paper-with-me

Papers

Generative Models with ELBOs Converging to Entropy Sums

2024-12-25 · Jan Warnken, Dmytro Velychko, Simon Damm, Asja Fischer, Jörg Lücke

The evidence lower bound (ELBO) is one of the most central objectives for probabilistic unsupervised learning. For the ELBOs of several generative models and model classes, we here prove convergence to entropy sums. As one result, we provide a list of generative models for which entropy convergence has been shown, so far, along with the corresponding expressions for entropy sums. Our considerations include very prominent generative models such as probabilistic PCA, sigmoid belief nets or Gaussian mixture models. However, we treat more models and entire model classes such as general mixtures of exponential family distributions. Our main contributions are the proofs for the individual models. For each given model we show that the conditions stated in Theorem 1 or Theorem 2 of [arXiv:2209.03077] are fulfilled such that by virtue of the theorems the given model's ELBO is equal to an entropy sum at all stationary points. The equality of the ELBO at stationary points applies under realistic conditions: for finite numbers of data points, for model/data mismatches, at any stationary point including saddle points etc, and it applies for any well behaved family of variational distributions.

📄 PDF Abstract BibTeX arXiv:2501.09022

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

Similar Papers 제목 키워드 기반

Learning Sparse Codes with Entropy-Based ELBOs

2023-11-03 · Dmytro Velychko, Simon Damm, Asja Fischer, Jörg Lücke

Standard probabilistic sparse coding assumes a Laplace prior, a linear mapping from latents to observables, and Gaussian observable distributions. We here derive a solely entropy-based learning objective for the paramete…

On the Convergence of the ELBO to Entropy Sums

2022-09-07 · Jörg Lücke, Jan Warnken

The variational lower bound (a.k.a. ELBO or free energy) is the central objective for many established as well as for many novel algorithms for unsupervised learning. Such algorithms usually increase the bound until para…

Sample as You Infer: Predictive Coding With Langevin Dynamics

2023-11-22 · Umais Zahid, Qinghai Guo, Zafeirios Fountas

We present a novel algorithm for parameter learning in generic deep generative models that builds upon the predictive coding (PC) framework of computational neuroscience. Our approach modifies the standard PC algorithm t…

Beta Diffusion

2023-09-14 · NeurIPS 2023 11 · Mingyuan Zhou, Tianqi Chen, Zhendong Wang, Huangjie Zheng

We introduce beta diffusion, a novel generative modeling method that integrates demasking and denoising to generate data within bounded ranges. Using scaled and shifted beta distributions, beta diffusion utilizes multipl…

Denoising

Tighter Variational Bounds are Not Necessarily Better

2018-02-13 · ICML 2018 7 · Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J. Maddison 외

We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient esti…