Solving Boltzmann Optimization Problems with Deep Learning

Decades of exponential scaling in high performance computing (HPC) efficiency is coming to an end. Transistor based logic in complementary metal-oxide semiconductor (CMOS) technology is approaching physical limits beyond which further miniaturization will be impossible. Future HPC efficiency gains will necessarily rely on new technologies and paradigms of compute. The Ising model shows particular promise as a future framework for highly energy efficient computation. Ising systems are able to operate at energies approaching thermodynamic limits for energy consumption of computation. …

beyond boltzmann cmos compute computing cs.et cs.lg deep learning efficiency future high performance computing hpc logic math.oc metal optimization performance scaling semiconductor shows technologies technology will