Unsupervised learning for combinatorial optimization with principled objective relaxation
Using machine learning to solve combinatorial optimization (CO) problems is challenging,
especially when the data is unlabeled. This work proposes an unsupervised learning …
especially when the data is unlabeled. This work proposes an unsupervised learning …
Data-driven offline decision-making via invariant representation learning
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 …
box utility function, using a previously-collected static dataset, with no active interaction …
Dosa: Differentiable model-based one-loop search for dnn accelerators
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 …
parameters and algorithm-to-hardware map**s. Previous work has largely approached …
An evaluation of edge tpu accelerators for convolutional neural networks
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 …
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
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 …
space exploration for domain-specific architectures. While appealing, using ML for design …