Rich Caruana

Efficient Forward Architecture Search

2019 · arXiv (Cornell University)

We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers. The added shortcut connections effectively perform gradient boosting on the augmented layers. The proposed algorithm is motivated …

Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?

2023 · arXiv (Cornell University)

Missing values are a fundamental problem in data science. Many datasets have missing values that must be properly handled because the way missing values are treated can have large impact on the resulting machine learning …

LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs

2023 · arXiv (Cornell University)

We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can provide comprehensive model-level …

Improving Document Ranking with Dual Word Embeddings

2016

This paper investigates the popular neural word embedding method Word2vec as a source of evidence in document ranking. In contrast to NLP applications of word2vec, which tend to use only the input embeddings, we retain …