Summary of Inversion-based Latent Bayesian Optimization, by Jaewon Chu et al.
Inversion-based Latent Bayesian Optimization
by Jaewon Chu, Jinyoung Park, Seunghun Lee, Hyunwoo J. Kim
First submitted to arxiv on: 8 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 proposes a new approach to latent Bayesian optimization (LBO) called Inversion-based Latent Bayesian Optimization (InvBO). The authors identify two issues with existing LBO methods: the “misalignment problem” caused by reconstruction errors in the encoder-decoder architecture, and the lack of consideration for the trust region’s potential in anchor selection. InvBO addresses these issues through an inversion method that searches for a latent code to reconstruct target data, and a potential-aware trust region anchor selection that considers the trust region’s capability for local optimization. The approach is demonstrated on nine real-world benchmarks, including molecule design and arithmetic expression fitting tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to improve an existing method called latent Bayesian optimization (LBO). LBO helps find the best solution by searching in a special space called the latent space. But some of these methods have problems that make them not work well. The authors of this paper came up with a new approach called InvBO, which solves these problems. It has two parts: one part finds the right spot in the latent space to start looking for solutions, and another part makes sure that where we look is good for finding a solution. They tested their method on several real-world tasks and it worked well. |
Keywords
» Artificial intelligence » Encoder decoder » Latent space » Optimization
