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

Dumont, Vincent; Garner, Casey; Trivedi, Anuradha G.; Jones, Chelsea; Ganapati, Vidya; Mueller, Jacob L.; Perciano, Talita; Kiran, Mariam; Day, Marc

doi:10.1109/mlhpc54614.2021.00013

Cited by 6 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we hypothesize that the limited capacity of the neural network may not allow for joint reconstruction on all the examples of a larger dataset. Future work aims to use hyperparameter optimization [99] Results on the foam dataset demonstrate single-shot (n = 1) imaging for a small array of 29 LEDs under the assumption of a thin, approximately 2D specimen. In the case of 3D imaging, more measurements may be needed.…”

Section: Resultsmentioning

confidence: 99%

Data-Driven Computational Imaging for Scientific Discovery

Andrew¹,

Hu²,

Ganapati³

2022

Preprint

View full text Add to dashboard Cite

In computational imaging, hardware for signal sampling and software for object reconstruction are designed in tandem for improved capability. Examples of such systems include computed tomography (CT), magnetic resonance imaging (MRI), and superresolution microscopy. In contrast to more traditional cameras, in these devices, indirect measurements are taken and computational algorithms are used for reconstruction. This allows for advanced capabilities such as super-resolution or 3dimensional imaging, pushing forward the frontier of scientific discovery. However, these techniques generally require a large number of measurements, causing low throughput, motion artifacts, and/or radiation damage, limiting applications. Datadriven approaches to reducing the number of measurements needed have been proposed, but they predominately require a ground truth or reference dataset, which may be impossible to collect. This work outlines a self-supervised approach and explores the future work that is necessary to make such a technique usable for real applications. Light-emitting diode (LED) array microscopy, a modality that allows visualization of transparent objects in two and three dimensions with high resolution and field-of-view, is used as an illustrative example. We release our code at https://github.com/vganapati/LED_PVAE and our experimental data at https://doi.org/10.6084/m9.figshare.21232088.

show abstract

Section: Resultsmentioning

confidence: 99%

Data-Driven Computational Imaging for Scientific Discovery

Andrew¹,

Hu²,

Ganapati³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Once selected, these values were used throughout with all subsequent models. Methods are available to systematically explore hyperparameters (Dumont et al, 2021), however, it would take significant adaptation to use these approaches and to allow the hyperparameters to vary between models. This approach could be employed recursively by creating a new classifier not from the base LSTM but from the active-learning improved LSTMs.…”

Section: Discussionmentioning

confidence: 99%

An active learning convolutional neural network for predicting river flow in a human impacted system

Reed

2023

Front. Water

View full text Add to dashboard Cite

The South Platte river system contains a mixture of natural streams, reservoirs, and pipeline projects that redirect water to front range communities in Colorado. At many timepoints, a simple persistence model is the best predictor for flow from pipelines and reservoirs but at other times, flows change based on snowmelt and inputs such as reservoir fill rates, local weather, and anticipated demand. Here we find that a convolutional Long Short-Term Memory (LSTM) network is well suited to modeling flow in parts of this basin that are strongly impacted by water projects as well as ones that are relatively free from direct human modifications. Furthermore, it is found that including an active learning component in which separate Convolutional Neural Networks (CNNs) are used to classify and then select the data that is then used for training a convolutional LSTM network is advantageous. Models specific for each gauge are created by transfer of parameter from a base model and these gauge-specific models are then fine-tuned based a curated subset of training data. The result is accurate predictions for both natural flow and human influenced flow using only past river flow, reservoir capacity, and historical temperature data. In 14 of the 16 gauges modeled, the error in the prediction is reduced when using the combination of on-the-fly classification by CNN followed by analysis by either a persistence or convolutional LSTM model. The methods designed here could be applied broadly to other basins and to other situations where multiple models are needed to fit data at different times and locations.

show abstract

“…Measurement noise should ideally be propagated through the model, but computing required probability densities analytically is possible only for specific types of activation functions (Gast & Roth, 2018; Loquercio et al, 2020). Uncertainty quantification methods that exploit and extend such approaches to obtain confidence intervals for predictions are needed (Dumont et al, 2021).…”

Section: Opportunities For Advancement Of Water Quality MLmentioning

confidence: 99%

Can machine learning accelerate process understanding and decision‐relevant predictions of river water quality?

Varadharajan

Appling

Arora

et al. 2022

Hydrological Processes

Self Cite

View full text Add to dashboard Cite

The global decline of water quality in rivers and streams has resulted in a pressing need to design new watershed management strategies. Water quality can be affected by multiple stressors including population growth, land use change, global warming, and extreme events, with repercussions on human and ecosystem health. A scientific understanding of factors affecting riverine water quality and predictions at local to regional scales, and at sub‐daily to decadal timescales are needed for optimal management of watersheds and river basins. Here, we discuss how machine learning (ML) can enable development of more accurate, computationally tractable, and scalable models for analysis and predictions of river water quality. We review relevant state‐of‐the art applications of ML for water quality models and discuss opportunities to improve the use of ML with emerging computational and mathematical methods for model selection, hyperparameter optimization, incorporating process knowledge into ML models, improving explainablity, uncertainty quantification, and model‐data integration. We then present considerations for using ML to address water quality problems given their scale and complexity, available data and computational resources, and stakeholder needs. When combined with decades of process understanding, interdisciplinary advances in knowledge‐guided ML, information theory, data integration, and analytics can help address fundamental science questions and enable decision‐relevant predictions of riverine water quality.

show abstract

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

Cited by 6 publications

References 26 publications

Data-Driven Computational Imaging for Scientific Discovery

Data-Driven Computational Imaging for Scientific Discovery

An active learning convolutional neural network for predicting river flow in a human impacted system

Can machine learning accelerate process understanding and decision‐relevant predictions of river water quality?

Contact Info

Product

Resources

About