Summary of Latent Energy-based Odyssey: Black-box Optimization Via Expanded Exploration in the Energy-based Latent Space, by Peiyu Yu and Dinghuai Zhang and Hengzhi He and Xiaojian Ma and Ruiyao Miao and Yifan Lu and Yasi Zhang and Deqian Kong and Ruiqi Gao and Jianwen Xie and Guang Cheng and Ying Nian Wu
Latent Energy-Based Odyssey: Black-Box Optimization via Expanded Exploration in the Energy-Based Latent Space
by Peiyu Yu, Dinghuai Zhang, Hengzhi He, Xiaojian Ma, Ruiyao Miao, Yifan Lu, Yasi Zhang, Deqian Kong, Ruiqi Gao, Jianwen Xie, Guang Cheng, Ying Nian Wu
First submitted to arxiv on: 27 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Applications (stat.AP)
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 Offline Black-Box Optimization (BBO) method tackles the challenges of optimizing black-box functions by learning a compressed yet accurate representation of the input-design space. The approach formulates an learnable energy-based latent space, using Noise-intensified Telescoping density-Ratio Estimation (NTRE) to learn an accurate model without Markov Chain Monte Carlo. This learned latent space is then used for gradient-based sampling from an inverse model, encouraging expanded exploration around high-value design modes. The proposed method outperforms previous methods on both synthetic and real-world datasets, such as the design-bench suite. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Offline Black-Box Optimization aims to optimize a black-box function using knowledge from a pre-collected dataset of function values and corresponding input designs. This paper introduces a new approach that learns a compressed yet accurate representation of the design-value joint space, allowing for effective exploration of high-value input design modes. The method uses a learnable energy-based latent space and a Noise-intensified Telescoping density-Ratio Estimation scheme to optimize the black-box function without relying on costly Markov Chain Monte Carlo methods. This approach is shown to significantly improve upon previous methods on both synthetic and real-world datasets. |
Keywords
» Artificial intelligence » Latent space » Optimization
