3 papers
cs.LG2026
The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning
Kareem M. Gameel, Ihor Neporozhnii, Sjoerd Hoogland +1
In scientific machine learning, -learning trains models on residual errors relative to physical baselines, assuming that more accurate baselines with smaller residual scales inh…
physics.chem-ph2026
Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs
Ihor Neporozhnii, Sjoerd Hoogland, Oleksandr Voznyy
Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately simulate materials and molecules. Incorpor…
cs.LG2024
Efficient Biological Data Acquisition through Inference Set Design
Ihor Neporozhnii, Julien Roy, Emmanuel Bengio +1
In drug discovery, highly automated high-throughput laboratories are used to screen a large number of compounds in search of effective drugs. These experiments are expensive, so on…