Smaller, Faster, Cheaper: Architectural Designs for Efficient Machine Learning

• URL: http://arxiv.org/abs/2507.19795v1
• Date: Sat, 26 Jul 2025 04:56:53 GMT
• Title: Smaller, Faster, Cheaper: Architectural Designs for Efficient Machine Learning
• Authors: Steven Walton,
• Abstract summary: dissertation focuses on architectural principles through which models can achieve increased performance while reducing their computational demands.<n>First, we focus on data ingress and egress, investigating how information may be passed into and retrieved from our core neural processing units.<n>Second, we investigate modifications to the core neural architecture, applied to restricted attention in vision transformers.<n>Third, we explore the natural structures of Normalizing Flows and how we can leverage these properties to better distill model knowledge.
• Score: 1.1557918404865375
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Major advancements in the capabilities of computer vision models have been primarily fueled by rapid expansion of datasets, model parameters, and computational budgets, leading to ever-increasing demands on computational infrastructure. However, as these models are deployed in increasingly diverse and resource-constrained environments, there is a pressing need for architectures that can deliver high performance while requiring fewer computational resources. This dissertation focuses on architectural principles through which models can achieve increased performance while reducing their computational demands. We discuss strides towards this goal through three directions. First, we focus on data ingress and egress, investigating how information may be passed into and retrieved from our core neural processing units. This ensures that our models make the most of available data, allowing smaller architectures to become more performant. Second, we investigate modifications to the core neural architecture, applied to restricted attention in vision transformers. This section explores how removing uniform context windows in restricted attention increases the expressivity of the underlying neural architecture. Third, we explore the natural structures of Normalizing Flows and how we can leverage these properties to better distill model knowledge. These contributions demonstrate that careful design of neural architectures can increase the efficiency of machine learning algorithms, allowing them to become smaller, faster, and cheaper.

Related papers

• On Accelerating Edge AI: Optimizing Resource-Constrained Environments [1.7355861031903428]
  Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations.<n>We present a comprehensive overview of the primary strategies for accelerating deep learning models under such constraints.
  arXiv  Detail & Related papers  (2025-01-25T01:37:03Z)
• Exploring the design space of deep-learning-based weather forecasting systems [56.129148006412855]
  This paper systematically analyzes the impact of different design choices on deep-learning-based weather forecasting systems. We study fixed-grid architectures such as UNet, fully convolutional architectures, and transformer-based models. We propose a hybrid system that combines the strong performance of fixed-grid models with the flexibility of grid-invariant architectures.
  arXiv  Detail & Related papers  (2024-10-09T22:25:50Z)
• Learning From Simplicial Data Based on Random Walks and 1D Convolutions [6.629765271909503]
  simplicial complex neural network learning architecture based on random walks and fast 1D convolutions. We empirically evaluate SCRaWl on real-world datasets and show that it outperforms other simplicial neural networks.
  arXiv  Detail & Related papers  (2024-04-04T13:27:22Z)
• Neural Architecture Codesign for Fast Bragg Peak Analysis [1.7081438846690533]
  We develop an automated pipeline to streamline neural architecture codesign for fast, real-time Bragg peak analysis in microscopy. Our method employs neural architecture search and AutoML to enhance these models, including hardware costs, leading to the discovery of more hardware-efficient neural architectures.
  arXiv  Detail & Related papers  (2023-12-10T19:42:18Z)
• Computation-efficient Deep Learning for Computer Vision: A Survey [121.84121397440337]
  Deep learning models have reached or even exceeded human-level performance in a range of visual perception tasks. Deep learning models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios. New research focus is computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference.
  arXiv  Detail & Related papers  (2023-08-27T03:55:28Z)
• Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics [1.0154623955833253]
  We demonstrate three types of neural network architectures for efficient learning of deformations of solid bodies. The first two are based on the recently proposed CNN U-NET and MAgNET frameworks which have shown promising performance for learning on mesh-based data. The third architecture is Perceiver IO, a very recent architecture that belongs to the family of attention-based neural networks.
  arXiv  Detail & Related papers  (2022-12-01T13:10:56Z)
• Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers [52.30336730712544]
  We introduce a deep reinforcement learning architecture whose purpose is to increase sample efficiency without sacrificing performance. We propose a visually attentive model that uses transformers to learn a self-attention mechanism on the feature maps of the state representation. We demonstrate empirically that this architecture improves sample complexity for several Atari environments, while also achieving better performance in some of the games.
  arXiv  Detail & Related papers  (2022-02-01T19:03:03Z)
• Transformer-Based Behavioral Representation Learning Enables Transfer Learning for Mobile Sensing in Small Datasets [4.276883061502341]
  We provide a neural architecture framework for mobile sensing data that can learn generalizable feature representations from time series. This architecture combines benefits from CNN and Trans-former architectures to enable better prediction performance.
  arXiv  Detail & Related papers  (2021-07-09T22:26:50Z)
• Top-KAST: Top-K Always Sparse Training [50.05611544535801]
  We propose Top-KAST, a method that preserves constant sparsity throughout training. We show that it performs comparably to or better than previous works when training models on the established ImageNet benchmark. In addition to our ImageNet results, we also demonstrate our approach in the domain of language modeling.
  arXiv  Detail & Related papers  (2021-06-07T11:13:05Z)
• A Semi-Supervised Assessor of Neural Architectures [157.76189339451565]
  We employ an auto-encoder to discover meaningful representations of neural architectures. A graph convolutional neural network is introduced to predict the performance of architectures.
  arXiv  Detail & Related papers  (2020-05-14T09:02:33Z)
• Stage-Wise Neural Architecture Search [65.03109178056937]
  Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications. These networks consist of stages, which are sets of layers that operate on representations in the same resolution. It has been demonstrated that increasing the number of layers in each stage improves the prediction ability of the network. However, the resulting architecture becomes computationally expensive in terms of floating point operations, memory requirements and inference time.
  arXiv  Detail & Related papers  (2020-04-23T14:16:39Z)

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.