Multi-objective Neural Architecture Search via Non-stationary Policy
Gradient
- URL: http://arxiv.org/abs/2001.08437v2
- Date: Fri, 31 Jan 2020 03:42:43 GMT
- Title: Multi-objective Neural Architecture Search via Non-stationary Policy
Gradient
- Authors: Zewei Chen, Fengwei Zhou, George Trimponias, Zhenguo Li
- Abstract summary: Multi-objective Neural Architecture Search (NAS) aims to discover novel architectures in the presence of multiple conflicting objectives.
In this work, we explore the novel reinforcement learning based paradigm of non-stationary policy gradient (NPG)
- Score: 43.70611769739058
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multi-objective Neural Architecture Search (NAS) aims to discover novel
architectures in the presence of multiple conflicting objectives. Despite
recent progress, the problem of approximating the full Pareto front accurately
and efficiently remains challenging. In this work, we explore the novel
reinforcement learning (RL) 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 the
dominant paradigms of 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 with various datasets shows that our framework
can approximate the full Pareto front well at fast speeds. Moreover, our
discovered cells can achieve supreme predictive performance compared to other
multi-objective NAS methods, and other single-objective NAS methods at similar
network sizes. Our work demonstrates the potential of NPG as a simple,
efficient, and effective paradigm for multi-objective NAS.
Related papers
- A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism [58.855741970337675]
Neural architecture search (NAS) enables re-searchers to automatically explore vast search spaces and find efficient neural networks.
NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search process.
We propose the SMEM-NAS, a pairwise com-parison relation-assisted multi-objective evolutionary algorithm based on a multi-population mechanism.
arXiv Detail & Related papers (2024-07-22T12:46:22Z) - Latent-Conditioned Policy Gradient for Multi-Objective Deep
Reinforcement Learning [4.7210697296108926]
We propose a novel multi-objective reinforcement learning (MORL) algorithm that trains a single neural network via policy gradient.
The proposed method works in both continuous and discrete action spaces with no design change of the policy network.
arXiv Detail & Related papers (2023-03-15T20:07:48Z) - Surrogate-assisted Multi-objective Neural Architecture Search for
Real-time Semantic Segmentation [11.866947846619064]
neural architecture search (NAS) has emerged as a promising avenue toward automating the design of architectures.
We propose a surrogate-assisted multi-objective method to address the challenges of applying NAS to semantic segmentation.
Our method can identify architectures significantly outperforming existing state-of-the-art architectures designed both manually by human experts and automatically by other NAS methods.
arXiv Detail & Related papers (2022-08-14T10:18:51Z) - Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural
Architecture Search [15.454709248397208]
This study focuses on how to find feasible deep models under diverse design objectives.
We propose a classification-wise Pareto evolution approach for one-shot NAS, where an online classifier is trained to predict the dominance relationship between the candidate and constructed reference architectures.
We find a number of neural architectures with different model sizes ranging from 2M to 6M under diverse objectives and constraints.
arXiv Detail & Related papers (2021-09-14T13:28:07Z) - Elastic Architecture Search for Diverse Tasks with Different Resources [87.23061200971912]
We study a new challenging problem of efficient deployment for diverse tasks with different resources, where the resource constraint and task of interest corresponding to a group of classes are dynamically specified at testing time.
Previous NAS approaches seek to design architectures for all classes simultaneously, which may not be optimal for some individual tasks.
We present a novel and general framework, called Elastic Architecture Search (EAS), permitting instant specializations at runtime for diverse tasks with various resource constraints.
arXiv Detail & Related papers (2021-08-03T00:54:27Z) - Hyperparameter Optimization in Neural Networks via Structured Sparse
Recovery [54.60327265077322]
We study two important problems in the automated design of neural networks through the lens of sparse recovery methods.
In the first part of this paper, we establish a novel connection between HPO and structured sparse recovery.
In the second part of this paper, we establish a connection between NAS and structured sparse recovery.
arXiv Detail & Related papers (2020-07-07T00:57:09Z) - DrNAS: Dirichlet Neural Architecture Search [88.56953713817545]
We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet distribution.
With recently developed pathwise derivatives, the Dirichlet parameters can be easily optimized with gradient-based generalization.
To alleviate the large memory consumption of differentiable NAS, we propose a simple yet effective progressive learning scheme.
arXiv Detail & Related papers (2020-06-18T08:23:02Z) - MTL-NAS: Task-Agnostic Neural Architecture Search towards
General-Purpose Multi-Task Learning [71.90902837008278]
We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL)
In order to adapt to different task combinations, we disentangle the GP-MTL networks into single-task backbones.
We also propose a novel single-shot gradient-based search algorithm that closes the performance gap between the searched architectures.
arXiv Detail & Related papers (2020-03-31T09:49:14Z)
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.