Genealogical Population-Based Training for Hyperparameter Optimization

• URL: http://arxiv.org/abs/2109.14925v2
• Date: Sun, 9 Apr 2023 08:07:12 GMT
• Title: Genealogical Population-Based Training for Hyperparameter Optimization
• Authors: Antoine Scardigli and Paul Fournier and Matteo Vilucchio and David Naccache
• Abstract summary: We experimentally demonstrate that our method cuts down by 2 to 3 times the computational cost required. Our method is search-algorithm so that the inner search routine can be any search algorithm like TPE, GP, CMA or random search.
• Score: 1.0514231683620516
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: HyperParameter Optimization (HPO) aims at finding the best HyperParameters (HPs) of learning models, such as neural networks, in the fastest and most efficient way possible. Most recent HPO algorithms try to optimize HPs regardless of the model that obtained them, assuming that for different models, same HPs will produce very similar results. We break free from this paradigm and propose a new take on preexisting methods that we called Genealogical Population Based Training (GPBT). GPBT, via the shared histories of "genealogically"-related models, exploit the coupling of HPs and models in an efficient way. We experimentally demonstrate that our method cuts down by 2 to 3 times the computational cost required, generally allows a 1% accuracy improvement on computer vision tasks, and reduces the variance of the results by an order of magnitude, compared to the current algorithms. Our method is search-algorithm agnostic so that the inner search routine can be any search algorithm like TPE, GP, CMA or random search.

Related papers

• A Comparative Study of Hyperparameter Tuning Methods [0.0]
  Tree-structured Parzen Estimator (TPE), Genetic Search, and Random Search are evaluated across regression and classification tasks. Random Search excelled in regression tasks, while TPE was more effective for classification tasks.
  arXiv  Detail & Related papers  (2024-08-29T10:35:07Z)
• A Reinforcement Learning-assisted Genetic Programming Algorithm for Team Formation Problem Considering Person-Job Matching [70.28786574064694]
  A reinforcement learning-assisted genetic programming algorithm (RL-GP) is proposed to enhance the quality of solutions. The hyper-heuristic rules obtained through efficient learning can be utilized as decision-making aids when forming project teams.
  arXiv  Detail & Related papers  (2023-04-08T14:32:12Z)
• Enhancing Machine Learning Model Performance with Hyper Parameter Optimization: A Comparative Study [0.0]
  One of the most critical issues in machine learning is the selection of appropriate hyper parameters for training models. Hyper parameter optimization (HPO) is a popular topic that artificial intelligence studies have focused on recently. In this study, classical methods, such as grid, random search and Bayesian optimization, and population-based algorithms, such as genetic algorithms and particle swarm optimization, are discussed.
  arXiv  Detail & Related papers  (2023-02-14T10:12:10Z)
• Massively Parallel Genetic Optimization through Asynchronous Propagation of Populations [50.591267188664666]
  Propulate is an evolutionary optimization algorithm and software package for global optimization. We provide an MPI-based implementation of our algorithm, which features variants of selection, mutation, crossover, and migration. We find that Propulate is up to three orders of magnitude faster without sacrificing solution accuracy.
  arXiv  Detail & Related papers  (2023-01-20T18:17:34Z)
• Towards Learning Universal Hyperparameter Optimizers with Transformers [57.35920571605559]
  We introduce the OptFormer, the first text-based Transformer HPO framework that provides a universal end-to-end interface for jointly learning policy and function prediction. Our experiments demonstrate that the OptFormer can imitate at least 7 different HPO algorithms, which can be further improved via its function uncertainty estimates.
  arXiv  Detail & Related papers  (2022-05-26T12:51:32Z)
• 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)
• Evolving Reinforcement Learning Algorithms [186.62294652057062]
  We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
  arXiv  Detail & Related papers  (2021-01-08T18:55:07Z)
• Towards Optimally Efficient Tree Search with Deep Learning [76.64632985696237]
  This paper investigates the classical integer least-squares problem which estimates signals integer from linear models. The problem is NP-hard and often arises in diverse applications such as signal processing, bioinformatics, communications and machine learning. We propose a general hyper-accelerated tree search (HATS) algorithm by employing a deep neural network to estimate the optimal estimation for the underlying simplified memory-bounded A* algorithm.
  arXiv  Detail & Related papers  (2021-01-07T08:00:02Z)
• Practical and sample efficient zero-shot HPO [8.41866793161234]
  We provide an overview of available approaches and introduce two novel techniques to handle the problem. The first is based on a surrogate model and adaptively chooses pairs of dataset, configuration to query. The second is for settings where finding, tuning and testing a surrogate model is problematic, is a multi-fidelity technique combining HyperBand with submodular optimization.
  arXiv  Detail & Related papers  (2020-07-27T08:56:55Z)
• Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning [93.1435980666675]
  We show how optimistic exploration can be easily combined with state-of-the-art reinforcement learning algorithms. Our experiments demonstrate that optimistic exploration significantly speeds-up learning when there are penalties on actions.
  arXiv  Detail & Related papers  (2020-06-15T18:37:38Z)
• Hypernetwork-Based Augmentation [1.6752182911522517]
  We propose an efficient gradient-based search algorithm, called Hypernetwork-Based Augmentation (HBA) Our HBA uses a hypernetwork to approximate a population-based training algorithm. Our results show that HBA is competitive to the state-of-the-art methods in terms of both search speed and accuracy.
  arXiv  Detail & Related papers  (2020-06-11T10:36:39Z)

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.