From the 1 of 4 linked papers with an AI index.
4 papers
The Challenger: When Do New Data Sources Justify Switching Machine Learning Models?
Vassilis Digalakis, Christophe Pérignon, Sébastien Saurin +1
The paper proposes a framework for deciding when to replace an existing predictive model with a new one that uses additional data features, linking learning‑curve dynamics to the e…
ML Compass: Navigating Capability, Cost, and Compliance Trade-offs in AI Model Deployment
Vassilis Digalakis, Ramayya Krishnan, Gonzalo Martin Fernandez +1
We study how organizations should select among competing AI models when user utility, deployment costs, and compliance requirements jointly matter. Widely used capability leaderboa…
Interpretable Time Series Autoregression for Periodicity Quantification
Xinyu Chen, Vassilis Digalakis, Lijun Ding +2
Time series autoregression (AR) is a classical tool for modeling auto-correlations and periodic structures in real-world systems. We revisit this model from an interpretable machin…
Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences
Dimitris Bertsimas, Vassilis Digalakis, Yu Ma +1
We consider the problem of retraining machine learning (ML) models when new batches of data become available. Existing approaches greedily optimize for predictive power independent…