A Hardware-Aware System for Accelerating Deep Neural Network Optimization

• URL: http://arxiv.org/abs/2202.12954v1
• Date: Fri, 25 Feb 2022 20:07:29 GMT
• Title: A Hardware-Aware System for Accelerating Deep Neural Network Optimization
• Authors: Anthony Sarah, Daniel Cummings, Sharath Nittur Sridhar, Sairam Sundaresan, Maciej Szankin, Tristan Webb, J. Pablo Munoz
• Abstract summary: We propose a comprehensive system that automatically and efficiently finds sub-networks from a pre-trained super-network. By combining novel search tactics and algorithms with intelligent use of predictors, we significantly decrease the time needed to find optimal sub-networks.
• Score: 7.189421078452572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in Neural Architecture Search (NAS) which extract specialized hardware-aware configurations (a.k.a. "sub-networks") from a hardware-agnostic "super-network" have become increasingly popular. While considerable effort has been employed towards improving the first stage, namely, the training of the super-network, the search for derivative high-performing sub-networks is still largely under-explored. For example, some recent network morphism techniques allow a super-network to be trained once and then have hardware-specific networks extracted from it as needed. These methods decouple the super-network training from the sub-network search and thus decrease the computational burden of specializing to different hardware platforms. We propose a comprehensive system that automatically and efficiently finds sub-networks from a pre-trained super-network that are optimized to different performance metrics and hardware configurations. By combining novel search tactics and algorithms with intelligent use of predictors, we significantly decrease the time needed to find optimal sub-networks from a given super-network. Further, our approach does not require the super-network to be refined for the target task a priori, thus allowing it to interface with any super-network. We demonstrate through extensive experiments that our system works seamlessly with existing state-of-the-art super-network training methods in multiple domains. Moreover, we show how novel search tactics paired with evolutionary algorithms can accelerate the search process for ResNet50, MobileNetV3 and Transformer while maintaining objective space Pareto front diversity and demonstrate an 8x faster search result than the state-of-the-art Bayesian optimization WeakNAS approach.

Related papers

• SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search [6.121126813817338]
  Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. We show that by using multi-objective search algorithms paired with lightly trained predictors, we can efficiently search for both the sub-network architecture and the corresponding quantization policy.
  arXiv  Detail & Related papers  (2023-12-19T22:08:49Z)
• OFA$^2$: A Multi-Objective Perspective for the Once-for-All Neural Architecture Search [79.36688444492405]
  Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints. We aim to give one step further in the search for efficiency by explicitly conceiving the search stage as a multi-objective optimization problem.
  arXiv  Detail & Related papers  (2023-03-23T21:30:29Z)
• A Hardware-Aware Framework for Accelerating Neural Architecture Search Across Modalities [7.542742087154667]
  We show how evolutionary algorithms can be paired with lightly trained objective predictors in an iterative cycle to accelerate architecture search. Specifically, we show how evolutionary algorithms can be paired with lightly trained objective predictors in an iterative cycle to accelerate architecture search.
  arXiv  Detail & Related papers  (2022-05-19T20:41:01Z)
• Evolutionary Neural Cascade Search across Supernetworks [68.8204255655161]
  We introduce ENCAS - Evolutionary Neural Cascade Search. ENCAS can be used to search over multiple pretrained supernetworks. We test ENCAS on common computer vision benchmarks.
  arXiv  Detail & Related papers  (2022-03-08T11:06:01Z)
• Enabling NAS with Automated Super-Network Generation [60.72821429802335]
  Recent Neural Architecture Search (NAS) solutions have produced impressive results training super-networks and then derivingworks. We present BootstrapNAS, a software framework for automatic generation of super-networks for NAS.
  arXiv  Detail & Related papers  (2021-12-20T21:45:48Z)
• Searching for Efficient Multi-Stage Vision Transformers [42.0565109812926]
  Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks. ViT-ResNAS is an efficient multi-stage ViT architecture designed with neural architecture search (NAS)
  arXiv  Detail & Related papers  (2021-09-01T22:37:56Z)
• Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight [66.8543732597723]
  Recent worksin neural architecture search (NAS) can aid transfer learning by establishing sufficient network search space. We propose a novel framework consisting of two modules, the neural architecturesearch module for architecture transfer and the neural weight search module for weight transfer. These two modules conduct search on thetarget task based on a reduced super-networks, so we only need to trainonce on the source task.
  arXiv  Detail & Related papers  (2021-05-19T08:58:04Z)
• Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search [60.965024145243596]
  One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. To alleviate this problem, we present a simple yet effective architecture distillation method. We introduce the concept of prioritized path, which refers to the architecture candidates exhibiting superior performance during training. Since the prioritized paths are changed on the fly depending on their performance and complexity, the final obtained paths are the cream of the crop.
  arXiv  Detail & Related papers  (2020-10-29T17:55:05Z)
• NAS-Navigator: Visual Steering for Explainable One-Shot Deep Neural Network Synthesis [53.106414896248246]
  We present a framework that allows analysts to effectively build the solution sub-graph space and guide the network search by injecting their domain knowledge. Applying this technique in an iterative manner allows analysts to converge to the best performing neural network architecture for a given application.
  arXiv  Detail & Related papers  (2020-09-28T01:48:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.