Adaptive Generative Modeling in Resource-Constrained Environments
Last modified: Mon May 24 01:52:33 2021 GMT.
Authors
Jung-Eun KimRichard Bradford
Max Del Giudice
Zhong Shao
Abstract
Modern generative techniques, deriving realistic data from incomplete or noisy inputs, require massive computation for rigorous results. These limitations hinder generative techniques from being incorporated in systems in resource-constrained environment, thus motivating methods that grant users control over the time-quality trade-offs for a reasonable "payoff" of execution cost. Hence, as a new paradigm for adaptively organizing and employing recurrent networks, we propose an architectural design for generative modeling achieving flexible quality. We boost the overall efficiency by introducing non-recurrent layers into stacked recurrent architectures. Accordingly, we design the architecture with no redundant recurrent cells so we avoid unnecessary overhead.
