Search Results for author: Vaibhav Saxena

Found 6 papers, 1 papers with code

Generalizable Pose Estimation Using Implicit Scene Representations

no code implementations26 May 2023 Vaibhav Saxena, Kamal Rahimi Malekshan, Linh Tran, Yotto Koga

Most widely used methods learn to infer the object pose in a discriminative setup where the model filters useful information to infer the exact pose of the object.

Density Estimation Object +1

Clockwork Variational Autoencoders

2 code implementations NeurIPS 2021 Vaibhav Saxena, Jimmy Ba, Danijar Hafner

We introduce the Clockwork VAE (CW-VAE), a video prediction model that leverages a hierarchy of latent sequences, where higher levels tick at slower intervals.

Video Prediction

Video Prediction with Variational Temporal Hierarchies

no code implementations1 Jan 2021 Vaibhav Saxena, Jimmy Ba, Danijar Hafner

Deep learning has shown promise for accurately predicting high-dimensional video sequences.

Video Prediction

Effective Elastic Scaling of Deep Learning Workloads

no code implementations24 Jun 2020 Vaibhav Saxena, K. R. Jayaram, Saurav Basu, Yogish Sabharwal, Ashish Verma

We design a fast dynamic programming based optimizer to solve this problem in real-time to determine jobs that can be scaled up/down, and use this optimizer in an autoscaler to dynamically change the allocated resources and batch sizes of individual DL jobs.

Dyna-AIL : Adversarial Imitation Learning by Planning

no code implementations8 Mar 2019 Vaibhav Saxena, Srinivasan Sivanandan, Pulkit Mathur

Adversarial methods for imitation learning have been shown to perform well on various control tasks.

Imitation Learning

PowerAI DDL

no code implementations7 Aug 2017 Minsik Cho, Ulrich Finkler, Sameer Kumar, David Kung, Vaibhav Saxena, Dheeraj Sreedhar

We train Resnet-101 on Imagenet 22K with 64 IBM Power8 S822LC servers (256 GPUs) in about 7 hours to an accuracy of 33. 8 % validation accuracy.

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