# Guided Hyperparameter Tuning Through Visualization and Inference

arXiv: https://arxiv.org/abs/2105.11516 · HTML: https://mlsanity.com/paper/2105.11516/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 24 May 2021.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Joey NMT: A Minimalist NMT Toolkit for Novices](https://mlsanity.com/paper/1907.12484/) (2019)
- [A Generalized Framework for Population Based Training](https://mlsanity.com/paper/1902.01894/) (2019)
- [HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks](https://mlsanity.com/paper/2009.02078/) (2020)

## Built on by (most cited first, 1 of 1)

- [VisCUIT: Visual Auditor for Bias in CNN Image Classifier](https://mlsanity.com/paper/2204.05899/) (2022)

## Abstract (arXiv)

For deep learning practitioners, hyperparameter tuning for optimizing model performance can be a computationally expensive task. Though visualization can help practitioners relate hyperparameter settings to overall model performance, significant manual inspection is still required to guide the hyperparameter settings in the next batch of experiments. In response, we present a streamlined visualization system enabling deep learning practitioners to more efficiently explore, tune, and optimize hyperparameters in a batch of experiments. A key idea is to directly suggest more optimal hyperparameter values using a predictive mechanism. We then integrate this mechanism with current visualization practices for deep learning. Moreover, an analysis on the variance in a selected performance metric in the context of the model hyperparameters shows the impact that certain hyperparameters have on the performance metric. We evaluate the tool with a user study on deep learning model builders, finding that our participants have little issue adopting the tool and working with it as part of their workflow.