Summary of Incorporating Exponential Smoothing Into Mlp: a Simple but Effective Sequence Model, by Jiqun Chu et al.
Incorporating Exponential Smoothing into MLP: A Simple but Effective Sequence Model
by Jiqun Chu, Zuoquan Lin
First submitted to arxiv on: 26 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
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 The recently developed Structured State Space (S4) model has shown significant effectiveness in modeling long-range sequences. However, it is unclear whether its success can be attributed to its intricate parameterization and HiPPO initialization or simply due to State Space Models (SSMs). To further investigate the potential of deep SSMs, this study starts with exponential smoothing (ETS), a simple SSM, and proposes a stacked architecture by directly incorporating it into an element-wise MLP. The model achieves comparable results to S4 on the LRA benchmark despite increasing less than 1% of parameters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores how to better model long-range dependencies in sequential data. It compares different approaches to see which one works best. The researchers started with a simple method called exponential smoothing (ETS) and added more complexity to it. They found that this approach can achieve similar results to the Structured State Space (S4) model, even though they used much less computational power. |
