Towards Learning Universal Hyperparameter Optimizers with Transformers
- URL: http://arxiv.org/abs/2205.13320v1
- Date: Thu, 26 May 2022 12:51:32 GMT
- Title: Towards Learning Universal Hyperparameter Optimizers with Transformers
- Authors: Yutian Chen, Xingyou Song, Chansoo Lee, Zi Wang, Qiuyi Zhang, David
Dohan, Kazuya Kawakami, Greg Kochanski, Arnaud Doucet, Marc'aurelio Ranzato,
Sagi Perel, Nando de Freitas
- Abstract summary: 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.
- Score: 57.35920571605559
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Meta-learning hyperparameter optimization (HPO) algorithms from prior
experiments is a promising approach to improve optimization efficiency over
objective functions from a similar distribution. However, existing methods are
restricted to learning from experiments sharing the same set of
hyperparameters. In this paper, 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 when trained on
vast tuning data from the wild. Our extensive experiments demonstrate that the
OptFormer can imitate at least 7 different HPO algorithms, which can be further
improved via its function uncertainty estimates. Compared to a Gaussian
Process, the OptFormer also learns a robust prior distribution for
hyperparameter response functions, and can thereby provide more accurate and
better calibrated predictions. This work paves the path to future extensions
for training a Transformer-based model as a general HPO optimizer.
Related papers
- Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values.
We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO)
Our method is versatile and can be readily adapted to various preference optimization frameworks.
arXiv Detail & Related papers (2024-06-04T20:33:22Z) - Deep Ranking Ensembles for Hyperparameter Optimization [9.453554184019108]
We present a novel method that meta-learns neural network surrogates optimized for ranking the configurations' performances while modeling their uncertainty via ensembling.
In a large-scale experimental protocol comprising 12 baselines, 16 HPO search spaces and 86 datasets/tasks, we demonstrate that our method achieves new state-of-the-art results in HPO.
arXiv Detail & Related papers (2023-03-27T13:52:40Z) - Agent-based Collaborative Random Search for Hyper-parameter Tuning and
Global Function Optimization [0.0]
This paper proposes an agent-based collaborative technique for finding near-optimal values for any arbitrary set of hyper- parameters in a machine learning model.
The behavior of the presented model, specifically against the changes in its design parameters, is investigated in both machine learning and global function optimization applications.
arXiv Detail & Related papers (2023-03-03T21:10:17Z) - Sparse high-dimensional linear regression with a partitioned empirical
Bayes ECM algorithm [62.997667081978825]
We propose a computationally efficient and powerful Bayesian approach for sparse high-dimensional linear regression.
Minimal prior assumptions on the parameters are used through the use of plug-in empirical Bayes estimates.
The proposed approach is implemented in the R package probe.
arXiv Detail & Related papers (2022-09-16T19:15:50Z) - Multi-objective hyperparameter optimization with performance uncertainty [62.997667081978825]
This paper presents results on multi-objective hyperparameter optimization with uncertainty on the evaluation of Machine Learning algorithms.
We combine the sampling strategy of Tree-structured Parzen Estimators (TPE) with the metamodel obtained after training a Gaussian Process Regression (GPR) with heterogeneous noise.
Experimental results on three analytical test functions and three ML problems show the improvement over multi-objective TPE and GPR.
arXiv Detail & Related papers (2022-09-09T14:58:43Z) - Pre-training helps Bayesian optimization too [49.28382118032923]
We seek an alternative practice for setting functional priors.
In particular, we consider the scenario where we have data from similar functions that allow us to pre-train a tighter distribution a priori.
Our results show that our method is able to locate good hyper parameters at least 3 times more efficiently than the best competing methods.
arXiv Detail & Related papers (2022-07-07T04:42:54Z) - Enhancing Explainability of Hyperparameter Optimization via Bayesian
Algorithm Execution [13.037647287689438]
We study the combination of HPO with interpretable machine learning (IML) methods such as partial dependence plots.
We propose a modified HPO method which efficiently searches for optimum global predictive performance.
Our method returns more reliable explanations of the underlying black-box without a loss of optimization performance.
arXiv Detail & Related papers (2022-06-11T07:12:04Z) - Surrogate modeling for Bayesian optimization beyond a single Gaussian
process [62.294228304646516]
We propose a novel Bayesian surrogate model to balance exploration with exploitation of the search space.
To endow function sampling with scalability, random feature-based kernel approximation is leveraged per GP model.
To further establish convergence of the proposed EGP-TS to the global optimum, analysis is conducted based on the notion of Bayesian regret.
arXiv Detail & Related papers (2022-05-27T16:43:10Z) - Improving Hyperparameter Optimization by Planning Ahead [3.8673630752805432]
We propose a novel transfer learning approach, defined within the context of model-based reinforcement learning.
We propose a new variant of model predictive control which employs a simple look-ahead strategy as a policy.
Our experiments on three meta-datasets comparing to state-of-the-art HPO algorithms show that the proposed method can outperform all baselines.
arXiv Detail & Related papers (2021-10-15T11:46:14Z) - Few-Shot Bayesian Optimization with Deep Kernel Surrogates [7.208515071018781]
We propose a few-shot learning problem in which we train a shared deep surrogate model to adapt to the response function of a new task.
We propose the use of a deep kernel network for a Gaussian process surrogate that is meta-learned in an end-to-end fashion.
As a result, the novel few-shot optimization of our deep kernel surrogate leads to new state-of-the-art results at HPO.
arXiv Detail & Related papers (2021-01-19T15:00:39Z)
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.