Latent Dimensionality and Random Encoders
نویسندگان
چکیده
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders.
منابع مشابه
On the Latent Space of Wasserstein Auto-Encoders
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders. We highlight the potential of WAEs for representation learning with promising results on a benchmark disentanglement task.
متن کاملGaussian Process Latent Random Field
The Gaussian process latent variable model (GPLVM) is an unsupervised probabilistic model for nonlinear dimensionality reduction. A supervised extension, called discriminative GPLVM (DGPLVM), incorporates supervisory information into GPLVM to enhance the classification performance. However, its limitation of the latent space dimensionality to at most C − 1 (C is the number of classes) leads to ...
متن کاملDimensionality Reduction Techniques for Document Clustering- A Survey
Dimensionality reduction technique is applied to get rid of the inessential terms like redundant and noisy terms in documents. In this paper a systematic study is conducted for seven dimensionality reduction methods such as Latent Semantic Indexing (LSI), Random Projection (RP), Principle Component Analysis (PCA) and CUR decomposition, Latent Dirichlet Allocation(LDA), Singular value decomposit...
متن کاملThe Comparison of Two Models for Evaluation of Pre-internship Comprehensive Test: Classical and Latent Trait
Introduction: Despite the widespread use of pre-internship comprehensive test and its importance in medical students’ assessment, there is a paucity of the studies that can provide a systematic psychometric analysis of the items of this test. Thus, the present study sought to assess March 2011 pre-internship test using classical and latent trait models and compare their results. Methods: In th...
متن کاملRandom Walk Features for Network-aware Topic Models
Topic Models such as Latent Dirichlet Allocation (LDA) have been successfully applied as a data analysis and dimensionality reduction tool. With the emergence of social networks, many datasets are available in the form of a network with typed nodes (documents, authors, URLs, publication dates, . . . ) and edges (authorship, citation, friendship, . . . ). We propose a network-aware topic model t...
متن کامل