paper-with-me

홈 › Papers

LayerNAS: Neural Architecture Search in Polynomial Complexity

2023-04-23 · Yicheng Fan, Dana Alon, Jingyue Shen, Daiyi Peng, Keshav Kumar, Yun Long, Xin Wang, Fotis Iliopoulos, Da-Cheng Juan, Erik Vee

Neural Architecture Search (NAS) has become a popular method for discovering effective model architectures, especially for target hardware. As such, NAS methods that find optimal architectures under constraints are essential. In our paper, we propose LayerNAS to address the challenge of multi-objective NAS by transforming it into a combinatorial optimization problem, which effectively constrains the search complexity to be polynomial. For a model architecture with $L$ layers, we perform layerwise-search for each layer, selecting from a set of search options $\mathbb{S}$. LayerNAS groups model candidates based on one objective, such as model size or latency, and searches for the optimal model based on another objective, thereby splitting the cost and reward elements of the search. This approach limits the search complexity to $ O(H \cdot |\mathbb{S}| \cdot L) $, where $H$ is a constant set in LayerNAS. Our experiments show that LayerNAS is able to consistently discover superior models across a variety of search spaces in comparison to strong baselines, including search spaces derived from NATS-Bench, MobileNetV2 and MobileNetV3.

📄 PDF Abstract BibTeX arXiv:2304.11517

Code (0)

등록된 구현이 없습니다.

Tasks

Combinatorial OptimizationNeural Architecture Search

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Sigmoid Activation 설명 없음
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
ReLU6 ReLU6 is a modification of the rectified linear unit where we limit the activation to a maximum size of $6$. This is due to increased…
Average Pooling 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

New Complexity-Theoretic Frontiers of Tractability for Neural Network Training

2026-07-23 · Cornelius Brand, Robert Ganian, Mathis Rocton arxiv

In spite of the fundamental role of neural networks in contemporary machine learning research, our understanding of the computational complexity of optimally training neural networks remains incomplete even when dealing …

Bounding the Complexity of Formally Verifying Neural Networks: A Geometric Approach

2020-12-22 · James Ferlez, Yasser Shoukry

In this paper, we consider the computational complexity of formally verifying the behavior of Rectified Linear Unit (ReLU) Neural Networks (NNs), where verification entails determining whether the NN satisfies convex pol…

Optimal Cooperative Driving at Signal-Free Intersections with Polynomial-Time Complexity

2021-04-28 · Huaxin Pei, Yuxiao Zhang, Yi Zhang, Shuo Feng

Cooperative driving at signal-free intersections, which aims to improve driving safety and efficiency for connected and automated vehicles, has attracted increasing interest in recent years. However, existing cooperative…

On the Study of Sample Complexity for Polynomial Neural Networks

2022-07-18 · Chao Pan, Chuanyi Zhang

As a general type of machine learning approach, artificial neural networks have established state-of-art benchmarks in many pattern recognition and data analysis tasks. Among various kinds of neural networks architecture…

Face RecognitionImage GenerationPolynomial Neural Networks

The Vertex Sample Complexity of Free Energy is Polynomial

2018-02-16 · Vishesh Jain, Frederic Koehler, Elchanan Mossel

We study the following question: given a massive Markov random field on $n$ nodes, can a small sample from it provide a rough approximation to the free energy $\mathcal{F}_n = \log{Z_n}$? Results in graph limit literat…

LEMMA