Prakash Panangaden

Core Academic Member
Prakash Panangaden
Full Professor, McGill University
Prakash Panangaden

Prakash Panangaden is a Core academic member of Mila. Professor at the School of Computer Science at McGill University, he is interested in mathematical foundations of machine learning.  He has worked on bisimulation, metrics and approximation for Markov processes. He has also worked on logics for probabilistic systems, Stone duality for Markov processes and programming languages.  His recent activity includes a quantitative extension of equational logic and semantics for a stochastic lambda-calculus. In other recent work, he and his collaborators developed a notion of approximate minimization of weighted finite automata and bisimulation for such automata.  This has led to current activity in automata learning. Past research activities include quantum information theory, concurrent programming semantics, modal logic and category theory.

Publications

2020-11

Universal Semantics for the Stochastic Lambda-Calculus.
Pedro Amorim, Dexter Kozen, Radu Mardare, Prakash Panangaden and Michael Roberts
arXiv: Logic in Computer Science
(2020-11-29)
dblp.uni-trier.dePDF
Weighted automata are compact and actively learnable.
Artem Kaznatcheev and Prakash Panangaden
arXiv preprint arXiv:2011.10498
(2020-11-20)
dblp.uni-trier.dePDF
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)
arxiv.orgPDF
Bisimulation metrics and norms for real-weighted automata
Borja Balle, Pascale Gourdeau and Prakash Panangaden
Information & Computation
(2020-11-01)
api.elsevier.com

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)
api.elsevier.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)
ui.adsabs.harvard.eduPDF

2020-05

Minimisation in Logical Form.
Nick Bezhanishvili, Marcello M. Bonsangue, Helle Hvid Hansen, Dexter Kozen, Clemens Kupke, Prakash Panangaden and Alexandra Silva
arXiv preprint arXiv:2005.11551
(2020-05-23)
dblp.uni-trier.dePDF

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

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms.

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 preprint arXiv:1904.00976 (2019-04-01)]

2019-10

Singular value automata and approximate minimization
Mathematical Structures in Computer Science
(2019-10-01)
ui.adsabs.harvard.eduPDF

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

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }