Improving Sequential Latent Variable Models with Autoregressive Flows
We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of reference, removing temporal correlations, and simplifying the modeling of higher-level dynamics. This technique provides a simple, general-purpose method for improving sequence modeling, with connections to existing and classical techniques. We demonstrate the proposed approach both with standalone flow-based models and as a component within sequential latent variable models. Results are presented on three benchmark video datasets, where autoregressive flow-based dynamics improve log-likelihood performance over baseline models. Finally, we illustrate the decorrelation and improved generalization properties of using flow-based dynamics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, whic…
Machine TranslationNMTTranslationHierarchical Autoregressive Modeling for Neural Video Compression
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models. We draw a connection between such autore…
Density EstimationVideo CompressionGenerative Video Compression as Hierarchical Variational Inference
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models. We draw a connection between such autore…
Density EstimationVariational InferenceVideo CompressionNon-autoregressive electron flow generation for reaction prediction
Reaction prediction is a fundamental problem in computational chemistry. Existing approaches typically generate a chemical reaction by sampling tokens or graph edits sequentially, conditioning on previously generated out…
Computational chemistryDecoderPredictionNatural Image Manipulation for Autoregressive Models Using Fisher Scores
Deep autoregressive models are one of the most powerful models that exist today which achieve state-of-the-art bits per dim. However, they lie at a strict disadvantage when it comes to controlled sample generation compar…
Image Manipulation