Symbolic discovery of optimization algorithms

X Chen, C Liang, D Huang, E Real… - Advances in neural …, 2023‏ - proceedings.neurips.cc
We present a method to formulate algorithm discovery as program search, and apply it to
discover optimization algorithms for deep neural network training. We leverage efficient …

Advances in neural architecture search

X Wang, W Zhu - National Science Review, 2024‏ - academic.oup.com
Automated machine learning (AutoML) has achieved remarkable success in automating the
non-trivial process of designing machine learning models. Among the focal areas of AutoML …

Differential neural architecture search for tabular data: Efficient neural network design for tabular datasets

M Medhage - 2024‏ - diva-portal.org
Artificial neural networks are some of the most powerful machine learning models and have
gained interest in the telecommunications domain as well as other fields and applications …

Learned Mixing Weights for Transferable Tabular Data Augmentation

T Shaharabany, L Wolf‏ - openreview.net
We present an architecture-agnostic method for tabular data augmentation, which mixes
pairs of samples from the training set. The mixing procedure is based on a set of per-feature …