paper-with-me

홈 › Papers

Generalization Gap in Amortized Inference

2022-05-23 · Mingtian Zhang, Peter Hayes, David Barber

The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression. In this work, we study the generalization of a popular class of probabilistic model - the Variational Auto-Encoder (VAE). We discuss the two generalization gaps that affect VAEs and show that overfitting is usually dominated by amortized inference. Based on this observation, we propose a new training objective that improves the generalization of amortized inference. We demonstrate how our method can improve performance in the context of image modeling and lossless compression.

📄 PDF Abstract BibTeX arXiv:2205.11640

Code (1)

zmtomorrow/generalizationgapinamortizedinference 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Amortized Inference Regularization

2018-05-23 · NeurIPS 2018 12 · Rui Shu, Hung H. Bui, Shengjia Zhao, Mykel J. Kochenderfer 외

The variational autoencoder (VAE) is a popular model for density estimation and representation learning. Canonically, the variational principle suggests to prefer an expressive inference model so that the variational app…

Density EstimationRepresentation Learning

A Statistical Assessment of Amortized Inference Under Signal-to-Noise Variation and Distribution Shift

2026-01-12 · Roy Shivam Ram Shreshtth, Arnab Hazra, Gourab Mukherjee arxiv

Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex and large-scale predictive problems. The recent suc…

Bayesian Inference

Amortized Variational Inference: A Systematic Review

2022-09-22 · Ankush Ganguly, Sanjana Jain, Ukrit Watchareeruetai

The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be …

Representation LearningVariational Inference

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

2024-07-23 · Sojin Lee, Dogyun Park, Inho Kong, Hyunwoo J. Kim

Recent studies on inverse problems have proposed posterior samplers that leverage the pre-trained diffusion models as powerful priors. These attempts have paved the way for using diffusion models in a wide range of inver…

ColorizationDeblurringDenoisingImage Colorization+6

Bayesian Program Learning by Decompiling Amortized Knowledge

2023-06-13 · Alessandro B. Palmarini, Christopher G. Lucas, N. Siddharth

DreamCoder is an inductive program synthesis system that, whilst solving problems, learns to simplify search in an iterative wake-sleep procedure. The cost of search is amortized by training a neural search policy, reduc…

Program inductionProgram Synthesis