# A Generalized Framework for Population Based Training

arXiv: https://arxiv.org/abs/1902.01894 · HTML: https://mlsanity.com/paper/1902.01894/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2019.

## Built on by (most cited first, 22 of 22)

- [Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges](https://mlsanity.com/paper/2107.05847/) (2021)
- [Hyperparameters in Reinforcement Learning and How To Tune Them](https://mlsanity.com/paper/2306.01324/) (2023)
- [FederatedScope: A Flexible Federated Learning Platform for Heterogeneity](https://mlsanity.com/paper/2204.05011/) (2022)
- [AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks](https://mlsanity.com/paper/2306.08107/) (2023)
- [Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity](https://mlsanity.com/paper/2207.14138/) (2022)
- [Automated Deep Learning: Neural Architecture Search Is Not the End](https://mlsanity.com/paper/2112.09245/) (2021)
- [Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL](https://mlsanity.com/paper/2106.15883/) (2021)
- [AutoRL Hyperparameter Landscapes](https://mlsanity.com/paper/2304.02396/) (2023)
- [GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning](https://mlsanity.com/paper/2106.06232/) (2021)
- [Learning Diverse Risk Preferences in Population-based Self-play](https://mlsanity.com/paper/2305.11476/) (2023)
- [Episodic Policy Gradient Training](https://mlsanity.com/paper/2112.01853/) (2021)
- [High-Throughput Virtual Screening of Small Molecule Inhibitors for SARS-CoV-2 Protein Targets with Deep Fusion Models](https://mlsanity.com/paper/2104.04547/) (2021)
- [AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop](https://mlsanity.com/paper/2111.15317/) (2021)
- [Guided Hyperparameter Tuning Through Visualization and Inference](https://mlsanity.com/paper/2105.11516/) (2021)
- [Composing Efficient, Robust Tests for Policy Selection](https://mlsanity.com/paper/2306.07372/) (2023)
- [A hyperparameter-tuning approach to automated inverse planning](https://mlsanity.com/paper/2105.07024/) (2021)
- [Robust Temporal Ensembling for Learning with Noisy Labels](https://mlsanity.com/paper/2109.14563/) (2021)
- [Asynchronously Trained Distributed Topographic Maps](https://mlsanity.com/paper/2301.08379/) (2023)
- [Beyond Trend Following: Deep Learning for Market Trend Prediction](https://mlsanity.com/paper/2407.13685/) (2024)
- [HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks](https://mlsanity.com/paper/2504.19382/) (2025)
- [Analysis of Hyperparameter Optimization Effects on Lightweight Deep Models for Real-Time Image Classification](https://mlsanity.com/paper/2507.23315/) (2025)
- [Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search](https://mlsanity.com/paper/2609.02172/) (2026)

## Abstract (arXiv)

Population Based Training (PBT) is a recent approach that jointly optimizes neural network weights and hyperparameters which periodically copies weights of the best performers and mutates hyperparameters during training. Previous PBT implementations have been synchronized glass-box systems. We propose a general, black-box PBT framework that distributes many asynchronous "trials" (a small number of training steps with warm-starting) across a cluster, coordinated by the PBT controller. The black-box design does not make assumptions on model architectures, loss functions or training procedures. Our system supports dynamic hyperparameter schedules to optimize both differentiable and non-differentiable metrics. We apply our system to train a state-of-the-art WaveNet generative model for human voice synthesis. We show that our PBT system achieves better accuracy, less sensitivity and faster convergence compared to existing methods, given the same computational resource.