Summary of Fourier Basis Density Model, by Alfredo De La Fuente et al.
Fourier Basis Density Model
by Alfredo De la Fuente, Saurabh Singh, Johannes Ballé
First submitted to arxiv on: 23 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
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 proposed probability density model uses a constrained Fourier basis and is trained end-to-end, offering a lightweight and flexible solution for approximating multi-modal 1D densities. Compared to the deep factorized model introduced in [1], this approach achieves lower cross-entropy at a similar computational cost. The authors also demonstrate the method’s utility in learned compression tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary We developed a new probability density model that can be trained easily and doesn’t use too many resources. It works well for tricky 1D densities with multiple modes. This model is better than another one we looked at, called the deep factorized model, because it gets lower cross-entropy without using more computer power. We also showed how this method can help compress data in a smart way. |
Keywords
* Artificial intelligence * Cross entropy * Multi modal * Probability
