Unsupervised learning for combinatorial optimization with principled objective relaxation

HP Wang, N Wu, H Yang, C Hao… - Advances in Neural …, 2022 - proceedings.neurips.cc
Using machine learning to solve combinatorial optimization (CO) problems is challenging,
especially when the data is unlabeled. This work proposes an unsupervised learning …

Data-driven offline decision-making via invariant representation learning

H Qi, Y Su, A Kumar, S Levine - Advances in Neural …, 2022 - proceedings.neurips.cc
The goal in offline data-driven decision-making is synthesize decisions that optimize a black-
box utility function, using a previously-collected static dataset, with no active interaction …

Dosa: Differentiable model-based one-loop search for dnn accelerators

C Hong, Q Huang, G Dinh, M Subedar… - Proceedings of the 56th …, 2023 - dl.acm.org
In the hardware design space exploration process, it is critical to optimize both hardware
parameters and algorithm-to-hardware map**s. Previous work has largely approached …

An evaluation of edge tpu accelerators for convolutional neural networks

K Seshadri, B Akin, J Laudon… - 2022 IEEE …, 2022 - ieeexplore.ieee.org
Edge TPUs are a domain of accelerators for low-power, edge devices and are widely used
in various Google products such as Coral and Pixel devices. In this paper, we first discuss …

Archgym: An open-source gymnasium for machine learning assisted architecture design

S Krishnan, A Yazdanbakhsh, S Prakash… - Proceedings of the 50th …, 2023 - dl.acm.org
Machine learning (ML) has become a prevalent approach to tame the complexity of design
space exploration for domain-specific architectures. While appealing, using ML for design …