Multi-objective Neural Architecture Search via Non-stationary Policy Gradient

01/23/2020
by   Zewei Chen, et al.
0

Multi-objective Neural Architecture Search (NAS) aims to discover novel architectures in the presence of multiple conflicting objectives. Recent approaches based on scalarization and evolution have yielded promising results, but the problem of approximating the full Pareto front accurately and efficiently remains challenging. To this end, we explore in this work the novel reinforcement learning based paradigm of non-stationary policy gradient (NPG). NPG utilizes a non-stationary reward function, and encourages a continuous adaptation of the policy to capture the entire Pareto front efficiently. We introduce two novel reward functions with elements from scalarization and evolution. To handle non-stationarity, we propose a new exploration scheme using cosine temperature decay with warm restarts. For fast and accurate architecture evaluation, we introduce a novel pre-trained shared model that we continuously fine-tune throughout training. Our extensive experimental study on CIFAR-10, CIFAR-100, and ImageNet shows that our framework can uncover a representative Pareto front at fast speeds, while achieving superior predictive performance than other multi-objective NAS methods, and many state-of-the-art NAS methods at similar network sizes. Our work demonstrates the potential of NPG as a simple, fast, and effective paradigm for multi-objective NAS.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/06/2021

TND-NAS: Towards Non-differentiable Objectives in Progressive Differentiable NAS Framework

Differentiable architecture search has gradually become the mainstream r...
research
09/14/2021

How to Simplify Search: Classification-wise Pareto Evolution for One-shot Neural Architecture Search

In the deployment of deep neural models, how to effectively and automati...
research
04/23/2023

LayerNAS: Neural Architecture Search in Polynomial Complexity

Neural Architecture Search (NAS) has become a popular method for discove...
research
11/27/2020

Multi-objective Neural Architecture Search with Almost No Training

In the recent past, neural architecture search (NAS) has attracted incre...
research
04/20/2020

Local Search is a Remarkably Strong Baseline for Neural Architecture Search

Neural Architecture Search (NAS), i.e., the automation of neural network...
research
03/28/2023

FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation

We present FMAS, a fast multi-objective neural architecture search frame...
research
08/03/2020

Evolving Multi-Resolution Pooling CNN for Monaural Singing Voice Separation

Monaural Singing Voice Separation (MSVS) is a challenging task and has b...

Please sign up or login with your details

Forgot password? Click here to reset