相关论文: ZeroLM: Data-Free Transformer Architecture Search …

Recently, several approaches successfully demonstrated that weight-sharing Neural Architecture Search (NAS) can effectively explore a search space of elastic low-rank adapters (LoRA), allowing the parameter-efficient fine-tuning (PEFT) and…

Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the…

The increasing demand for tabular data analysis calls for transitioning from manual architecture design to Neural Architecture Search (NAS). This transition demands an efficient and responsive anytime NAS approach that is capable of…

In the realm of neural architecture design, achieving high performance is largely reliant on the manual expertise of researchers. Despite the emergence of Neural Architecture Search (NAS) as a promising technique for automating this…

Estimating the network performance using zero-cost (ZC) metrics has proven both its efficiency and efficacy in Neural Architecture Search (NAS). However, a notable limitation of most ZC proxies is their inconsistency, as reflected by the…

Neural Architecture Search (NAS) aims to automatically discover high-performing deep neural network (DNN) architectures. However, conventional algorithm-driven NAS relies on carefully hand-crafted search spaces to ensure executability,…

This paper introduces a novel framework for designing efficient neural network architectures specifically tailored to tiny machine learning (TinyML) platforms. By leveraging large language models (LLMs) for neural architecture search (NAS),…

Neural Architecture Search (NAS) represents a class of methods to generate the optimal neural network architecture and typically iterate over candidate architectures till convergence over some particular metric like validation loss. They…

With the rapid development of neural architecture search (NAS), researchers found powerful network architectures for a wide range of vision tasks. However, it remains unclear if the searched architecture can transfer across different types…

Networks found with Neural Architecture Search (NAS) achieve state-of-the-art performance in a variety of tasks, out-performing human-designed networks. However, most NAS methods heavily rely on human-defined assumptions that constrain the…

Neural Architecture Search (NAS) often trains and evaluates a large number of architectures. Recent predictor-based NAS approaches attempt to alleviate such heavy computation costs with two key steps: sampling some architecture-performance…

Diffusion models (DMs) are powerful generative models capable of producing high-fidelity images but are constrained by high computational costs due to iterative multi-step inference. While Neural Architecture Search (NAS) can optimize DMs,…

Neural architecture search (NAS) is a recent methodology for automating the design of neural network architectures. Differentiable neural architecture search (DARTS) is a promising NAS approach that dramatically increases search efficiency.…

Architecture plays an important role in deciding the performance of deep neural networks. However, the search for the optimal architecture is often hindered by the vast search space, making it a time-intensive process. Recently, a novel…

Neural structure search (NAS), as the mainstream approach to automate deep neural architecture design, has achieved much success in recent years. However, the performance estimation component adhering to NAS is often prohibitively costly,…

Neural Architecture Search (NAS) has become the de fecto tools in the industry in automating the design of deep neural networks for various applications, especially those driven by mobile and edge devices with limited computing resources.…

This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the structure of…

Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with…

Recently, numerous efficient Transformers have been proposed to reduce the quadratic computational complexity of standard Transformers caused by the Softmax attention. However, most of them simply swap Softmax with an efficient attention…

Efficient search is a core issue in Neural Architecture Search (NAS). It is difficult for conventional NAS algorithms to directly search the architectures on large-scale tasks like ImageNet. In general, the cost of GPU hours for NAS grows…