paper-with-me

Papers

On Implicit Regularization in $β$-VAEs

2020-01-31 · Abhishek Kumar, Ben Poole

While the impact of variational inference (VI) on posterior inference in a fixed generative model is well-characterized, its role in regularizing a learned generative model when used in variational autoencoders (VAEs) is poorly understood. We study the regularizing effects of variational distributions on learning in generative models from two perspectives. First, we analyze the role that the choice of variational family plays in imparting uniqueness to the learned model by restricting the set of optimal generative models. Second, we study the regularization effect of the variational family on the local geometry of the decoding model. This analysis uncovers the regularizer implicit in the $\beta$-VAE objective, and leads to an approximation consisting of a deterministic autoencoding objective plus analytic regularizers that depend on the Hessian or Jacobian of the decoding model, unifying VAEs with recent heuristics proposed for training regularized autoencoders. We empirically verify these findings, observing that the proposed deterministic objective exhibits similar behavior to the $\beta$-VAE in terms of objective value and sample quality.

📄 PDF Abstract BibTeX arXiv:2002.00041

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Similar Papers 제목 키워드 기반

On Implicit Regularization in $\beta$-VAEs

2020-01-01 · ICML 2020 1 · Abhishek Kumar, Ben Poole

While the impact of variational inference (VI) on posterior inference in a fixed generative model is well-characterized, its role in regularizing a learned generative model when used in variational autoencoders (VAEs) is…

Variational Inference

Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs

2025-05-30 · Zihao Chen, Yu Xiang, Wenyong Wang

Despite the success in learning semantically meaningful, unsupervised disentangled representations, variational autoencoders (VAEs) and their variants face a fundamental theoretical challenge: substantial evidence indica…

DisentanglementInductive Bias

Implicit Deep Latent Variable Models for Text Generation

2019-08-30 · IJCNLP 2019 11 · Le Fang, Chunyuan Li, Jianfeng Gao, Wen Dong 외

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. …

Language ModelingLanguage ModellingResponse GenerationStyle Transfer+1

A Bayesian Nonparametrics View into Deep Representations

2020-12-01 · NeurIPS 2020 12 · Michał Jamroż, Marcin Kurdziel, Mateusz Opala

We investigate neural network representations from a probabilistic perspective. Specifically, we leverage Bayesian nonparametrics to construct models of neural activations in Convolutional Neural Networks (CNNs) and late…

Memorization

Variational Rank Reduction Autoencoder

2025-05-14 · Jad Mounayer, Alicia Tierz, Jerome Tomezyk, Chady Ghnatios 외

Deterministic Rank Reduction Autoencoders (RRAEs) enforce by construction a regularization on the latent space by applying a truncated SVD. While this regularization makes Autoencoders more powerful, using them for gener…