# AutoML in Heavily Constrained Applications

arXiv: https://arxiv.org/abs/2306.16913 · HTML: https://mlsanity.com/paper/2306.16913/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 78 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 29 of 29)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning](https://mlsanity.com/paper/2007.04074/) (2020)
- [Bayesian Optimization with Unknown Constraints](https://mlsanity.com/paper/1403.5607/) (2014)
- [Hyperparameter Importance Across Datasets](https://mlsanity.com/paper/1710.04725/) (2017)
- [An ADMM Based Framework for AutoML Pipeline Configuration](https://mlsanity.com/paper/1905.00424/) (2019)
- [Fair Bayesian Optimization](https://mlsanity.com/paper/2006.05109/) (2020)
- [VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition](https://mlsanity.com/paper/2107.08861/) (2021)
- [Towards Green Automated Machine Learning: Status Quo and Future Directions](https://mlsanity.com/paper/2111.05850/) (2021)
- [Emulation of physical processes with Emukit](https://mlsanity.com/paper/2110.13293/) (2021)
- [Overton: A Data System for Monitoring and Improving Machine-Learned Products](https://mlsanity.com/paper/1909.05372/) (2019)
- [SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle](https://mlsanity.com/paper/1909.02976/) (2019)
- [GPflowOpt: A Bayesian Optimization Library using TensorFlow](https://mlsanity.com/paper/1711.03845/) (2017)
- [Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters](https://mlsanity.com/paper/1908.06674/) (2019)
- [KeystoneML: Optimizing Pipelines for Large-Scale Advanced Analytics](https://mlsanity.com/paper/1610.09451/) (2016)
- [FairPrep: Promoting Data to a First-Class Citizen in Studies on Fairness-Enhancing Interventions](https://mlsanity.com/paper/1911.12587/) (2019)
- [Helix: Holistic Optimization for Accelerating Iterative Machine Learning](https://mlsanity.com/paper/1812.05762/) (2018)
- [Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search](https://mlsanity.com/paper/2106.13861/) (2021)
- [Real-Time Machine Learning: The Missing Pieces](https://mlsanity.com/paper/1703.03924/) (2017)
- [DiffML: End-to-end Differentiable ML Pipelines](https://mlsanity.com/paper/2207.01269/) (2022)
- [An Efficient Asynchronous Batch Bayesian Optimization Approach for Analog Circuit Synthesis](https://mlsanity.com/paper/2106.14683/) (2021)
- [A Cost-based Optimizer for Gradient Descent Optimization](https://mlsanity.com/paper/1703.09193/) (2017)

## Built on by (most cited first, 3 of 3)

- [Position: A Call to Action for a Human-Centered AutoML Paradigm](https://mlsanity.com/paper/2406.03348/) (2024)
- [REMSA: Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent](https://mlsanity.com/paper/2511.17442/) (2025)
- [VirnyFlow: Optimizing ML Pipelines for Accuracy, Fairness, and Stability at Scale](https://mlsanity.com/paper/2506.01584/) (2025)

## Abstract (arXiv)

Optimizing a machine learning pipeline for a task at hand requires careful configuration of various hyperparameters, typically supported by an AutoML system that optimizes the hyperparameters for the given training dataset. Yet, depending on the AutoML system's own second-order meta-configuration, the performance of the AutoML process can vary significantly. Current AutoML systems cannot automatically adapt their own configuration to a specific use case. Further, they cannot compile user-defined application constraints on the effectiveness and efficiency of the pipeline and its generation. In this paper, we propose CAML, which uses meta-learning to automatically adapt its own AutoML parameters, such as the search strategy, the validation strategy, and the search space, for a task at hand. The dynamic AutoML strategy of CAML takes user-defined constraints into account and obtains constraint-satisfying pipelines with high predictive performance.