# Accelerating Deep Learning with Fixed Time Budget

arXiv: https://arxiv.org/abs/2410.03790 · HTML: https://mlsanity.com/paper/2410.03790/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [Not All Samples Are Created Equal: Deep Learning with Importance Sampling](https://mlsanity.com/paper/1803.00942/) (2018)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Dataset Pruning: Reducing Training Data by Examining Generalization Influence](https://mlsanity.com/paper/2205.09329/) (2022)
- [CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images](https://mlsanity.com/paper/1808.01097/) (2018)
- [Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network](https://mlsanity.com/paper/1903.00853/) (2019)
- [Visualizing the Feature Importance for Black Box Models](https://mlsanity.com/paper/1804.06620/) (2018)
- [CNN-based Density Estimation and Crowd Counting: A Survey](https://mlsanity.com/paper/2003.12783/) (2020)
- [CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting](https://mlsanity.com/paper/1707.09605/) (2017)
- [Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints](https://mlsanity.com/paper/1905.04753/) (2019)
- [Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness](https://mlsanity.com/paper/2211.11109/) (2022)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [LCDnet: A Lightweight Crowd Density Estimation Model for Real-time Video Surveillance](https://mlsanity.com/paper/2302.05374/) (2023)
- [Learning Error-Driven Curriculum for Crowd Counting](https://mlsanity.com/paper/2007.09676/) (2020)
- [A Survey on Deep Learning-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal](https://mlsanity.com/paper/2012.15685/) (2020)
- [CLIP: Train Faster with Less Data](https://mlsanity.com/paper/2212.01452/) (2022)
- [DroneNet: Crowd Density Estimation using Self-ONNs for Drones](https://mlsanity.com/paper/2211.07137/) (2022)
- [Time-Constrained Learning](https://mlsanity.com/paper/2202.01913/) (2022)
- [Curriculum for Crowd Counting -- Is it Worthy?](https://mlsanity.com/paper/2401.07586/) (2024)

## Abstract (arXiv)

The success of modern deep learning is attributed to two key elements: huge amounts of training data and large model sizes. Where a vast amount of data allows the model to learn more features, the large model architecture boosts the learning capability of the model. However, both these factors result in prolonged training time. In some practical applications such as edge-based learning and federated learning, limited-time budgets necessitate more efficient training methods. This paper proposes an effective technique for training arbitrary deep learning models within fixed time constraints utilizing sample importance and dynamic ranking. The proposed method is extensively evaluated in both classification and regression tasks in computer vision. The results consistently show clear gains achieved by the proposed method in improving the learning performance of various state-of-the-art deep learning models in both regression and classification tasks.