R
Ruslan Salakhutdinov
Researcher at Carnegie Mellon University
Publications - 457
Citations - 142495
Ruslan Salakhutdinov is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 107, co-authored 410 publications receiving 115921 citations. Previous affiliations of Ruslan Salakhutdinov include Carnegie Learning & University of Toronto.
Papers
More filters
Proceedings Article
Instabilities of Offline RL with Pre-Trained Neural Representation
TL;DR: In this article, the authors study the effect of sample-efficient offline RL using pre-trained neural networks and show that substantial error amplification does occur even when using such pretrained representations.
Posted Content
Selecting the Best in GANs Family: a Post Selection Inference Framework
Yao-Hung Hubert Tsai,Makoto Yamada,Denny Wu,Ruslan Salakhutdinov,Ichiro Takeuchi,Kenji Fukumizu +5 more
TL;DR: In this paper, a U-statistics estimate of maximum mean discrepancy was proposed to measure the distribution discrepancy between generated and real images, and a GAN analysis framework was proposed for selecting and testing the "best" member in GANs family using the Post Selection Inference (PSI) algorithm.
Posted Content
Data-Dependent Path Normalization in Neural Networks
TL;DR: A unified framework for neural net normalization, regularization and optimization is proposed, which includes Path-SGD and Batch-Normalization and interpolates between them across two different dimensions and investigates issue of invariance of the optimization, data dependence and the connection with natural gradients.
Posted Content
ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers
TL;DR: ConditionalQA as mentioned in this paper is a dataset that contains complex questions with conditional answers, i.e., the answers are only applicable when certain conditions apply, and it is designed to motivate further research in answering complex questions over long documents.