RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search

2021-09-13 · Zheyu Yan, Weiwen Jiang, Xiaobo Sharon Hu, Yiyu Shi

Differentiable neural architecture search (DNAS) is known for its capacity in the automatic generation of superior neural networks. However, DNAS based methods suffer from memory usage explosion when the search space expands, which may prevent them from running successfully on even advanced GPU platforms. On the other hand, reinforcement learning (RL) based methods, while being memory efficient, are extremely time-consuming. Combining the advantages of both types of methods, this paper presents RADARS, a scalable RL-aided DNAS framework that can explore large search spaces in a fast and memory-efficient manner. RADARS iteratively applies RL to prune undesired architecture candidates and identifies a promising subspace to carry out DNAS. Experiments using a workstation with 12 GB GPU memory show that on CIFAR-10 and ImageNet datasets, RADARS can achieve up to 3.41% higher accuracy with 2.5X search time reduction compared with a state-of-the-art RL-based method, while the two DNAS baselines cannot complete due to excessive memory usage or search time. To the best of the authors' knowledge, this is the first DNAS framework that can handle large search spaces with bounded memory usage.

📄 PDF Abstract BibTeX arXiv:2109.05691

Code (0)

등록된 구현이 없습니다.

Tasks

GPUNeural Architecture Search reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Gumbel Softmax 설명 없음

DNAS 설명 없음

EgoMap: Projective mapping and structured egocentric memory for Deep RL

2020-01-24 · Edward Beeching, Christian Wolf, Jilles Dibangoye, Olivier Simonin

Tasks involving localization, memorization and planning in partially observable 3D environments are an ongoing challenge in Deep Reinforcement Learning. We present EgoMap, a spatially structured neural memory architectur…

Deep Reinforcement Learning Memorization reinforcement-learning Reinforcement Learning+1

Decentralized Automotive Radar Spectrum Allocation to Avoid Mutual Interference Using Reinforcement Learning

2020-01-07 · PengFei Liu, Yimin Liu, Tianyao Huang, Yuxiang Lu 외

Nowadays, mutual interference among automotive radars has become a problem of wide concern. In this paper, a decentralized spectrum allocation approach is presented to avoid mutual interference among automotive radars. A…

Decision Making reinforcement-learning Reinforcement Learning (RL)

RadarSim: Simulating Single-Chip Radar via Multimodal Neural Fields

2026-05-25 · Chuhan Chen, Tianshu Huang, Akarsh Prabhakara, Chaithanya Kumar Mummadi 외 arxiv

Radars are an ideal complement to cameras: both are inexpensive, solid-state sensors, with cameras offering fine angular resolution, while radars provide metric depth and robustness under adverse weather. However, radar …

Novel View Synthesis

Quantum Long Short-term Memory with Differentiable Architecture Search

2025-08-20 · Samuel Yen-Chi Chen, Prayag Tiwari arxiv

Recent advances in quantum computing and machine learning have given rise to quantum machine learning (QML), with growing interest in learning from sequential data. Quantum recurrent models like QLSTM are promising for t…

Quantum Machine Learning Reinforcement Learning

Variational Inference Aided Estimation of Time Varying Channels

2022-10-31 · Benedikt Böck, Michael Baur, Valentina Rizzello, Wolfgang Utschick

One way to improve the estimation of time varying channels is to incorporate knowledge of previous observations. In this context, Dynamical VAEs (DVAEs) build a promising deep learning (DL) framework which is well suited…

Time Series Time Series Analysis Variational Inference