paper-with-me

Papers

A Closer Look at Disentangling in $β$-VAE

2019-12-11 · Harshvardhan Sikka, Weishun Zhong, Jun Yin, Cengiz Pehlevan

In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others. If data generating factors are also statistically independent, disentangled representations can be formed by Bayesian inference of latent variables. We examine a generalization of the Variational Autoencoder (VAE), $\beta$-VAE, for learning such representations using variational inference. $\beta$-VAE enforces conditional independence of its bottleneck neurons controlled by its hyperparameter $\beta$. This condition is in general not compatible with the statistical independence of latents. By providing analytical and numerical arguments, we show that this incompatibility leads to a non-monotonic inference performance in $\beta$-VAE with a finite optimal $\beta$.

📄 PDF Abstract BibTeX arXiv:1912.05127

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceVariational Inference

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

A closer look at the performance of neural language models on reflexive anaphor licensing

2020-01-01 · SCiL 2020 1 · Jennifer Hu, Sherry Yong Chen, Roger Levy

A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples

2021-08-01 · Findings (ACL) 2021 8 · Yuxuan Wang, Wanxiang Che, Ivan Titov, Shay B. Cohen 외

Disentangling Neural Disjunctive Normal Form Models

2025-07-14 · Kexin Gu Baugh, Vincent Perreault, Matthew Baugh, Luke Dickens 외 arxiv

Neural Disjunctive Normal Form (DNF) based models are powerful and interpretable approaches to neuro-symbolic learning and have shown promising results in classification and reinforcement learning settings without prior …

Reinforcement Learning

Noise or Signal: The Role of Image Backgrounds in Object Recognition

2020-06-17 · ICLR 2021 1 · Kai Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry

We assess the tendency of state-of-the-art object recognition models to depend on signals from image backgrounds. We create a toolkit for disentangling foreground and background signal on ImageNet images, and find that (…

BIG-bench Machine LearningObject Recognition

A Structural Approach to Growth-at-Risk

2024-10-06 · Robert Wojciechowski

We identify the structural impulse responses of quantiles of the outcome variable to a shock. Our estimation strategy explicitly distinguishes treatment from control variables, allowing us to model responses of unconditi…