[1809.09087] Implicit Maximum Likelihood Estimation
Abstract:Implicit probabilistic models are models defined naturally in terms of a sampling procedure and often induces a likelihood function that cannot be expressed explicitly. We develop a simple method for estimating parameters in implicit models that does not require knowledge of the form of the likelihood function or any derived quantities, but can be shown to be equivalent to maximizing likelihood under some conditions. Our result holds in the non-asymptotic parametric setting, where both the capacity of the model and the number of data examples are finite. We also demonstrate encouraging experimental results.
Implicit Maximum Likelihood Estimation Ke Li Jitendra Malik Department of Electrical Engineering and Computer Sciences University of California, Berkeley Berkeley, CA 94720 United States arXiv:1809.09087v2 [cs.LG] 22…
saved by
related reading
- Sampling: Two Basic Algorithmsgregorygundersen.com
- [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
- 2409.02908arxiv.org
- A Gallery of Methods Beyond RL — Part I: Sampling Methodsshengyu-feng.github.io
- [2010.02502] Denoising Diffusion Implicit Modelsarxiv.org
- arxiv.org/pdf/1805.08522arxiv.org
- NeurIPS-2021-understanding-end-to-end-model-based-reinforcement-learning-methods-as-implicit-parameterization-Supplemental.pdflis.csail.mit.edu
- Tips for Training Likelihood Modelsblog.evjang.com
- Denoising Density Estimatorsarxiv.org
- [1906.02691] An Introduction to Variational Autoencodersarxiv.org
- https://arxiv.org/pdf/2006.11239arxiv.org
- [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org