Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 1847268

HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization

Dumont, Vincent·Garner, Casey·Trivedi, Anuradha·Ganapati, Vidya·Mueller, Juliane·Perciano, Talita·Kiran, Mariam·Day, Marc (ORCID:0000000217113963)
View original source ↗Export metadata ↓

Abstract

We present a new software, HYPPO, that enables the automatic tuning of hyperparameters of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) methods, HYPPO uses adaptive surrogate models and directly accounts for uncertainty in model predictions to find accurate and reliable models that make robust predictions. Using asynchronous nested parallelism, we are able to significantly alleviate the computational burden of training complex architectures and quantifying the uncertainty. HYPPO is implemented in Python and can be used with both TensorFlow and PyTorch libraries. We demonstrate various software features on time-series prediction and image classification problems as well as a scientific application in computed tomography image reconstruction. Finally, we show that (1) we can reduce by an order of magnitude the number of evaluations necessary to find the most optimal region in the hyperparameter space and (2) we can reduce by two orders of magnitude the throughput for such HPO process to complete.

Explore related subjects

adaptation modelscomputational modelingMATHEMATICS AND COMPUTINGparallel processingpredictive modelsstochastic processestraininguncertainty

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Dumont, Vincent, Garner, Casey, Trivedi, Anuradha, Ganapati, Vidya, Mueller, Juliane, Perciano, Talita, Kiran, Mariam, Day, Marc (ORCID:0000000217113963). 2021-12-27. HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization. https://doi.org/10.1109/mlhpc54614.2021.00013

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2025

Learning with Adaptive Conservativeness for Distributionally Robust Optimization: Incentive Design for Voltage Regulation

Information asymmetry between the Distribution System Operator (DSO) and Distributed Energy Resource Aggregators (DERAs) obstructs designing effective incentives for voltage regulation. To capture this effect, we employ a Stackelberg game-theoretic framework, where the DSO seeks to overcome the information asymmetry and refine its incentive strategies by learning from DERA behavior over multiple iterations. We introduce a model-based online learning algorithm for the DSO, aimed at inferring the relationship between incentives and DERA responses. Given the uncertain nature of these responses, we also propose a distributionally robust incentive design model to control the probability of voltage regulation failure and then reformulate it into a convex problem. This model allows the DSO to periodically revise distribution assumptions on uncertain parameters in the decision model of the DERA. Finally, we present a gradient-based method that permits the DSO to adaptively modify its conservativeness level, measured by the size of a Wasserstein metric-based ambiguity set, according to historical voltage regulation performance. The effectiveness of our proposed method is demonstrated through numerical experiments.

adaptation models↗