Preconditioners for the Stochastic Training of Implicit Neural Representations

arXiv:2402.08784v1 Announce Type: cross
Abstract: Implicit neural representations have emerged as a powerful technique for encoding complex continuous multidimensional signals as neural networks, enabling a wide range of applications in computer vision, robotics, and geometry. While Adam is commonly used for training due to its stochastic proficiency, it entails lengthy training durations. To address this, we explore alternative optimization techniques for accelerated training without sacrificing accuracy. Traditional second-order optimizers like L-BFGS are suboptimal in stochastic settings, making them unsuitable for …

abstract adam applications arxiv computer computer vision continuous cs.cv cs.lg enabling encoding geometry implicit neural representations multidimensional networks neural networks robotics stochastic training type vision