Jovita Lukasik

A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction

2019 · arXiv (Cornell University)

In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest. In the past, NAS was hardly accessible to researchers without access to large-scale compute systems, due to …

An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance Prediction to Model Robustness

2024 · International Journal of Computer Vision

Abstract Zero-cost proxies are nowadays frequently studied and used to search for neural architectures. They show an impressive ability to predict the performance of architectures by making use of their untrained weights. These techniques allow …