R
Rahul G. Krishnan
Researcher at Massachusetts Institute of Technology
Publications - 30
Citations - 1848
Rahul G. Krishnan is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Computer science & Generative model. The author has an hindex of 10, co-authored 15 publications receiving 1113 citations. Previous affiliations of Rahul G. Krishnan include Microsoft & New York University.
Papers
More filters
Proceedings ArticleDOI
Variational Autoencoders for Collaborative Filtering
TL;DR: In this article, a variational autoencoder (VAE) was extended to collaborative filtering for implicit feedback, and a generative model with multinomial likelihood and Bayesian inference for parameter estimation was proposed.
Proceedings Article
Structured Inference Networks for Nonlinear State Space Models
TL;DR: In this paper, a unified algorithm is proposed to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks.
Posted Content
Variational Autoencoders for Collaborative Filtering
TL;DR: In this paper, a variational autoencoder (VAE) was extended to collaborative filtering for implicit feedback, and a generative model with multinomial likelihood and Bayesian inference for parameter estimation was proposed.
Posted Content
Deep Kalman Filters.
TL;DR: A unified algorithm is introduced to efficiently learn a broad spectrum of Kalman filters and investigates the efficacy of temporal generative models for counterfactual inference, and introduces the "Healing MNIST" dataset where long-term structure, noise and actions are applied to sequences of digits.
Proceedings ArticleDOI
Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
Richard Chen,Chengkuan Chen,Yicong Li,Tiffany Y. Chen,Andrew D. Trister,Rahul G. Krishnan,Faisal Mahmood +6 more
TL;DR: HIPT with hierarchical pretraining outperforms current state-of-the-art methods for cancer subtyping and survival prediction, and self-supervised ViTs are able to model important inductive biases about the hierarchical structure of phenotypes in the tumor microenvironment.