Summary of Learning K-u-net with Constant Complexity: An Application to Time Series Forecasting, by Jiang You et al.
Learning K-U-Net with constant complexity: An Application to time series forecasting
by Jiang You, Arben Cela, René Natowicz, Jacob Ouanounou, Patrick Siarry
First submitted to arxiv on: 3 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel exponentially weighted stochastic gradient descent algorithm to address the time complexity challenge in deep models for time series forecasting. By leveraging temporal redundancy, the authors find that high-level features are learned significantly slower than low-level features. To overcome this limitation, they introduce a new algorithm with constant time complexity, demonstrating a significant reduction in computational requirements while maintaining accuracy on synthetic datasets using Kernel U-Net (K-U-Net). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Deep learning models for time series forecasting have a crucial challenge: time complexity. The authors show that high-level features are learned much slower than low-level features and introduce an algorithm to solve this problem. They prove it works and test it on some data, making it faster and more accurate. |
Keywords
» Artificial intelligence » Deep learning » Stochastic gradient descent » Time series
