Summary of Settling Time Vs. Accuracy Tradeoffs For Clustering Big Data, by Andrew Draganov et al.
Settling Time vs. Accuracy Tradeoffs for Clustering Big Data
by Andrew Draganov, David Saulpic, Chris Schwiegelshohn
First submitted to arxiv on: 2 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Data Structures and Algorithms (cs.DS)
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 paper investigates the runtime limits of k-means and k-median clustering on large datasets, exploring ways to efficiently compress data for clustering. It highlights the trade-off between accuracy and speed, showcasing algorithms that balance these factors. The authors introduce a novel algorithm for constructing coresets via sensitivity sampling in effectively linear time, outperforming previous approaches. They also demonstrate the spectrum of sampling strategies across various settings, providing a comprehensive blueprint for effective clustering regardless of data size. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Clustering is a way to group similar things together. This paper looks at how long it takes to do this with big datasets. Right now, most clustering methods take too long and are slow. The authors want to find a faster way to do clustering that still gives good results. They tested different ways of compressing data (like taking random samples) and found that some work better than others. They also discovered an algorithm that can create “coresets” – shortcuts that help with clustering – really fast. This helps us understand when we need these shortcuts and when we can use simpler methods. The authors share their code and experiments so others can try it out. |
Keywords
* Artificial intelligence * Clustering * K means
