Explicit and data-Efficient Encoding via Gradient Flow

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Flouris, Kyriakos, Volokitin, Anna, Bredell, Gustav, Konukoglu, Ender
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916551997784064
author Flouris, Kyriakos
Volokitin, Anna
Bredell, Gustav
Konukoglu, Ender
author_facet Flouris, Kyriakos
Volokitin, Anna
Bredell, Gustav
Konukoglu, Ender
contents The autoencoder model typically uses an encoder to map data to a lower dimensional latent space and a decoder to reconstruct it. However, relying on an encoder for inversion can lead to suboptimal representations, particularly limiting in physical sciences where precision is key. We introduce a decoder-only method using gradient flow to directly encode data into the latent space, defined by ordinary differential equations (ODEs). This approach eliminates the need for approximate encoder inversion. We train the decoder via the adjoint method and show that costly integrals can be avoided with minimal accuracy loss. Additionally, we propose a $2^{nd}$ order ODE variant, approximating Nesterov's accelerated gradient descent for faster convergence. To handle stiff ODEs, we use an adaptive solver that prioritizes loss minimization, improving robustness. Compared to traditional autoencoders, our method demonstrates explicit encoding and superior data efficiency, which is crucial for data-scarce scenarios in the physical sciences. Furthermore, this work paves the way for integrating machine learning into scientific workflows, where precise and efficient encoding is critical. \footnote{The code for this work is available at \url{https://github.com/k-flouris/gfe}.}
format Preprint
id arxiv_https___arxiv_org_abs_2412_00864
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Explicit and data-Efficient Encoding via Gradient Flow
Flouris, Kyriakos
Volokitin, Anna
Bredell, Gustav
Konukoglu, Ender
Machine Learning
Artificial Intelligence
Optimization and Control
Computational Physics
The autoencoder model typically uses an encoder to map data to a lower dimensional latent space and a decoder to reconstruct it. However, relying on an encoder for inversion can lead to suboptimal representations, particularly limiting in physical sciences where precision is key. We introduce a decoder-only method using gradient flow to directly encode data into the latent space, defined by ordinary differential equations (ODEs). This approach eliminates the need for approximate encoder inversion. We train the decoder via the adjoint method and show that costly integrals can be avoided with minimal accuracy loss. Additionally, we propose a $2^{nd}$ order ODE variant, approximating Nesterov's accelerated gradient descent for faster convergence. To handle stiff ODEs, we use an adaptive solver that prioritizes loss minimization, improving robustness. Compared to traditional autoencoders, our method demonstrates explicit encoding and superior data efficiency, which is crucial for data-scarce scenarios in the physical sciences. Furthermore, this work paves the way for integrating machine learning into scientific workflows, where precise and efficient encoding is critical. \footnote{The code for this work is available at \url{https://github.com/k-flouris/gfe}.}
title Explicit and data-Efficient Encoding via Gradient Flow
topic Machine Learning
Artificial Intelligence
Optimization and Control
Computational Physics
url https://arxiv.org/abs/2412.00864