Research map / Probabilistic and scientific modeling / Variational and generative sampling
On Fenchel Mini-Max Learning
Chenyang Tao, Liqun Chen, Shuyang Dai, Junya Chen, Ke Bai, Dong Wang, Jianfeng Feng, Wenlian Lu, Georgiy Bobashev, Lawrence Carin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace VAE ELBO training with FML | VAE · MNIST | FID: 24.3 -> 22.7 | Improved |
| replace VAE ELBO training with FML | VAE · MS COCO | perplexity: 9.5 -> 8.6 | Improved |
| replace VAE ELBO training with FML | VAE · EMNLP WMT news | perplexity: 12.5 -> 11.6 | Improved |
| use FML instead of DFM (DAE score estimator) for GAN training | GAN · Cifar10 | FID: 30.7 -> 30.0 | Improved |
| use FML instead of noise contrastive estimation | unnormalized models · UCI wine-red | test log-likelihood: 7.29 -> 8.45 | Improved |
| use FML instead of NCE | unnormalized models · UCI htru2 | test log-likelihood: 22.05 -> 22.15 | No clear effect |
| use FML instead of naive Monte Carlo | unnormalized models · toy banana | parameter estimation error: 3.46 -> 3.05 | Improved |
| use FML instead of NCE | unnormalized models · toy wave | parameter estimation error: 1.20 -> 1.27 | Mixed |
| replace SVGD sampler with FML-trained sampler in soft Q-learning | soft Q-learning · Hopper, Swimmer, Reacher | reward | Improved |
Closest papers by meaning
- Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation (ICLR 2021 · similarity 0.86)
- Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity (ICLR 2018 · similarity 0.86)
- An Iterative Min-Min Optimization Method for Sparse Bayesian Learning (ICML 2024 · similarity 0.85)
- Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework (NeurIPS 2025 · similarity 0.85)
- Smooth Min-Max Monotonic Networks (ICML 2024 · similarity 0.85)
- Large Language Models to Enhance Bayesian Optimization (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
