Summary of Decomposable Transformer Point Processes, by Aristeidis Panos
Decomposable Transformer Point Processes
by Aristeidis Panos
First submitted to arxiv on: 26 Sep 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG)
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 new framework for modeling marked point processes, which combines the advantages of attention-based architectures with efficient inference. The approach models the conditional distribution of inter-event times using a mixture of log-normals and the conditional probability mass function for marks using a Transformer-based architecture. This results in state-of-the-art performance in predicting the next event given its history. The method also outperforms a baseline specifically designed for long-horizon prediction, with inference requiring significantly less time. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better understand how to model and predict events that happen over time. It uses new ideas from machine learning to make predictions more accurate and fast. The approach is tested on a challenging problem called long-horizon prediction, where it performs well and is much faster than other methods. |
Keywords
» Artificial intelligence » Attention » Inference » Machine learning » Probability » Transformer
