3 papers
stat.ML2025
Sparse Multiple Kernel Learning: Alternating Best Response and Semidefinite Relaxations
Dimitris Bertsimas, Caio de Prospero Iglesias, Nicholas A. G. Johnson
We study Sparse Multiple Kernel Learning (SMKL), which is the problem of selecting a sparse convex combination of prespecified kernels for support vector binary classification. Unl…
stat.ML2024
Predictive Low Rank Matrix Learning under Partial Observations: Mixed-Projection ADMM
Dimitris Bertsimas, Nicholas A. G. Johnson
We study the problem of learning a partially observed matrix under the low rank assumption in the presence of fully observed side information that depends linearly on the true unde…
eess.SP2023
Compressed Sensing: A Discrete Optimization Approach
Dimitris Bertsimas, Nicholas A. G. Johnson
We study the Compressed Sensing (CS) problem, which is the problem of finding the most sparse vector that satisfies a set of linear measurements up to some numerical tolerance. We…