dissertation · Papyrus : Institutional Repository (Université de Montréal) · 2023
Model-based hyperparameter optimization
Crouther, Paul
Cited by 0Open access
Abstract
The primary goal of this work is to propose a methodology for discovering hyperparameters. \nHyperparameters aid systems in convergence when well-tuned and handcrafted. However, \nto this end, poorly chosen hyperparameters leave practitioners in limbo, between concerns \nwith implementation or improper choice in hyperparameter and system configuration. We \nspecifically analyze the choice of learning rate in stochastic gradient descent (SGD), a popular \nalgorithm. As a secondary goal, we attempt the discovery of fixed points using smoothing of \nthe loss landscape by exploiting assumptions about its distribution to improve the update \nrule in SGD. Smoothing of the loss landscape has been shown to make convergence possible in \nlarge-scale systems and difficult black-box optimization problems. However, we use stochastic \nvalue gradients (SVG) to smooth the loss landscape by learning a surrogate model and then \nbackpropagate through this model to discover fixed points on the real task SGD is trying to \nsolve. Additionally, we construct a gym environment for testing model-free algorithms, such \nas Proximal Policy Optimization (PPO) as a hyperparameter optimizer for SGD. For tasks, \nwe focus on a toy problem and analyze the convergence of SGD on MNIST using model-free \nand model-based reinforcement learning methods for control. The model is learned from \nthe parameters of the true optimizer and used specifically for learning rates rather than for \nprediction. In experiments, we perform in an online and offline setting. In the online setting, \nwe learn a surrogate model alongside the true optimizer, where hyperparameters are tuned \nin real-time for the true optimizer. In the offline setting, we show that there is more potential \nin the model-based learning methodology than in the model-free configuration due to this \nsurrogate model that smooths out the loss landscape and makes for more helpful gradients \nduring backpropagation.
Cite this paper
Crouther, P. (2023). Model-based hyperparameter optimization. Papyrus : Institutional Repository (Université de Montréal).
Crouther, Paul. “Model-based hyperparameter optimization.” Papyrus : Institutional Repository (Université de Montréal), 2023.
Crouther, Paul. 2023. “Model-based hyperparameter optimization.” Papyrus : Institutional Repository (Université de Montréal).
Crouther, P. (2023) ‘Model-based hyperparameter optimization’, Papyrus : Institutional Repository (Université de Montréal).
@phdthesis{crouther2023model,
title = {{Model-based hyperparameter optimization}},
author = {Crouther, Paul},
school = {Papyrus : Institutional Repository (Université de Montréal)},
year = {2023}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.