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
Posted Content
C-Learning: Learning to Achieve Goals via Recursive Classification
TL;DR: This work lays a principled foundation for goal-conditioned RL as density estimation, providing justification for goalschooling methods used in prior work, and an off-policy variant of this algorithm allows us to predict the future state distribution of a new policy, without collecting new experience.
Proceedings Article
Transformation Autoregressive Networks
Junier B. Oliva,Avinava Dubey,Manzil Zaheer,Barnabás Póczos,Ruslan Salakhutdinov,Eric P. Xing,Jeff Schneider +6 more
TL;DR: In this article, a comprehensive study over both real world and synthetic data, the authors show for that jointly leveraging transformations of variables and autoregressive conditional models, results in a considerable improvement in performance.
Posted Content
On Reward-Free Reinforcement Learning with Linear Function Approximation
TL;DR: In this article, the authors give an algorithm for reward-free RL in the linear Markov decision process setting where both the transition and the reward admit linear representations, and the sample complexity of their algorithm is polynomial in the feature dimension and the planning horizon, and is independent of the number of states and actions.
Posted Content
Capsules with Inverted Dot-Product Attention Routing
TL;DR: In this paper, a child capsule is routed to a parent capsule based only on agreement between the parent's state and the child's vote, which improves the performance of capsule networks.
Proceedings Article
Iterative Refinement of the Approximate Posterior for Directed Belief Networks
R Devon Hjelm,Ruslan Salakhutdinov,Kyunghyun Cho,Nebojsa Jojic,Vince D. Calhoun,Junyoung Chung +5 more
TL;DR: This article proposed an iterative refinement procedure for improving the approximate posterior of the recognition network and showed that training with the refined posterior is competitive with state-of-the-art methods.