Latency-Aware Differentiable Neural Architecture Search

01/17/2020
by   Yuhui Xu, et al.
3

Differentiable neural architecture search methods became popular in automated machine learning, mainly due to their low search costs and flexibility in designing the search space. However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware. This paper deals with this problem by adding a differentiable latency loss term into optimization, so that the search process can tradeoff between accuracy and latency with a balancing coefficient. The core of latency prediction is to encode each network architecture and feed it into a multi-layer regressor, with the training data being collected from randomly sampling a number of architectures and evaluating them on the hardware. We evaluate our approach on NVIDIA Tesla-P100 GPUs. With 100K sampled architectures (requiring a few hours), the latency prediction module arrives at a relative error of lower than 10%. Equipped with this module, the search method can reduce the latency by 20 approach also enjoys the ability of being transplanted to a wide range of hardware platforms with very few efforts, or being used to optimizing other non-differentiable factors such as power consumption.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/17/2021

RHNAS: Realizable Hardware and Neural Architecture Search

The rapidly evolving field of Artificial Intelligence necessitates autom...
research
06/13/2023

Flexible Channel Dimensions for Differentiable Architecture Search

Finding optimal channel dimensions (i.e., the number of filters in DNN l...
research
09/14/2021

Hardware-aware Real-time Myocardial Segmentation Quality Control in Contrast Echocardiography

Automatic myocardial segmentation of contrast echocardiography has shown...
research
06/17/2019

Hardware Aware Neural Network Architectures using FbNet

We implement a differentiable Neural Architecture Search (NAS) method in...
research
08/25/2022

SONAR: Joint Architecture and System Optimization Search

There is a growing need to deploy machine learning for different tasks o...
research
09/08/2020

AutoKWS: Keyword Spotting with Differentiable Architecture Search

Smart audio devices are gated by an always-on lightweight keyword spotti...
research
12/12/2020

Efficient Incorporation of Multiple Latency Targets in the Once-For-All Network

Neural Architecture Search has proven an effective method of automating ...

Please sign up or login with your details

Forgot password? Click here to reset