3 papers
math.OC2026
Mixtures Closest to a Given Measure: A Semidefinite Programming Approach
SreÄko ÄuraÅ¡inoviÄ, Srećko Đurašinović, Jean-Bernard Lasserre +1
Mixture models, such as Gaussian mixture models, are widely used in machine learning to represent complex data distributions. A key challenge, especially in high-dimensional settin…
math.OC2026
Finite convergence of the Moment-SOS hierarchy under hidden convexity
SreÄko ÃuraÅ¡inoviÄ, Srećko Ðurašinović, Jean B. Lasserre
We consider polynomial optimization problems with compact feasible set defined by SOS-concave polynomials of arbitrary degree, and whose objective…
cs.LG2025
Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
Jianting Yang, SreÄko ÃuraÅ¡inoviÄ, Srećko Ðurašinović +3
This paper explores methods for verifying the properties of Binary Neural Networks (BNNs), focusing on robustness against adversarial attacks. Despite their lower computational and…