arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.02525cs.ET
收藏

用 Ising 机基底支持基于能量的学习:以 RBM 为例的案例研究

Supporting Energy-Based Learning With An Ising Machine Substrate: A Case Study on RBM

Uday Kumar Reddy Vengalam, Yongchao Liu, Tong Geng, Hui Wu, Michael Huang

AI总结:

提出一种增强型 Ising 机,通过硬件与算法协同演化支持基于能量的机器学习训练与推理,实现完全在硬件中完成训练,相比 TPU 获得约 29 倍加速和 1000 倍能耗降低。

摘要:

大自然显然不断进行大量计算。如果我们能在合适的层面上利用其中一部分计算,就有可能比使用冯·诺依曼计算机更快、更高效地执行某些类型的计算。事实上,许多强大的算法都受自然启发,因此是基于自然计算的绝佳候选者。这一努力中近期取得快速进展的一个特定分支是 Ising 机。一些 Ising 机在优化问题上已经展现出更好的性能和能效。通过硬件与算法之间的设计迭代和协同演化,我们期望从基于自然的计算系统中获得更多益处。在本文中,我们提出了一种增强型 Ising 机,适合使用基于能量的机器学习算法进行训练和推理。我们表明,通过微小的改动,Ising 基底能够加速算法的关键部分,并实现非平凡的速度提升和效率增益。通过更实质性的改动,我们可以将机器转变为一个自给自足的梯度跟随器,从而几乎完全在硬件中完成训练。与 Tensor Processing Unit (TPU) 主机相比,这可带来约 29 倍的速度提升和约 1000 倍的能耗降低。

英文摘要:

Nature apparently does a lot of computation constantly. If we can harness some of that computation at an appropriate level, we can potentially perform certain type of computation (much) faster and more efficiently than we can do with a von Neumann computer. Indeed, many powerful algorithms are inspired by nature and are thus prime candidates for nature-based computation. One particular branch of this effort that has seen some recent rapid advances is Ising machines. Some Ising machines are already showing better performance and energy efficiency for optimization problems. Through design iterations and co-evolution between hardware and algorithm, we expect more benefits from nature-based computing systems. In this paper, we make a case for an augmented Ising machine suitable for both training and inference using an energy-based machine learning algorithm. We show that with a small change, the Ising substrate accelerate key parts of the algorithm and achieve non-trivial speedup and efficiency gain. With a more substantial change, we can turn the machine into a self-sufficient gradient follower to virtually complete training entirely in hardware. This can bring about 29x speedup and about 1000x reduction in energy compared to a Tensor Processing Unit (TPU) host.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑