
OffDynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
We propose a simple, practical, and intuitive approach for domain adapta...
read it

On RewardFree Reinforcement Learning with Linear Function Approximation
Rewardfree reinforcement learning (RL) is a framework which is suitable...
read it

Demystifying SelfSupervised Learning: An InformationTheoretical Framework
Selfsupervised representation learning adopts selfdefined signals as s...
read it

Neural Methods for Pointwise Dependency Estimation
Since its inception, the neural estimation of mutual information (MI) ha...
read it

Feature Robust Optimal Transport for Highdimensional Data
Optimal transport is a machine learning technique with applications incl...
read it

Provably Efficient Reinforcement Learning with General Value Function Approximation
Value function approximation has demonstrated phenomenal empirical succe...
read it

Guaranteeing Reproducibility in Deep Learning Competitions
To encourage the development of methods with reproducible and robust tra...
read it

Exploring Controllable Text Generation Techniques
Neural controllable text generation is an important area gaining attenti...
read it

Topological Sort for Sentence Ordering
Sentence ordering is the task of arranging the sentences of a given text...
read it

Politeness Transfer: A Tag and Generate Approach
This paper introduces a new task of politeness transfer which involves c...
read it

Interpretable Multimodal Routing for Human Multimodal Language
The human language has heterogeneous sources of information, including t...
read it

WeaklySupervised Reinforcement Learning for Controllable Behavior
Reinforcement learning (RL) is a powerful framework for learning to take...
read it

On Emergent Communication in Competitive MultiAgent Teams
Several recent works have found the emergence of grounded compositional ...
read it

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
Multitask reinforcement learning (RL) aims to simultaneously learn poli...
read it

Differentiable Reasoning over a Virtual Knowledge Base
We consider the task of answering complex multihop questions using a co...
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...
read it

Capsules with Inverted DotProduct Attention Routing
We introduce a new routing algorithm for capsule networks, in which a ch...
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...
read it

Geometric Capsule Autoencoders for 3D Point Clouds
We propose a method to learn object representations from 3D point clouds...
read it

Worst Cases Policy Gradients
Recent advances in deep reinforcement learning have demonstrated the cap...
read it

Multiple Futures Prediction
Temporal prediction is critical for making intelligent and robust decisi...
read it

Enhanced Convolutional Neural Tangent Kernels
Recent research shows that for training with ℓ_2 loss, convolutional neu...
read it

Learning Data Manipulation for Augmentation and Weighting
Manipulating data, such as weighting data examples or augmenting with ne...
read it

Complex Transformer: A Framework for Modeling ComplexValued Sequence
While deep learning has received a surge of interest in a variety of fie...
read it

Harnessing the Power of Infinitely Wide Deep Nets on Smalldata Tasks
Recent research shows that the following two models are equivalent: (a) ...
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...
read it

LSMISinkhorn: Semisupervised SquaredLoss Mutual Information Estimation with Optimal Transport
Estimating mutual information is an important machine learning and stati...
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...
read it

MineRL: A LargeScale Dataset of Minecraft Demonstrations
The sample inefficiency of standard deep reinforcement learning methods ...
read it

Learning Neural Networks with Adaptive Regularization
Feedforward neural networks can be understood as a combination of an in...
read it

Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
There has been an increased interest in multimodal language processing i...
read it

Deep Gamblers: Learning to Abstain with Portfolio Theory
We deal with the selective classification problem (supervisedlearning p...
read it

XLNet: Generalized Autoregressive Pretraining for Language Understanding
With the capability of modeling bidirectional contexts, denoising autoen...
read it

"My Way of Telling a Story": Persona based Grounded Story Generation
Visual storytelling is the task of generating stories based on a sequenc...
read it

Efficient Exploration via State Marginal Matching
To solve tasks with sparse rewards, reinforcement learning algorithms mu...
read it

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
The history of learning for control has been an exciting back and forth ...
read it

Multimodal Transformer for Unaligned Multimodal Language Sequences
Human language is often multimodal, which comprehends a mixture of natur...
read it

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
While graph kernels (GKs) are easy to train and enjoy provable theoretic...
read it

Strong and Simple Baselines for Multimodal Utterance Embeddings
Human language is a rich multimodal signal consisting of spoken words, f...
read it

On Exact Computation with an Infinitely Wide Neural Net
How well does a classic deep net architecture like AlexNet or VGG19 clas...
read it

The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
Though deep reinforcement learning has led to breakthroughs in many diff...
read it

Video Relationship Reasoning using Gated SpatioTemporal Energy Graph
Visual relationship reasoning is a crucial yet challenging task for unde...
read it

Concurrent Meta Reinforcement Learning
Stateoftheart meta reinforcement learning algorithms typically assume...
read it

The Omniglot Challenge: A 3Year Progress Report
Three years ago, we released the Omniglot dataset for developing more hu...
read it

Embodied Multimodal Multitask Learning
Recent efforts on training visual navigation agents conditioned on langu...
read it

TransformerXL: Attentive Language Models Beyond a FixedLength Context
Transformer networks have a potential of learning longerterm dependency...
read it

Connecting the Dots Between MLE and RL for Sequence Generation
Sequence generation models such as recurrent networks can be trained wit...
read it

Stackelberg GAN: Towards Provable Minimax Equilibrium via MultiGenerator Architectures
We study the problem of alleviating the instability issue in the GAN tra...
read it

On the Complexity of Exploration in GoalDriven Navigation
Building agents that can explore their environments intelligently is a c...
read it

Point Cloud GAN
Generative Adversarial Networks (GAN) can achieve promising performance ...
read it
Ruslan Salakhutdinov
is this you? claim profile
Associate Professor, Machine Learning Department at Carnegie Mellon University