Borealis AI

Borealis AI is an RBC Institute for Research. We're dedicated to achieving state-of-the-art in machine learning through curiosity-driven research.

CDT: Cascading Decision Trees for Explainable Reinforcement Learning

Deep Reinforcement Learning (DRL) has recently achieved significant adva...
11/15/2020 ∙ by Zihan Ding, et al. ∙ 30 ∙ share

read it
Continuous Graph Flow for Flexible Density Estimation

In this paper, we propose Continuous Graph Flow, a generative continuous...
08/07/2019 ∙ by Zhiwei Deng, et al. ∙ 21 ∙ share

read it
Noise Flow: Noise Modeling with Conditional Normalizing Flows

Modeling and synthesizing image noise is an important aspect in many com...
08/22/2019 ∙ by Abdelrahman Abdelhamed, et al. ∙ 12 ∙ share

read it
Adapting Grad-CAM for Embedding Networks

The gradient-weighted class activation mapping (Grad-CAM) method can fai...
01/17/2020 ∙ by Lei Chen, et al. ∙ 9 ∙ share

read it
A Globally Normalized Neural Model for Semantic Parsing

In this paper, we propose a globally normalized model for context-free g...
06/07/2021 ∙ by Chenyang Huang, et al. ∙ 7 ∙ share

read it
Scalable Recommender Systems through Recursive Evidence Chains

Recommender systems can be formulated as a matrix completion problem, pr...
07/05/2018 ∙ by Elias Tragas, et al. ∙ 6 ∙ share

read it
A Coordinate-Free Construction of Scalable Natural Gradient

Most neural networks are trained using first-order optimization methods,...
08/30/2018 ∙ by Kevin Luk, et al. ∙ 6 ∙ share

read it
Interactive Learning of Environment Dynamics for Sequential Tasks

In order for robots and other artificial agents to efficiently learn to ...
07/19/2019 ∙ by Robert Loftin, et al. ∙ 5 ∙ share

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...
07/26/2019 ∙ by Chao Gao, et al. ∙ 5 ∙ share

read it
Tails of Triangular Flows

Triangular maps are a construct in probability theory that allows the tr...
07/10/2019 ∙ by Priyank Jaini, et al. ∙ 2 ∙ share

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...
04/10/2019 ∙ by Bilal Kartal, et al. ∙ 1 ∙ share

read it
Metatrace: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control

Reinforcement learning (RL) has had many successes in both "deep" and "s...
05/10/2018 ∙ by Kenny Young, et al. ∙ 0 ∙ share

read it
Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds

In this paper, we investigate Dimensionality reduction (DR) maps in an i...
10/31/2018 ∙ by Kry Yik Chau Lui, et al. ∙ 0 ∙ share

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...
10/31/2018 ∙ by André Belotto da Silva, et al. ∙ 0 ∙ share

read it
Boosting Model Performance through Differentially Private Model Aggregation

A key factor in developing high performing machine learning models is th...
11/12/2018 ∙ by Sophia Collet, et al. ∙ 0 ∙ share

read it
Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL

Deep reinforcement learning (DRL) has achieved great successes in recent...
11/30/2018 ∙ by Bilal Kartal, et al. ∙ 0 ∙ share

read it
Few-Shot Self Reminder to Overcome Catastrophic Forgetting

Deep neural networks are known to suffer the catastrophic forgetting pro...
12/03/2018 ∙ by Junfeng Wen, et al. ∙ 0 ∙ share

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...
04/20/2019 ∙ by Chao Gao, et al. ∙ 0 ∙ share

read it
Better Long-Range Dependency By Bootstrapping A Mutual Information Regularizer

In this work, we develop a novel regularizer to improve the learning of ...
05/28/2019 ∙ by Yanshuai Cao, et al. ∙ 0 ∙ share

read it
Diachronic Embedding for Temporal Knowledge Graph Completion

Knowledge graphs (KGs) typically contain temporal facts indicating relat...
07/06/2019 ∙ by Rishab Goel, et al. ∙ 0 ∙ share

read it
Agent Modeling as Auxiliary Task for Deep Reinforcement Learning

In this paper we explore how actor-critic methods in deep reinforcement ...
07/22/2019 ∙ by Pablo Hernandez-Leal, et al. ∙ 0 ∙ share

read it
Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning

Deep reinforcement learning has achieved great successes in recent years...
07/24/2019 ∙ by Bilal Kartal, et al. ∙ 0 ∙ share

read it
Action Guidance with MCTS for Deep Reinforcement Learning

Deep reinforcement learning has achieved great successes in recent years...
07/25/2019 ∙ by Bilal Kartal, et al. ∙ 0 ∙ share

read it
Normalizing Flows: Introduction and Ideas

Normalizing Flows are generative models which produce tractable distribu...
08/25/2019 ∙ by Ivan Kobyzev, et al. ∙ 0 ∙ share

read it
Graph Generation with Variational Recurrent Neural Network

Generating graph structures is a challenging problem due to the diverse ...
10/02/2019 ∙ by Shih-Yang Su, et al. ∙ 0 ∙ share

read it
Preventing Posterior Collapse in Sequence VAEs with Pooling

Variational Autoencoders (VAEs) hold great potential for modelling text,...
11/10/2019 ∙ by Teng Long, et al. ∙ 0 ∙ share

read it
Unsupervised Multilingual Alignment using Wasserstein Barycenter

We study unsupervised multilingual alignment, the problem of finding wor...
01/28/2020 ∙ by Xin Lian, et al. ∙ 0 ∙ share

read it
Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation

Learning disentangled representations of real world data is a challengin...
04/22/2020 ∙ by Vikash Balasubramanian, et al. ∙ 0 ∙ share

read it
Out-of-Sample Representation Learning for Multi-Relational Graphs

Many important problems can be formulated as reasoning in multi-relation...
04/28/2020 ∙ by Marjan Albooyeh, et al. ∙ 0 ∙ share

read it
Learning Discriminative Prototypes with Dynamic Time Warping

Dynamic Time Warping (DTW) is widely used for temporal data processing. ...
03/17/2021 ∙ by Xiaobin Chang, et al. ∙ 0 ∙ share

read it
Heterogeneous Multi-task Learning with Expert Diversity

Predicting multiple heterogeneous biological and medical targets is a ch...
06/20/2021 ∙ by Raquel Aoki, et al. ∙ 0 ∙ share

read it
TD-GEN: Graph Generation With Tree Decomposition

We propose TD-GEN, a graph generation framework based on tree decomposit...
06/20/2021 ∙ by Hamed Shirzad, et al. ∙ 0 ∙ share

read it

Borealis AI

Featured Researchers