# ROMO: Retrieval-enhanced Offline Model-based Optimization

arXiv: https://arxiv.org/abs/2310.07560 · HTML: https://mlsanity.com/paper/2310.07560/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 11 Oct 2023.

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [Scalable Bayesian Optimization Using Deep Neural Networks](https://mlsanity.com/paper/1502.05700/) (2015)
- [Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks](https://mlsanity.com/paper/1905.13210/) (2019)
- [A Variational Perspective on Diffusion-Based Generative Models and Score Matching](https://mlsanity.com/paper/2106.02808/) (2021)
- [Dense Text Retrieval based on Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.14876/) (2022)
- [Conditioning by adaptive sampling for robust design](https://mlsanity.com/paper/1901.10060/) (2019)
- [Neural Nearest Neighbors Networks](https://mlsanity.com/paper/1810.12575/) (2018)
- [Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization](https://mlsanity.com/paper/2202.08450/) (2022)
- [Conservative Objective Models for Effective Offline Model-Based Optimization](https://mlsanity.com/paper/2107.06882/) (2021)
- [Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes](https://mlsanity.com/paper/1706.10239/) (2017)
- [Model Inversion Networks for Model-Based Optimization](https://mlsanity.com/paper/1912.13464/) (2019)
- [Safe Controller Optimization for Quadrotors with Gaussian Processes](https://mlsanity.com/paper/1509.01066/) (2015)
- [Diffusion Models for Black-Box Optimization](https://mlsanity.com/paper/2306.07180/) (2023)
- [Autofocused oracles for model-based design](https://mlsanity.com/paper/2006.08052/) (2020)
- [DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning](https://mlsanity.com/paper/2102.11492/) (2021)
- [Retrieval-Enhanced Machine Learning](https://mlsanity.com/paper/2205.01230/) (2022)
- [Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data](https://mlsanity.com/paper/1807.00311/) (2018)
- [Generative Pretraining for Black-Box Optimization](https://mlsanity.com/paper/2206.10786/) (2022)
- [Data-Driven Offline Decision-Making via Invariant Representation Learning](https://mlsanity.com/paper/2211.11349/) (2022)
- [Data-efficient Learning of Morphology and Controller for a Microrobot](https://mlsanity.com/paper/1905.01334/) (2019)
- [Retrieval & Interaction Machine for Tabular Data Prediction](https://mlsanity.com/paper/2108.05252/) (2021)
- [Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples](https://mlsanity.com/paper/1802.09502/) (2018)
- [Assigning Agents to Increase Network-Based Neighborhood Diversity](https://mlsanity.com/paper/2301.02876/) (2023)

## Built on by (most cited first, 1 of 1)

- [Generative Adversarial Model-Based Optimization via Source Critic Regularization](https://mlsanity.com/paper/2402.06532/) (2024)

## Abstract (arXiv)

Data-driven black-box model-based optimization (MBO) problems arise in a great number of practical application scenarios, where the goal is to find a design over the whole space maximizing a black-box target function based on a static offline dataset. In this work, we consider a more general but challenging MBO setting, named constrained MBO (CoMBO), where only part of the design space can be optimized while the rest is constrained by the environment. A new challenge arising from CoMBO is that most observed designs that satisfy the constraints are mediocre in evaluation. Therefore, we focus on optimizing these mediocre designs in the offline dataset while maintaining the given constraints rather than further boosting the best observed design in the traditional MBO setting. We propose retrieval-enhanced offline model-based optimization (ROMO), a new derivable forward approach that retrieves the offline dataset and aggregates relevant samples to provide a trusted prediction, and use it for gradient-based optimization. ROMO is simple to implement and outperforms state-of-the-art approaches in the CoMBO setting. Empirically, we conduct experiments on a synthetic Hartmann (3D) function dataset, an industrial CIO dataset, and a suite of modified tasks in the Design-Bench benchmark. Results show that ROMO performs well in a wide range of constrained optimization tasks.