
CDT: Cascading Decision Trees for Explainable Reinforcement Learning
Deep Reinforcement Learning (DRL) has recently achieved significant adva...
read it

Continuous Graph Flow for Flexible Density Estimation
In this paper, we propose Continuous Graph Flow, a generative continuous...
read it

Noise Flow: Noise Modeling with Conditional Normalizing Flows
Modeling and synthesizing image noise is an important aspect in many com...
read it

Adapting GradCAM for Embedding Networks
The gradientweighted class activation mapping (GradCAM) method can fai...
read it

A Globally Normalized Neural Model for Semantic Parsing
In this paper, we propose a globally normalized model for contextfree g...
read it

Scalable Recommender Systems through Recursive Evidence Chains
Recommender systems can be formulated as a matrix completion problem, pr...
read it

A CoordinateFree Construction of Scalable Natural Gradient
Most neural networks are trained using firstorder optimization methods,...
read it

Interactive Learning of Environment Dynamics for Sequential Tasks
In order for robots and other artificial agents to efficiently learn to ...
read it

On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman
How to best explore in domains with sparse, delayed, and deceptive rewar...
read it

Tails of Triangular Flows
Triangular maps are a construct in probability theory that allows the tr...
read it

Safer Deep RL with Shallow MCTS: A Case Study in Pommerman
Safe reinforcement learning has many variants and it is still an open re...
read it

Metatrace: Online Stepsize Tuning by Metagradient Descent for Reinforcement Learning Control
Reinforcement learning (RL) has had many successes in both "deep" and "s...
read it

Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds
In this paper, we investigate Dimensionality reduction (DR) maps in an i...
read it

A general system of differential equations to model first order adaptive algorithms
First order optimization algorithms play a major role in large scale mac...
read it

Boosting Model Performance through Differentially Private Model Aggregation
A key factor in developing high performing machine learning models is th...
read it

Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL
Deep reinforcement learning (DRL) has achieved great successes in recent...
read it

FewShot Self Reminder to Overcome Catastrophic Forgetting
Deep neural networks are known to suffer the catastrophic forgetting pro...
read it

Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition
The Pommerman Team Environment is a recently proposed benchmark which in...
read it

Better LongRange Dependency By Bootstrapping A Mutual Information Regularizer
In this work, we develop a novel regularizer to improve the learning of ...
read it

Diachronic Embedding for Temporal Knowledge Graph Completion
Knowledge graphs (KGs) typically contain temporal facts indicating relat...
read it

Agent Modeling as Auxiliary Task for Deep Reinforcement Learning
In this paper we explore how actorcritic methods in deep reinforcement ...
read it

Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning
Deep reinforcement learning has achieved great successes in recent years...
read it

Action Guidance with MCTS for Deep Reinforcement Learning
Deep reinforcement learning has achieved great successes in recent years...
read it

Normalizing Flows: Introduction and Ideas
Normalizing Flows are generative models which produce tractable distribu...
read it

Graph Generation with Variational Recurrent Neural Network
Generating graph structures is a challenging problem due to the diverse ...
read it

Preventing Posterior Collapse in Sequence VAEs with Pooling
Variational Autoencoders (VAEs) hold great potential for modelling text,...
read it

Unsupervised Multilingual Alignment using Wasserstein Barycenter
We study unsupervised multilingual alignment, the problem of finding wor...
read it

PolarizedVAE: Proximity Based Disentangled Representation Learning for Text Generation
Learning disentangled representations of real world data is a challengin...
read it

OutofSample Representation Learning for MultiRelational Graphs
Many important problems can be formulated as reasoning in multirelation...
read it

Learning Discriminative Prototypes with Dynamic Time Warping
Dynamic Time Warping (DTW) is widely used for temporal data processing. ...
read it

Heterogeneous Multitask Learning with Expert Diversity
Predicting multiple heterogeneous biological and medical targets is a ch...
read it

TDGEN: Graph Generation With Tree Decomposition
We propose TDGEN, a graph generation framework based on tree decomposit...
read it
Borealis AI
Borealis AI is an RBC Institute for Research. We're dedicated to achieving stateoftheart in machine learning through curiositydriven research.