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 Razvan Pascanu

On the Role of Optimization in Double Descent: A Least Squares Study


Jul 27, 2021
Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, Amal Rannen-Triki, Razvan Pascanu


  Access Paper or Ask Questions

Reasoning-Modulated Representations


Jul 19, 2021
Petar Veličković, Matko Bošnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell

* ICML 2021 Workshop on Self-Supervised Learning for Reasoning and Perception (Spotlight Talk). 7 pages, 3 figures 

  Access Paper or Ask Questions

Task-agnostic Continual Learning with Hybrid Probabilistic Models


Jun 24, 2021
Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu


  Access Paper or Ask Questions

Predicting Unreliable Predictions by Shattering a Neural Network


Jun 15, 2021
Xu Ji, Razvan Pascanu, Devon Hjelm, Andrea Vedaldi, Balaji Lakshminarayanan, Yoshua Bengio


  Access Paper or Ask Questions

Top-KAST: Top-K Always Sparse Training


Jun 07, 2021
Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae, Simon Osindero, Erich Elsen

* Advances in Neural Information Processing Systems, 33, 20744-20754 

  Access Paper or Ask Questions

A study on the plasticity of neural networks


May 31, 2021
Tudor Berariu, Wojciech Czarnecki, Soham De, Jorg Bornschein, Samuel Smith, Razvan Pascanu, Claudia Clopath


  Access Paper or Ask Questions

Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error


May 27, 2021
Stanislav Fort, Andrew Brock, Razvan Pascanu, Soham De, Samuel L. Smith


  Access Paper or Ask Questions

Continual World: A Robotic Benchmark For Continual Reinforcement Learning


May 23, 2021
Maciej Wołczyk, Michał Zając, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś


  Access Paper or Ask Questions

Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective


May 11, 2021
Florin Gogianu, Tudor Berariu, Mihaela Rosca, Claudia Clopath, Lucian Busoniu, Razvan Pascanu

* Accepted at ICML2021 

  Access Paper or Ask Questions

Regularized Behavior Value Estimation


Mar 17, 2021
Caglar Gulcehre, Sergio Gómez Colmenarejo, Ziyu Wang, Jakub Sygnowski, Thomas Paine, Konrad Zolna, Yutian Chen, Matthew Hoffman, Razvan Pascanu, Nando de Freitas


  Access Paper or Ask Questions

Behavior Priors for Efficient Reinforcement Learning


Oct 27, 2020
Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh, Leonard Hasenclever, Razvan Pascanu, Jonathan Schwarz, Guillaume Desjardins, Wojciech Marian Czarnecki, Arun Ahuja, Yee Whye Teh, Nicolas Heess

* Submitted to Journal of Machine Learning Research (JMLR) 

  Access Paper or Ask Questions

BYOL works even without batch statistics


Oct 20, 2020
Pierre H. Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andrew Brock, Samuel Smith, Soham De, Razvan Pascanu, Bilal Piot, Michal Valko


  Access Paper or Ask Questions

Linear Mode Connectivity in Multitask and Continual Learning


Oct 09, 2020
Seyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur, Razvan Pascanu, Hassan Ghasemzadeh


  Access Paper or Ask Questions

Temporal Difference Uncertainties as a Signal for Exploration


Oct 05, 2020
Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann, Francesco Visin, Alexandre Galashov, Steven Kapturowski, Diana L. Borsa, Nicolas Heess, Andre Barreto, Razvan Pascanu

* 8 pages, 11 figures, 5 tables 

  Access Paper or Ask Questions

Understanding the Role of Training Regimes in Continual Learning


Jun 12, 2020
Seyed Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh


  Access Paper or Ask Questions

Pointer Graph Networks


Jun 11, 2020
Petar Veličković, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell


  Access Paper or Ask Questions

A Deep Neural Network's Loss Surface Contains Every Low-dimensional Pattern


Jan 02, 2020
Wojciech Marian Czarnecki, Simon Osindero, Razvan Pascanu, Max Jaderberg


  Access Paper or Ask Questions

Continual Unsupervised Representation Learning


Oct 31, 2019
Dushyant Rao, Francesco Visin, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu, Raia Hadsell

* NeurIPS 2019 

  Access Paper or Ask Questions

Improving the Gating Mechanism of Recurrent Neural Networks


Oct 22, 2019
Albert Gu, Caglar Gulcehre, Tom Le Paine, Matt Hoffman, Razvan Pascanu


  Access Paper or Ask Questions

Stabilizing Transformers for Reinforcement Learning


Oct 13, 2019
Emilio Parisotto, H. Francis Song, Jack W. Rae, Razvan Pascanu, Caglar Gulcehre, Siddhant M. Jayakumar, Max Jaderberg, Raphael Lopez Kaufman, Aidan Clark, Seb Noury, Matthew M. Botvinick, Nicolas Heess, Raia Hadsell


  Access Paper or Ask Questions

Meta-Learning with Warped Gradient Descent


Aug 30, 2019
Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Hujun Yin, Raia Hadsell

* 27 pages, 11 figures, 4 tables 

  Access Paper or Ask Questions

Task Agnostic Continual Learning via Meta Learning


Jun 12, 2019
Xu He, Jakub Sygnowski, Alexandre Galashov, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu


  Access Paper or Ask Questions

Meta-learning of Sequential Strategies


May 08, 2019
Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg

* DeepMind Technical Report (15 pages, 6 figures) 

  Access Paper or Ask Questions

Information asymmetry in KL-regularized RL


May 03, 2019
Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever, Dhruva Tirumala, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Yee Whye Teh, Razvan Pascanu, Nicolas Heess

* Accepted as a conference paper at ICLR 2019 

  Access Paper or Ask Questions

Ray Interference: a Source of Plateaus in Deep Reinforcement Learning


Apr 25, 2019
Tom Schaul, Diana Borsa, Joseph Modayil, Razvan Pascanu

* Full version of RLDM abstract 

  Access Paper or Ask Questions

A RAD approach to deep mixture models


Mar 18, 2019
Laurent Dinh, Jascha Sohl-Dickstein, Razvan Pascanu, Hugo Larochelle

* 9 pages of main content, 4 pages of appendices 

  Access Paper or Ask Questions

Exploiting Hierarchy for Learning and Transfer in KL-regularized RL


Mar 18, 2019
Dhruva Tirumala, Hyeonwoo Noh, Alexandre Galashov, Leonard Hasenclever, Arun Ahuja, Greg Wayne, Razvan Pascanu, Yee Whye Teh, Nicolas Heess


  Access Paper or Ask Questions

Distilling Policy Distillation


Feb 06, 2019
Wojciech Marian Czarnecki, Razvan Pascanu, Simon Osindero, Siddhant M. Jayakumar, Grzegorz Swirszcz, Max Jaderberg

* Accepted at AISTATS 2019 

  Access Paper or Ask Questions

Functional Regularisation for Continual Learning using Gaussian Processes


Jan 31, 2019
Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh


  Access Paper or Ask Questions