Summary of Learn: An Invex Loss For Outlier Oblivious Robust Online Optimization, by Adarsh Barik et al.
LEARN: An Invex Loss for Outlier Oblivious Robust Online Optimization
by Adarsh Barik, Anand Krishna, Vincent Y. F. Tan
First submitted to arxiv on: 12 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Optimization and Control (math.OC)
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 A novel online convex optimization framework is proposed that can withstand malicious outliers introduced by an adversary in unknown rounds. The Log Exponential Adjusted Robust and iNvex (LEARN) loss function is designed to mitigate the impact of these outliers, and a robust variant of online gradient descent is developed using this loss. Tight regret guarantees are established for the dynamic setting, with respect to uncorrupted rounds. Experimental validation supports the theoretical results. Additionally, a unified analysis framework is presented for developing online optimization algorithms for non-convex (invex) losses, providing regret bounds for the LEARN loss. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way for computers to learn and make decisions even when some of the information they’re given is wrong or misleading. It’s called the “Log Exponential Adjusted Robust and iNvex” (LEARN) method. This method helps machines ignore bad data and focus on what’s really important. The researchers show that their method works well in practice, and they also give a general framework for other people to use when creating similar methods. |
Keywords
» Artificial intelligence » Gradient descent » Loss function » Optimization
