Methods › General › Hyperparameter Search › Population Based Training
Population Based Training
Introduced by Max Jaderberg et al. in Population Based Training of Neural Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Population Based Training, or PBT, is an optimization method for finding parameters and hyperparameters, and extends upon parallel search methods and sequential optimisation methods. It leverages information sharing across a population of concurrently running optimisation processes, and allows for online propagation/transfer of parameters and hyperparameters between members of the population based on their performance. Furthermore, unlike most other adaptation schemes, the method is capable of performing online adaptation of hyperparameters -- which can be particularly important in problems with highly non-stationary learning dynamics, such as reinforcement learning settings. PBT is decentralised and asynchronous, although it could also be executed semi-serially or with partial synchrony if there is a binding budget constraint.
Papers archive 2025-07-28
18 shown of 18, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search 28 Jul 2023 · 1 repository · arXiv:2307.15621
-
Multi-Objective Population Based Training 2 Jun 2023 · 1 repository · arXiv:2306.01436Syntology ran 0 of 1 samples · 1 unverified
-
Reducing Exploitability with Population Based Training 10 Aug 2022 · 1 repository · arXiv:2208.05083Syntology ran 0 of 5 samples · 5 unverified
-
Faster Improvement Rate Population Based Training 28 Sep 2021 · 0 repositories · arXiv:2109.13800
-
Automated Graph Learning via Population Based Self-Tuning GCN 9 Jul 2021 · 0 repositories · arXiv:2107.04713
-
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL 30 Jun 2021 · 0 repositories · arXiv:2106.15883
-
Training Learned Optimizers with Randomly Initialized Learned Optimizers 14 Jan 2021 · 0 repositories · arXiv:2101.07367
-
Population Based Training for Data Augmentation and Regularization in Speech Recognition 8 Oct 2020 · 0 repositories · arXiv:2010.03899
-
Improving 3D Object Detection through Progressive Population Based Augmentation 2 Apr 2020 · 0 repositories · arXiv:2004.00831
-
Accelerating and Improving AlphaZero Using Population Based Training 13 Mar 2020 · 1 repository · arXiv:2003.06212
-
DADA: Differentiable Automatic Data Augmentation 8 Mar 2020 · 1 repository · arXiv:2003.03780Syntology ran 5 of 9 samples · 4 unverified
-
Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing 12 Feb 2020 · 0 repositories · arXiv:2002.05229
-
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits 6 Feb 2020 · 2 repositories · arXiv:2002.02518Syntology ran 2 of 5 samples · 3 unverified
-
Fast Efficient Hyperparameter Tuning for Policy Gradient Methods 1 Dec 2019 · 1 repository
-
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules 14 May 2019 · 3 repositories · arXiv:1905.05393Syntology ran 0 of 18 samples · 18 unverified · 18 pointer-only (licence)
-
Semi-supervised and Population Based Training for Voice Commands Recognition 10 May 2019 · 0 repositories · arXiv:1905.04230
-
Fast Efficient Hyperparameter Tuning for Policy Gradients 18 Feb 2019 · 1 repository · arXiv:1902.06583Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
-
Population Based Training of Neural Networks 27 Nov 2017 · 9 repositories · arXiv:1711.09846
Tasks archive 2025-07-28
20 shown of 32 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections