A list of software deleveloped with associated papers.
Holistic Robust (HR) learning provides certified protection against data poisoning and evasion attacks, while enjoying guaranteed generalization. HR-NN is a python package implemeting HR for deep neural network training.
Bennouna, M.A., R. Lucas, and B.P.G. Van Parys (2023). “Certified robust neural networks: Generalization and corruption resistance”. In: International Conference on Machine Learning (ICML). Honolulu, Hawaii, USA, pp. 2092–2112. Link
Bennouna, M.A. and B.P.G. Van Parys (2022). “Holistic robust data-driven decisions”. In: Mathematical Programming. Submitted. Finalist for 2023 INFORMS Data Mining Best Paper Award Competition. Link
This code can be used to reproduce and verify the results from the work
DuSA.jl is a Julia package which implements an optimal exploitation/exploration in DUal Structured Algorithm.
NExOS.jl is a Julia package that implements the Nonconvex Exterior-point Optimization Solver (NExOS). The package is tailored for minimizing a convex cost function over a nonconvex constraint set.