Accel-NASBench: Sustainable Benchmarking for Accelerator-Aware NAS

• URL: http://arxiv.org/abs/2404.08005v2
• Date: Tue, 18 Jun 2024 05:51:50 GMT
• Title: Accel-NASBench: Sustainable Benchmarking for Accelerator-Aware NAS
• Authors: Afzal Ahmad, Linfeng Du, Zhiyao Xie, Wei Zhang,
• Abstract summary: We present a technique that allows searching for training proxies that reduce the cost of benchmark construction by significant margins. We show that the benchmark is accurate and allows searching for state-of-the-art hardware-aware models at zero cost.
• Score: 3.598880812393792
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One of the primary challenges impeding the progress of Neural Architecture Search (NAS) is its extensive reliance on exorbitant computational resources. NAS benchmarks aim to simulate runs of NAS experiments at zero cost, remediating the need for extensive compute. However, existing NAS benchmarks use synthetic datasets and model proxies that make simplified assumptions about the characteristics of these datasets and models, leading to unrealistic evaluations. We present a technique that allows searching for training proxies that reduce the cost of benchmark construction by significant margins, making it possible to construct realistic NAS benchmarks for large-scale datasets. Using this technique, we construct an open-source bi-objective NAS benchmark for the ImageNet2012 dataset combined with the on-device performance of accelerators, including GPUs, TPUs, and FPGAs. Through extensive experimentation with various NAS optimizers and hardware platforms, we show that the benchmark is accurate and allows searching for state-of-the-art hardware-aware models at zero cost.

Related papers

• SiGeo: Sub-One-Shot NAS via Information Theory and Geometry of Loss Landscape [14.550053893504764]
  We introduce a "sub-one-shot" paradigm that serves as a bridge between zero-shot and one-shot NAS. In sub-one-shot NAS, the supernet is trained using only a small subset of the training data, a phase we refer to as "warm-up" We present SiGeo, a proxy founded on a novel theoretical framework that connects the supernet warm-up with the efficacy of the proxy.
  arXiv  Detail & Related papers  (2023-11-22T05:25:24Z)
• DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models [56.584561770857306]
  We propose a novel conditional Neural Architecture Generation (NAG) framework based on diffusion models, dubbed DiffusionNAG. Specifically, we consider the neural architectures as directed graphs and propose a graph diffusion model for generating them. We validate the effectiveness of DiffusionNAG through extensive experiments in two predictor-based NAS scenarios: Transferable NAS and Bayesian Optimization (BO)-based NAS. When integrated into a BO-based algorithm, DiffusionNAG outperforms existing BO-based NAS approaches, particularly in the large MobileNetV3 search space on the ImageNet 1K dataset.
  arXiv  Detail & Related papers  (2023-05-26T13:58:18Z)
• Generalization Properties of NAS under Activation and Skip Connection Search [66.8386847112332]
  We study the generalization properties of Neural Architecture Search (NAS) under a unifying framework. We derive the lower (and upper) bounds of the minimum eigenvalue of the Neural Tangent Kernel (NTK) under the (in)finite-width regime. We show how the derived results can guide NAS to select the top-performing architectures, even in the case without training.
  arXiv  Detail & Related papers  (2022-09-15T12:11:41Z)
• UnrealNAS: Can We Search Neural Architectures with Unreal Data? [84.78460976605425]
  Neural architecture search (NAS) has shown great success in the automatic design of deep neural networks (DNNs) Previous work has analyzed the necessity of having ground-truth labels in NAS and inspired broad interest. We take a further step to question whether real data is necessary for NAS to be effective.
  arXiv  Detail & Related papers  (2022-05-04T16:30:26Z)
• U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search [50.33956216274694]
  optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. We propose a novel hardware-aware NAS framework that does not only optimize for task accuracy and inference latency, but also for resource utilization. We achieve 2.8 - 4x speedup for DNN inference compared to prior hardware-aware NAS methods.
  arXiv  Detail & Related papers  (2022-03-23T13:44:15Z)
• NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy [37.72015163462501]
  We present an in-depth analysis of popular NAS algorithms and performance prediction methods across 25 different combinations of search spaces and datasets. We introduce NAS-Bench-Suite, a comprehensive and collection of NAS benchmarks, accessible through a unified interface.
  arXiv  Detail & Related papers  (2022-01-31T18:02:09Z)
• BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule [95.56873042777316]
  Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost. This paper formulates the neural architecture search as a distribution learning problem through relaxing the architecture weights into Gaussian distributions. We demonstrate how the differentiable NAS benefits from Bayesian principles, enhancing exploration and improving stability.
  arXiv  Detail & Related papers  (2021-11-25T18:13:42Z)
• NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters [4.039245878626346]
  This paper introduces the first benchmark dataset for joint optimization of network connections and training hyperparameters, which we call NAS-HPO-Bench-II. We collect the performance data of 4K cell-based convolutional neural network architectures trained on the CIFAR-10 dataset with different learning rate and batch size settings. We build a surrogate model predicting the accuracies after 200 epoch training to provide the performance data of longer training epoch.
  arXiv  Detail & Related papers  (2021-10-19T18:00:01Z)
• AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment [23.988393741948485]
  We propose a novel search strategy for one-shot and sparse propagation NAS, namely AdvantageNAS. AdvantageNAS is a gradient-based approach that improves the search efficiency by introducing credit assignment in gradient estimation for architecture updates. Experiments on the NAS-Bench-201 and PTB dataset show that AdvantageNAS discovers an architecture with higher performance under a limited time budget.
  arXiv  Detail & Related papers  (2020-12-11T05:45:03Z)
• Binarized Neural Architecture Search for Efficient Object Recognition [120.23378346337311]
  Binarized neural architecture search (BNAS) produces extremely compressed models to reduce huge computational cost on embedded devices for edge computing. An accuracy of $96.53%$ vs. $97.22%$ is achieved on the CIFAR-10 dataset, but with a significantly compressed model, and a $40%$ faster search than the state-of-the-art PC-DARTS.
  arXiv  Detail & Related papers  (2020-09-08T15:51:23Z)
• BRP-NAS: Prediction-based NAS using GCNs [21.765796576990137]
  BRP-NAS is an efficient hardware-aware NAS enabled by an accurate performance predictor-based on graph convolutional network (GCN) We show that our proposed method outperforms all prior methods on NAS-Bench-101 and NAS-Bench-201. We also release LatBench -- a latency dataset of NAS-Bench-201 models running on a broad range of devices.
  arXiv  Detail & Related papers  (2020-07-16T21:58:43Z)

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.