LATIDIA · Robótica

RAYEN: Imposición de restricciones convexas estrictas en redes neuronales

arXiv:2307.08336v3 Anuncio Tipo: replace-cross Resumen: A pesar de las numerosas aplicaciones de las restricciones convexas en Robótica, imponerlas dentro de marcos basados ​​en aprendizaje sigue siendo un desafío abierto. Técnica existente

La noticia

arXiv:2307.08336v3 Announce Type: replace-cross Abstract: Despite the numerous applications of convex constraints in Robotics, enforcing them within learning-based frameworks remains an open challenge. Existing techniques either fail to guarantee satisfaction at all times, or incur prohibitive computational costs. This paper presents RAYEN, a framework for imposing hard convex constraints on the output or latent variables of a neural network. RAYEN guarantees constraint satisfaction during both training and testing, for any input and any network weights. Unlike prior approaches, RAYEN avoids computationally expensive orthogonal projections, soft constraints, conservative approximations of the feasible set, and slow iterative corrections. RAYEN supports any combination of linear, convex quadratic, second-order cone (SOC), and linear matrix