Mila > Équipe > Prakash Panangaden

Prakash Panangaden

Membre académique principal
Professeur titulaire, McGill University

Prakash Panangaden est membre académique principal de Mila. Professeur à l’École d’informatique à l’Université McGill, il s’intéresse aux fondements mathématiques de l’apprentissage machine. Il a travaillé sur la bisimulation, les métriques et l’approximation des processus de Markov. Il a également étudié les logiques pour les systèmes probabilistes, la dualité de Stone pour les processus de Markov et les langages de programmation. Récemment il a travaillé sur une extension quantitative de la logique et de la sémantique équationnelle pour un lambda-calcul stochastique. Dans d’autres travaux récents, ses collaborateurs et lui-même ont développé une notion de minimisation approximative des automates finis pondérés et de la bisimulation pour de tels automates. Cela l’a conduit à étudier l’apprentissage des automates. Auparavant, il a également étudié la théorie de l’information quantique, la sémantique de la programmation concurrente, la logique modale et la théorie des catégories.

Publications

2021-12

MICo: Improved representations via sampling-based state similarity for Markov decision processes
Pablo Samuel Castro, Tyler Kastner, Prakash Panangaden and Mark Rowland
NEURIPS 2021
(2021-12-06)
papers.nips.ccPDF

2021-10

Weighted automata are compact and actively learnable
Artem Kaznatcheev and Prakash Panangaden

2021-09

Proceedings 17th International Conference on Quantum Physics and Logic: Preface
Pablo Arrighi, Shane Mansfield, Prakash Panangaden and Benoît Valiron
Electronic Proceedings in Theoretical Computer Science
(2021-09-06)
dx.doi.org
Tensor of quantitative equational theories
Giorgio Bacci, Radu Mardare, Prakash Panangaden and Gordon D. Plotkin
CALCO 2021
(2021-09-03)
drops.dagstuhl.dePDF
Proceedings 17th International Conference on Quantum Physics and Logic
Benoît Valiron, Shane Mansfield, Pablo Arrighi and Prakash Panangaden
arXiv preprint arXiv:2109.01534
(2021-09-03)
ui.adsabs.harvard.eduPDF

2021-06

Universal semantics for the stochastic λ-calculus
Pedro H. Azevedo de Amorim, Dexter Kozen, Radu Mardare, Prakash Panangaden and Michael Roberts
LICS 2021
(2021-06-29)
pureportal.strath.ac.uk
Fixed-points for quantitative equational logics
Radu Mardare, Prakash Panangaden and Gordon Plotkin
Universal Semantics for the Stochastic Lambda-Calculus
Pedro H Azevedo de Amorim, Dexter Kozen, Radu Mardare, Prakash Panangaden and Michael Roberts
Extracting Weighted Automata for Approximate Minimization in Language Modelling.
arXiv preprint arXiv:2106.02965
(2021-06-05)
ui.adsabs.harvard.eduPDF
MICo: Learning improved representations via sampling-based state similarity for Markov decision processes
Pablo Samuel Castro, Tyler Kastner, Prakash Panangaden and Mark Rowland
arXiv preprint arXiv:2106.08229
(2021-06-03)
ui.adsabs.harvard.eduPDF

2021-02

Optimal Spectral-Norm Approximate Minimization of Weighted Finite Automata
Borja Balle, Clara Lacroce, Prakash Panangaden, Doina Precup and Guillaume Rabusseau

2020-12

Quantitative Equational Reasoning
Giorgio Bacci, Radu Mardare, Prakash Panangaden and Gordon D. Plotkin
(venue unknown)
(2020-12-01)
eksperter.aau.dk

2020-11

Bisimulation metrics and norms for real-weighted automata
Borja Balle, Pascale Gourdeau and Prakash Panangaden
Information & Computation
(2020-11-18)
www.sciencedirect.com
A Study of Policy Gradient on a Class of Exactly Solvable Models.
Gavin McCracken, Colin Daniels, Rosie Zhao, Anna Brandenberger, Prakash Panangaden and Doina Precup
arXiv preprint arXiv:2011.01859
(2020-11-03)
ui.adsabs.harvard.eduPDF

2020-10

Towards a Classification of Behavioural Equivalences in Continuous-time Markov Processes.
Linan Chen, Florence Clerc and Prakash Panangaden
Electronic Notes in Theoretical Computer Science
(2020-10-01)
www.sciencedirect.com

2020-07

Latent Variable Modelling with Hyperbolic Normalizing Flows
Joey Bose, Ariella Smofsky, Renjie Liao, Prakash Panangaden and Will Hamilton
ICML 2020
(2020-07-12)
proceedings.mlr.pressPDF

2020-06

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms.

2020-02

Latent Variable Modelling with Hyperbolic Normalizing Flows
Avishek Joey Bose, Ariella Smofsky, Renjie Liao, Prakash Panangaden and William L. Hamilton
arXiv preprint arXiv:2002.06336
(2020-02-15)
arxiv.orgPDF

2020-01

Minimisation in Logical Form.
Nick Bezhanishvili, Marcello M. Bonsangue, Helle Hvid Hansen, Dexter Kozen, Clemens Kupke, Prakash Panangaden and Alexandra Silva
Outstanding Contributions to Logic
(2020-01-01)
www.narcis.nl[LATEST on arXiv preprint arXiv:2005.11551 (2020-05-23)]

2019-11

Bisimulation for Feller-Dynkin Processes
Linan Chen, Florence Clerc and Prakash Panangaden
Electronic Notes in Theoretical Computer Science
(2019-11-30)
www.sciencedirect.com[Also on arXiv: Logic in Computer Science (2019-04-01)]

2019-10

Singular value automata and approximate minimization
Mathematical Structures in Computer Science
(2019-10-01)
www.cambridge.orgPDF

2019-08

Expressiveness of probabilistic modal logics: A gradual approach
Florence Clerc, Nathanaël Fijalkow, Bartek Klin and Prakash Panangaden
Information & Computation
(2019-08-01)
www.sciencedirect.com

2019-05

Singular value automata and approximate minimization
Mathematical Structures in Computer Science
(2019-05-27)
ui.adsabs.harvard.eduPDF

2019-01

Temporally Extended Metrics for Markov Decision Processes.
AAAI 2019
(2019-01-01)
dblp.uni-trier.dePDF

Publications collected and formatted using Paperoni