3 papers
cs.LG2021
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders
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…
cs.LG2020
Finding Input Characterizations for Output Properties in ReLU Neural Networks
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. Despite the widespread success, their co…
cs.CG2018
Strong Collapse for Persistence
Jean-Daniel Boissonnat, Siddharth Pritam, Divyansh Pareek
We introduce a fast and memory efficient approach to compute the persistent homology (PH) of a sequence of simplicial complexes. The basic idea is to simplify the complexes of the…