Search Results for author: Divyansh Pareek

Found 2 papers, 1 papers with code

The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders

no code implementations ICML Workshop INNF 2021 Divyansh Pareek, Andrej Risteski

Training and using modern neural-network based latent-variable generative models (like Variational Autoencoders) often require simultaneously training a generative direction along with an inferential(encoding) direction, which approximates the posterior distribution over the latent variables.

Finding Input Characterizations for Output Properties in ReLU Neural Networks

1 code implementation9 Mar 2020 Saket Dingliwal, Divyansh Pareek, Jatin Arora

Deep Neural Networks (DNNs) have emerged as a powerful mechanism and are being increasingly deployed in real-world safety-critical domains.

Cannot find the paper you are looking for? You can Submit a new open access paper.