Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Pascal Poupart

Pascal Poupart

University of Waterloo

RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation


Oct 01, 2021
Md Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart

Figure 1 for RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation
Figure 2 for RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation
Figure 3 for RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation
Figure 4 for RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation

  Access Paper or Ask Questions

NTS-NOTEARS: Learning Nonparametric Temporal DAGs With Time-Series Data and Prior Knowledge


Sep 09, 2021
Xiangyu Sun, Guiliang Liu, Pascal Poupart, Oliver Schulte

Figure 1 for NTS-NOTEARS: Learning Nonparametric Temporal DAGs With Time-Series Data and Prior Knowledge
Figure 2 for NTS-NOTEARS: Learning Nonparametric Temporal DAGs With Time-Series Data and Prior Knowledge
Figure 3 for NTS-NOTEARS: Learning Nonparametric Temporal DAGs With Time-Series Data and Prior Knowledge
Figure 4 for NTS-NOTEARS: Learning Nonparametric Temporal DAGs With Time-Series Data and Prior Knowledge
* Preprint, under review 
  Access Paper or Ask Questions

Quantifying and Improving Transferability in Domain Generalization


Jun 07, 2021
Guojun Zhang, Han Zhao, Yaoliang Yu, Pascal Poupart

Figure 1 for Quantifying and Improving Transferability in Domain Generalization
Figure 2 for Quantifying and Improving Transferability in Domain Generalization
Figure 3 for Quantifying and Improving Transferability in Domain Generalization
Figure 4 for Quantifying and Improving Transferability in Domain Generalization
* 36 pages, 7 figures 
  Access Paper or Ask Questions

Robust Embeddings Via Distributions


Apr 17, 2021
Kira A. Selby, Yinong Wang, Ruizhe Wang, Peyman Passban, Ahmad Rashid, Mehdi Rezagholizadeh, Pascal Poupart

Figure 1 for Robust Embeddings Via Distributions
Figure 2 for Robust Embeddings Via Distributions
Figure 3 for Robust Embeddings Via Distributions
Figure 4 for Robust Embeddings Via Distributions

  Access Paper or Ask Questions

Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map


Mar 01, 2021
Elmira Amirloo, Mohsen Rohani, Ershad Banijamali, Jun Luo, Pascal Poupart

Figure 1 for Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
Figure 2 for Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
Figure 3 for Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
Figure 4 for Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map

  Access Paper or Ask Questions

Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning


Dec 25, 2020
Ershad Banijamali, Mohsen Rohani, Elmira Amirloo, Jun Luo, Pascal Poupart

Figure 1 for Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning
Figure 2 for Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning
Figure 3 for Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning
Figure 4 for Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning

  Access Paper or Ask Questions

Newton-type Methods for Minimax Optimization


Jun 25, 2020
Guojun Zhang, Kaiwen Wu, Pascal Poupart, Yaoliang Yu

Figure 1 for Newton-type Methods for Minimax Optimization
Figure 2 for Newton-type Methods for Minimax Optimization
Figure 3 for Newton-type Methods for Minimax Optimization
Figure 4 for Newton-type Methods for Minimax Optimization
* 26 pages 
  Access Paper or Ask Questions

Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory


Apr 16, 2020
Nabiha Asghar, Ivan Kobyzev, Jesse Hoey, Pascal Poupart, Muhammad Bilal Sheikh

Figure 1 for Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
Figure 2 for Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
Figure 3 for Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
Figure 4 for Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory

  Access Paper or Ask Questions

Multi Type Mean Field Reinforcement Learning


Mar 09, 2020
Sriram Ganapathi Subramanian, Pascal Poupart, Matthew E. Taylor, Nidhi Hegde

Figure 1 for Multi Type Mean Field Reinforcement Learning
Figure 2 for Multi Type Mean Field Reinforcement Learning
Figure 3 for Multi Type Mean Field Reinforcement Learning
Figure 4 for Multi Type Mean Field Reinforcement Learning
* Paper to appear in the Proceedings of International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) 2020. Revised version has some typos corrected 
  Access Paper or Ask Questions

Complete Hierarchy of Relaxation for Constrained Signomial Positivity


Mar 08, 2020
Allen Houze Wang, Priyank Jaini, Yaoliang Yu, Pascal Poupart


  Access Paper or Ask Questions

Optimality and Stability in Non-Convex-Non-Concave Min-Max Optimization


Feb 27, 2020
Guojun Zhang, Pascal Poupart, Yaoliang Yu

Figure 1 for Optimality and Stability in Non-Convex-Non-Concave Min-Max Optimization
Figure 2 for Optimality and Stability in Non-Convex-Non-Concave Min-Max Optimization
Figure 3 for Optimality and Stability in Non-Convex-Non-Concave Min-Max Optimization
Figure 4 for Optimality and Stability in Non-Convex-Non-Concave Min-Max Optimization
* 39 pages 
  Access Paper or Ask Questions

Batch norm with entropic regularization turns deterministic autoencoders into generative models


Feb 25, 2020
Amur Ghose, Abdullah Rashwan, Pascal Poupart

Figure 1 for Batch norm with entropic regularization turns deterministic autoencoders into generative models
Figure 2 for Batch norm with entropic regularization turns deterministic autoencoders into generative models
Figure 3 for Batch norm with entropic regularization turns deterministic autoencoders into generative models
Figure 4 for Batch norm with entropic regularization turns deterministic autoencoders into generative models

  Access Paper or Ask Questions

Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games


Feb 21, 2020
Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre CΓ΄tΓ©, MikulΓ‘Ε‘ Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton

Figure 1 for Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games
Figure 2 for Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games
Figure 3 for Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games
Figure 4 for Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games

  Access Paper or Ask Questions

Unsupervised Multilingual Alignment using Wasserstein Barycenter


Jan 28, 2020
Xin Lian, Kshitij Jain, Jakub Truszkowski, Pascal Poupart, Yaoliang Yu

Figure 1 for Unsupervised Multilingual Alignment using Wasserstein Barycenter
Figure 2 for Unsupervised Multilingual Alignment using Wasserstein Barycenter
Figure 3 for Unsupervised Multilingual Alignment using Wasserstein Barycenter
Figure 4 for Unsupervised Multilingual Alignment using Wasserstein Barycenter
* Work in progress; comments welcome! 
  Access Paper or Ask Questions

MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection


Jan 09, 2020
Abdullah Rashwan, Rishav Agarwal, Agastya Kalra, Pascal Poupart

Figure 1 for MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
Figure 2 for MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
Figure 3 for MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
Figure 4 for MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
* This is the full paper for arXiv:1908.04646 with more applications, experiments, and ablation study 
  Access Paper or Ask Questions

Matrix Nets: A New Deep Architecture for Object Detection


Aug 14, 2019
Abdullah Rashwan, Agastya Kalra, Pascal Poupart

Figure 1 for Matrix Nets: A New Deep Architecture for Object Detection
Figure 2 for Matrix Nets: A New Deep Architecture for Object Detection
Figure 3 for Matrix Nets: A New Deep Architecture for Object Detection
* Short paper, stay tuned for the full paper! 
  Access Paper or Ask Questions

Comparing EM with GD in Mixture Models of Two Components


Jul 19, 2019
Guojun Zhang, Pascal Poupart, George Trimponias

Figure 1 for Comparing EM with GD in Mixture Models of Two Components
Figure 2 for Comparing EM with GD in Mixture Models of Two Components
Figure 3 for Comparing EM with GD in Mixture Models of Two Components
Figure 4 for Comparing EM with GD in Mixture Models of Two Components
* To appear at UAI 2019; Camera-ready version; A small modification at page 5 
  Access Paper or Ask Questions

Time2Vec: Learning a Vector Representation of Time


Jul 11, 2019
Seyed Mehran Kazemi, Rishab Goel, Sepehr Eghbali, Janahan Ramanan, Jaspreet Sahota, Sanjay Thakur, Stella Wu, Cathal Smyth, Pascal Poupart, Marcus Brubaker

Figure 1 for Time2Vec: Learning a Vector Representation of Time
Figure 2 for Time2Vec: Learning a Vector Representation of Time
Figure 3 for Time2Vec: Learning a Vector Representation of Time
Figure 4 for Time2Vec: Learning a Vector Representation of Time

  Access Paper or Ask Questions

Diachronic Embedding for Temporal Knowledge Graph Completion


Jul 06, 2019
Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker, Pascal Poupart

Figure 1 for Diachronic Embedding for Temporal Knowledge Graph Completion
Figure 2 for Diachronic Embedding for Temporal Knowledge Graph Completion
Figure 3 for Diachronic Embedding for Temporal Knowledge Graph Completion

  Access Paper or Ask Questions

Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey


May 27, 2019
Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain, Ivan Kobyzev, Akshay Sethi, Peter Forsyth, Pascal Poupart

Figure 1 for Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey
Figure 2 for Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey
Figure 3 for Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey
Figure 4 for Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey
* 49 pages, 2 figures 
  Access Paper or Ask Questions

SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks


Jan 11, 2019
Alejandro Molina, Antonio Vergari, Karl Stelzner, Robert Peharz, Pranav Subramani, Nicola Di Mauro, Pascal Poupart, Kristian Kersting

Figure 1 for SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks
* 4 pages, 1 figure, code 
  Access Paper or Ask Questions

Progressive Memory Banks for Incremental Domain Adaptation


Nov 01, 2018
Nabiha Asghar, Lili Mou, Kira A. Selby, Kevin D. Pantasdo, Pascal Poupart, Xin Jiang

Figure 1 for Progressive Memory Banks for Incremental Domain Adaptation
Figure 2 for Progressive Memory Banks for Incremental Domain Adaptation
Figure 3 for Progressive Memory Banks for Incremental Domain Adaptation
Figure 4 for Progressive Memory Banks for Incremental Domain Adaptation

  Access Paper or Ask Questions

Variational Attention for Sequence-to-Sequence Models


Jun 21, 2018
Hareesh Bahuleyan, Lili Mou, Olga Vechtomova, Pascal Poupart

Figure 1 for Variational Attention for Sequence-to-Sequence Models
Figure 2 for Variational Attention for Sequence-to-Sequence Models
Figure 3 for Variational Attention for Sequence-to-Sequence Models
Figure 4 for Variational Attention for Sequence-to-Sequence Models
* In Proceedings of COLING 2018. Also accepted by TADGM [email protected] 2018 for presentation 
  Access Paper or Ask Questions

On Improving Deep Reinforcement Learning for POMDPs


May 24, 2018
Pengfei Zhu, Xin Li, Pascal Poupart, Guanghui Miao

Figure 1 for On Improving Deep Reinforcement Learning for POMDPs
Figure 2 for On Improving Deep Reinforcement Learning for POMDPs
Figure 3 for On Improving Deep Reinforcement Learning for POMDPs
Figure 4 for On Improving Deep Reinforcement Learning for POMDPs
* 7 pages, 6 figures, 3 tables 
  Access Paper or Ask Questions

Unsupervised Video Object Segmentation for Deep Reinforcement Learning


May 20, 2018
Vik Goel, Jameson Weng, Pascal Poupart

Figure 1 for Unsupervised Video Object Segmentation for Deep Reinforcement Learning
Figure 2 for Unsupervised Video Object Segmentation for Deep Reinforcement Learning
Figure 3 for Unsupervised Video Object Segmentation for Deep Reinforcement Learning
Figure 4 for Unsupervised Video Object Segmentation for Deep Reinforcement Learning

  Access Paper or Ask Questions