2 papers
cs.LG2024
Training Safe Neural Networks with Global SDP Bounds
Roman Soletskyi, David "davidad" Dalrymple
This paper presents a novel approach to training neural networks with formal safety guarantees using semidefinite programming (SDP) for verification. Our method focuses on verifyin…
cs.IT2019
A theory of incremental compression
Arthur Franz, Oleksandr Antonenko, Roman Soletskyi
The ability to find short representations, i.e. to compress data, is crucial for many intelligent systems. We present a theory of incremental compression showing that arbitrary dat…