Dynamic Narrowing of VAE Bottlenecks Using GECO and L0 Regularization
When designing variational autoencoders (VAEs) or other types of latent space models, the dimensionality of the latent space is typically defined upfront. In this process, it is possible that the number of dimensions is under- or overprovisioned for the application at hand. In case the dimensionality is not predefined, this parameter is usually determined using time- and resource-consuming cross-validation. For these reasons we have developed a technique to shrink the latent space dimensionality of VAEs automatically and on-the-fly during training using Generalized ELBO with Constrained Optimization (GECO) and the $L_0$-Augment-REINFORCE-Merge ($L_0$-ARM) gradient estimator. The GECO optimizer ensures that we are not violating a predefined upper bound on the reconstruction error. This paper presents the algorithmic details of our method along with experimental results on five different datasets. We find that our training procedure is stable and that the latent space can be pruned effectively without violating the GECO constraints.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EdgeConvFormer: Dynamic Graph CNN and Transformer based Anomaly Detection in Multivariate Time Series
Transformer-based models for anomaly detection in multivariate time series can benefit from the self-attention mechanism due to its advantage in modeling long-term dependencies. However, Transformer-based anomaly detecti…
Anomaly DetectionTime SeriesGECO-MT: The Ghent Eye-tracking Corpus of Machine Translation
In the present paper, we describe a large corpus of eye movement data, collected during natural reading of a human translation and a machine translation of a full novel. This data set, called GECO-MT (Ghent Eye tracking …
Machine TranslationTranslationGeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency
We present a novel framework to regularize Neural Radiance Field (NeRF) in a few-shot setting with a geometry-aware consistency regularization. The proposed approach leverages a rendered depth map at unobserved viewpoint…
NeRFGeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes. By fusing residual motion and depth priors, GeCo produces interpretable, d…
Video GenerationEdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of CNNs hinders the deployment of CNNs onto resource-constrained embed…
Image ClassificationModel CompressionImage Cropping