Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

• URL: http://arxiv.org/abs/2002.02518v4
• Date: Fri, 4 Jun 2021 17:12:31 GMT
• Title: Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits
• Authors: Jack Parker-Holder and Vu Nguyen and Stephen Roberts
• Abstract summary: We introduce the first provably efficient Population-Based Bandits algorithm. PB2 uses a probabilistic model to guide the search in an efficient way. We show in a series of RL experiments that PB2 is able to achieve high performance with a modest computational budget.
• Score: 12.525529586816955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many of the recent triumphs in machine learning are dependent on well-tuned hyperparameters. This is particularly prominent in reinforcement learning (RL) where a small change in the configuration can lead to failure. Despite the importance of tuning hyperparameters, it remains expensive and is often done in a naive and laborious way. A recent solution to this problem is Population Based Training (PBT) which updates both weights and hyperparameters in a single training run of a population of agents. PBT has been shown to be particularly effective in RL, leading to widespread use in the field. However, PBT lacks theoretical guarantees since it relies on random heuristics to explore the hyperparameter space. This inefficiency means it typically requires vast computational resources, which is prohibitive for many small and medium sized labs. In this work, we introduce the first provably efficient PBT-style algorithm, Population-Based Bandits (PB2). PB2 uses a probabilistic model to guide the search in an efficient way, making it possible to discover high performing hyperparameter configurations with far fewer agents than typically required by PBT. We show in a series of RL experiments that PB2 is able to achieve high performance with a modest computational budget.

Related papers

• Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement Learning [10.164982368785854]
  Generalized Population-Based Training (GPBT) and Pairwise Learning (PL) PL employs a comprehensive pairwise strategy to identify performance differentials and provide holistic guidance to underperforming agents.
  arXiv  Detail & Related papers  (2024-04-12T04:23:20Z)
• Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search [62.997667081978825]
  We show that simultaneously training and mixing neural networks is a promising way to conduct Neural Architecture Search (NAS) We propose PBT-NAS, an adaptation of PBT to NAS where architectures are improved during training by replacing poorly-performing networks in a population with the result of mixing well-performing ones and inheriting the weights using the shrink-perturb technique.
  arXiv  Detail & Related papers  (2023-07-28T15:29:52Z)
• PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning [49.92394599459274]
  We propose PriorBand, an HPO algorithm tailored to Deep Learning (DL) pipelines. We show its robustness across a range of DL benchmarks and show its gains under informative expert input and against poor expert beliefs.
  arXiv  Detail & Related papers  (2023-06-21T16:26:14Z)
• Multi-Objective Population Based Training [62.997667081978825]
  Population Based Training (PBT) is an efficient hyperparameter optimization algorithm. In this work, we introduce a multi-objective version of PBT, MO-PBT.
  arXiv  Detail & Related papers  (2023-06-02T10:54:24Z)
• AutoRL Hyperparameter Landscapes [69.15927869840918]
  Reinforcement Learning (RL) has shown to be capable of producing impressive results, but its use is limited by the impact of its hyperparameters on performance. We propose an approach to build and analyze these hyperparameter landscapes not just for one point in time but at multiple points in time throughout training. This supports the theory that hyperparameters should be dynamically adjusted during training and shows the potential for more insights on AutoRL problems that can be gained through landscape analyses.
  arXiv  Detail & Related papers  (2023-04-05T12:14:41Z)
• Automating DBSCAN via Deep Reinforcement Learning [73.82740568765279]
  We propose a novel Deep Reinforcement Learning guided automatic DBSCAN parameters search framework, namely DRL-DBSCAN. The framework models the process of adjusting the parameter search direction by perceiving the clustering environment as a Markov decision process. The framework consistently improves DBSCAN clustering accuracy by up to 26% and 25% respectively.
  arXiv  Detail & Related papers  (2022-08-09T04:40:11Z)
• Bayesian Generational Population-Based Training [35.70338636901159]
  Population-Based Training (PBT) has led to impressive performance in several large scale settings. We introduce two new innovations in PBT-style methods. We show that these innovations lead to large performance gains.
  arXiv  Detail & Related papers  (2022-07-19T16:57:38Z)
• Parameter-Efficient Sparsity for Large Language Models Fine-Tuning [63.321205487234074]
  We propose a. sparse-efficient Sparse Training (PST) method to reduce the number of trainable parameters during sparse-aware training. Experiments with diverse networks (i.e., BERT, RoBERTa and GPT-2) demonstrate PST performs on par or better than previous sparsity methods.
  arXiv  Detail & Related papers  (2022-05-23T02:43:45Z)
• Faster Improvement Rate Population Based Training [7.661301899629696]
  This paper presents Faster Improvement Rate PBT (FIRE PBT) which addresses the problem of Population Based Training (PBT) We derive a novel fitness metric and use it to make some of the population members focus on long-term performance. Experiments show that FIRE PBT is able to outperform PBT on the ImageNet benchmark and match the performance of networks that were trained with a hand-tuned learning rate schedule.
  arXiv  Detail & Related papers  (2021-09-28T15:30:55Z)
• Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL [12.135280422000635]
  We introduce a new efficient hierarchical approach for optimizing both continuous and categorical variables. We show that explicitly modelling dependence between data augmentation and other hyper parameters improves generalization.
  arXiv  Detail & Related papers  (2021-06-30T08:15:59Z)
• On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning [27.36718899899319]
  Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL typically requires significant human expertise before it can be applied to new problems and domains.
  arXiv  Detail & Related papers  (2021-02-26T18:57:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.