Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.12636 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916430378696704 |
|---|---|
| author | Bischoff, Sebastian Darcher, Alana Deistler, Michael Gao, Richard Gerken, Franziska Gloeckler, Manuel Haxel, Lisa Kapoor, Jaivardhan Lappalainen, Janne K Macke, Jakob H Moss, Guy Pals, Matthijs Pei, Felix Rapp, Rachel Sağtekin, A Erdem Schröder, Cornelius Schulz, Auguste Stefanidi, Zinovia Toyota, Shoji Ulmer, Linda Vetter, Julius |
| author_facet | Bischoff, Sebastian Darcher, Alana Deistler, Michael Gao, Richard Gerken, Franziska Gloeckler, Manuel Haxel, Lisa Kapoor, Jaivardhan Lappalainen, Janne K Macke, Jakob H Moss, Guy Pals, Matthijs Pei, Felix Rapp, Rachel Sağtekin, A Erdem Schröder, Cornelius Schulz, Auguste Stefanidi, Zinovia Toyota, Shoji Ulmer, Linda Vetter, Julius |
| contents | Generative models are invaluable in many fields of science because of their ability to capture high-dimensional and complicated distributions, such as photo-realistic images, protein structures, and connectomes. How do we evaluate the samples these models generate? This work aims to provide an accessible entry point to understanding popular sample-based statistical distances, requiring only foundational knowledge in mathematics and statistics. We focus on four commonly used notions of statistical distances representing different methodologies: Using low-dimensional projections (Sliced-Wasserstein; SW), obtaining a distance using classifiers (Classifier Two-Sample Tests; C2ST), using embeddings through kernels (Maximum Mean Discrepancy; MMD), or neural networks (Fréchet Inception Distance; FID). We highlight the intuition behind each distance and explain their merits, scalability, complexity, and pitfalls. To demonstrate how these distances are used in practice, we evaluate generative models from different scientific domains, namely a model of decision-making and a model generating medical images. We showcase that distinct distances can give different results on similar data. Through this guide, we aim to help researchers to use, interpret, and evaluate statistical distances for generative models in science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12636 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science Bischoff, Sebastian Darcher, Alana Deistler, Michael Gao, Richard Gerken, Franziska Gloeckler, Manuel Haxel, Lisa Kapoor, Jaivardhan Lappalainen, Janne K Macke, Jakob H Moss, Guy Pals, Matthijs Pei, Felix Rapp, Rachel Sağtekin, A Erdem Schröder, Cornelius Schulz, Auguste Stefanidi, Zinovia Toyota, Shoji Ulmer, Linda Vetter, Julius Machine Learning Generative models are invaluable in many fields of science because of their ability to capture high-dimensional and complicated distributions, such as photo-realistic images, protein structures, and connectomes. How do we evaluate the samples these models generate? This work aims to provide an accessible entry point to understanding popular sample-based statistical distances, requiring only foundational knowledge in mathematics and statistics. We focus on four commonly used notions of statistical distances representing different methodologies: Using low-dimensional projections (Sliced-Wasserstein; SW), obtaining a distance using classifiers (Classifier Two-Sample Tests; C2ST), using embeddings through kernels (Maximum Mean Discrepancy; MMD), or neural networks (Fréchet Inception Distance; FID). We highlight the intuition behind each distance and explain their merits, scalability, complexity, and pitfalls. To demonstrate how these distances are used in practice, we evaluate generative models from different scientific domains, namely a model of decision-making and a model generating medical images. We showcase that distinct distances can give different results on similar data. Through this guide, we aim to help researchers to use, interpret, and evaluate statistical distances for generative models in science. |
| title | A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.12636 |