Ruslan Salakhutdinov

is this you? claim profile

∙ 4 followers
UNIVERSITY OF TORONTO ∙ MIT ∙ Apple Inc. ∙ Carnegie Mellon University

Associate Professor, Machine Learning Department at Carnegie Mellon University

Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation

Many real-world applications such as robotics provide hard constraints o...
04/04/2021 ∙ by Emilio Parisotto, et al. ∙ 0 ∙ share

read it
Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification

In the standard Markov decision process formalism, users specify tasks b...
03/23/2021 ∙ by Benjamin Eysenbach, et al. ∙ 0 ∙ share

read it
Self-supervised Representation Learning with Relative Predictive Coding

This paper introduces Relative Predictive Coding (RPC), a new contrastiv...
03/21/2021 ∙ by Yao-Hung Hubert Tsai, et al. ∙ 32 ∙ share

read it
Instabilities of Offline RL with Pre-Trained Neural Representation

In offline reinforcement learning (RL), we seek to utilize offline data ...
03/08/2021 ∙ by Ruosong Wang, et al. ∙ 15 ∙ share

read it
On Proximal Policy Optimization's Heavy-tailed Gradients

Modern policy gradient algorithms, notably Proximal Policy Optimization ...
02/20/2021 ∙ by Saurabh Garg, et al. ∙ 0 ∙ share

read it
Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

We present the Open Predicate Query Language (OPQL); a method for constr...
02/14/2021 ∙ by Haitian Sun, et al. ∙ 0 ∙ share

read it
The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors

Although deep reinforcement learning has led to breakthroughs in many di...
01/26/2021 ∙ by William H. Guss, et al. ∙ 11 ∙ share

read it
Understanding the Tradeoffs in Client-Side Privacy for Speech Recognition

Existing approaches to ensuring privacy of user speech data primarily fo...
01/22/2021 ∙ by Peter Wu, et al. ∙ 0 ∙ share

read it
Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment

The natural world is abundant with concepts expressed via visual, acoust...
12/04/2020 ∙ by Paul Pu Liang, et al. ∙ 6 ∙ share

read it
C-Learning: Learning to Achieve Goals via Recursive Classification

We study the problem of predicting and controlling the future state dist...
11/17/2020 ∙ by Benjamin Eysenbach, et al. ∙ 12 ∙ share

read it
Close Category Generalization

Out-of-distribution generalization is a core challenge in machine learni...
11/17/2020 ∙ by Yao-Yuan Yang, et al. ∙ 13 ∙ share

read it
Unsupervised Domain Adaptation for Visual Navigation

Advances in visual navigation methods have led to intelligent embodied n...
10/27/2020 ∙ by Shangda Li, et al. ∙ 5 ∙ share

read it
Planning with Submodular Objective Functions

We study planning with submodular objective functions, where instead of ...
10/22/2020 ∙ by Ruosong Wang, et al. ∙ 0 ∙ share

read it
Case Study: Deontological Ethics in NLP

Recent work in natural language processing (NLP) has focused on ethical ...
10/09/2020 ∙ by Shrimai Prabhumoye, et al. ∙ 0 ∙ share

read it
Graph Adversarial Networks: Protecting Information against Adversarial Attacks

We study the problem of protecting information when learning with graph ...
09/28/2020 ∙ by Peiyuan Liao, et al. ∙ 20 ∙ share

read it
Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

In this paper, we study bidirectional LSTM network for the task of text ...
09/08/2020 ∙ by Devendra Singh Sachan, et al. ∙ 0 ∙ share

read it
Few-Shot Learning with Intra-Class Knowledge Transfer

We consider the few-shot classification task with an unbalanced dataset,...
08/22/2020 ∙ by Vivek Roy, et al. ∙ 23 ∙ share

read it
Towards Debiasing Sentence Representations

As natural language processing methods are increasingly deployed in real...
07/16/2020 ∙ by Paul Pu Liang, et al. ∙ 0 ∙ share

read it
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

We propose a simple, practical, and intuitive approach for domain adapta...
06/24/2020 ∙ by Benjamin Eysenbach, et al. ∙ 15 ∙ share

read it
On Reward-Free Reinforcement Learning with Linear Function Approximation

Reward-free reinforcement learning (RL) is a framework which is suitable...
06/19/2020 ∙ by Ruosong Wang, et al. ∙ 0 ∙ share

read it
Demystifying Self-Supervised Learning: An Information-Theoretical Framework

Self-supervised representation learning adopts self-defined signals as s...
06/10/2020 ∙ by Yao-Hung Hubert Tsai, et al. ∙ 22 ∙ share

read it
Neural Methods for Point-wise Dependency Estimation

Since its inception, the neural estimation of mutual information (MI) ha...
06/09/2020 ∙ by Yao-Hung Hubert Tsai, et al. ∙ 13 ∙ share

read it
Feature Robust Optimal Transport for High-dimensional Data

Optimal transport is a machine learning technique with applications incl...
05/25/2020 ∙ by Mathis Petrovich, et al. ∙ 13 ∙ share

read it
Provably Efficient Reinforcement Learning with General Value Function Approximation

Value function approximation has demonstrated phenomenal empirical succe...
05/21/2020 ∙ by Ruosong Wang, et al. ∙ 13 ∙ share

read it
Guaranteeing Reproducibility in Deep Learning Competitions

To encourage the development of methods with reproducible and robust tra...
05/12/2020 ∙ by Brandon Houghton, et al. ∙ 3 ∙ share

read it
Exploring Controllable Text Generation Techniques

Neural controllable text generation is an important area gaining attenti...
05/04/2020 ∙ by Shrimai Prabhumoye, et al. ∙ 0 ∙ share

read it
Topological Sort for Sentence Ordering

Sentence ordering is the task of arranging the sentences of a given text...
05/01/2020 ∙ by Shrimai Prabhumoye, et al. ∙ 0 ∙ share

read it
Politeness Transfer: A Tag and Generate Approach

This paper introduces a new task of politeness transfer which involves c...
04/29/2020 ∙ by Aman Madaan, et al. ∙ 0 ∙ share

read it
Interpretable Multimodal Routing for Human Multimodal Language

The human language has heterogeneous sources of information, including t...
04/29/2020 ∙ by Yao-Hung Hubert Tsai, et al. ∙ 0 ∙ share

read it
Weakly-Supervised Reinforcement Learning for Controllable Behavior

Reinforcement learning (RL) is a powerful framework for learning to take...
04/06/2020 ∙ by Lisa Lee, et al. ∙ 11 ∙ share

read it
On Emergent Communication in Competitive Multi-Agent Teams

Several recent works have found the emergence of grounded compositional ...
03/04/2020 ∙ by Paul Pu Liang, et al. ∙ 10 ∙ share

read it
Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement

Multi-task reinforcement learning (RL) aims to simultaneously learn poli...
02/25/2020 ∙ by Benjamin Eysenbach, et al. ∙ 11 ∙ share

read it
Differentiable Reasoning over a Virtual Knowledge Base

We consider the task of answering complex multi-hop questions using a co...
02/25/2020 ∙ by Bhuwan Dhingra, et al. ∙ 0 ∙ share

read it
Learning Not to Learn in the Presence of Noisy Labels

Learning in the presence of label noise is a challenging yet important t...
02/16/2020 ∙ by Liu Ziyin, et al. ∙ 11 ∙ share

read it
Capsules with Inverted Dot-Product Attention Routing

We introduce a new routing algorithm for capsule networks, in which a ch...
02/12/2020 ∙ by Yao-Hung Hubert Tsai, et al. ∙ 5 ∙ share

read it
Think Locally, Act Globally: Federated Learning with Local and Global Representations

Federated learning is an emerging research paradigm to train models on p...
01/06/2020 ∙ by Paul Pu Liang, et al. ∙ 6 ∙ share

read it
Geometric Capsule Autoencoders for 3D Point Clouds

We propose a method to learn object representations from 3D point clouds...
12/06/2019 ∙ by Nitish Srivastava, et al. ∙ 21 ∙ share

read it
Worst Cases Policy Gradients

Recent advances in deep reinforcement learning have demonstrated the cap...
11/09/2019 ∙ by Yichuan Charlie Tang, et al. ∙ 20 ∙ share

read it
Multiple Futures Prediction

Temporal prediction is critical for making intelligent and robust decisi...
11/04/2019 ∙ by Yichuan Charlie Tang, et al. ∙ 23 ∙ share

read it
Enhanced Convolutional Neural Tangent Kernels

Recent research shows that for training with ℓ_2 loss, convolutional neu...
11/03/2019 ∙ by Zhiyuan Li, et al. ∙ 17 ∙ share

read it
Learning Data Manipulation for Augmentation and Weighting

Manipulating data, such as weighting data examples or augmenting with ne...
10/28/2019 ∙ by Zhiting Hu, et al. ∙ 30 ∙ share

read it
Complex Transformer: A Framework for Modeling Complex-Valued Sequence

While deep learning has received a surge of interest in a variety of fie...
10/22/2019 ∙ by Muqiao Yang, et al. ∙ 10 ∙ share

read it
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

Recent research shows that the following two models are equivalent: (a) ...
10/03/2019 ∙ by Sanjeev Arora, et al. ∙ 16 ∙ share

read it
On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps

The study of universal approximation of arbitrary functions f: X→Y by ne...
10/03/2019 ∙ by William H. Guss, et al. ∙ 12 ∙ share

read it
LSMI-Sinkhorn: Semi-supervised Squared-Loss Mutual Information Estimation with Optimal Transport

Estimating mutual information is an important machine learning and stati...
09/05/2019 ∙ by Yanbin Liu, et al. ∙ 6 ∙ share

read it
Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel

Transformer is a powerful architecture that achieves superior performanc...
08/30/2019 ∙ by Yao-Hung Hubert Tsai, et al. ∙ 32 ∙ share

read it
MineRL: A Large-Scale Dataset of Minecraft Demonstrations

The sample inefficiency of standard deep reinforcement learning methods ...
07/29/2019 ∙ by William H. Guss, et al. ∙ 7 ∙ share

read it
Learning Neural Networks with Adaptive Regularization

Feed-forward neural networks can be understood as a combination of an in...
07/14/2019 ∙ by Han Zhao, et al. ∙ 3 ∙ share

read it
Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization

There has been an increased interest in multimodal language processing i...
07/01/2019 ∙ by Paul Pu Liang, et al. ∙ 17 ∙ share

read it
Deep Gamblers: Learning to Abstain with Portfolio Theory

We deal with the selective classification problem (supervised-learning p...
06/29/2019 ∙ by Liu Ziyin, et al. ∙ 8 ∙ share

read it

Ruslan Salakhutdinov

Featured Co-authors