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.
In Syntology about another paper, arXiv:2003.06212: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: mentioned on GitHub). About another paper: this answer is about arXiv:2003.06212, while the archive credits arXiv:1711.09846.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Population Transformer (PopT) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Population Transformer (PopT)') - Maximum Entropy Population-Based Training · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Maximum Entropy Population-Based Training') - Neural-Guided Genetic Programming Population Seeding · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Neural-Guided Genetic Programming Population Seeding') - Shapley Population Variable Importance Measure estimator · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Shapley Population Variable Importance Measure estimator')
Origin paper of this answer, arXiv:2003.06212 (its page on this site · its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 18 · with a code link: 10 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 18 tagged: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 18 of 18, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
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 official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
Reducing Exploitability with Population Based Training 10 Aug 2022 · 1 repository · arXiv:2208.05083Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
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 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 5 pointer-only (licence)
-
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 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
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 official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified (of 18 harvested samples) · 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 0 ran · 1 unverified (of 1 harvested sample) · 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