method achieves state-of-the-art regret results against various baselines in experiments on standard hyperparameter optimisation tasks and also outperforms others in the real-world problems of mixed-integer programming tuning, antibody design, and logic synthesis for electronic design automation.