Portrait of Prakash Panangaden

Prakash Panangaden

Core Academic Member
Research Topics
Machine Learning Theory
Probabilistic Models
Quantum Information Theory
Reasoning
Reinforcement Learning

Biography

Prakash Panangaden studied physics at IIT Kanpur, India. He obtained an MS in physics at the University of Chicago studying stimulated emission from blacks holes. He obtained a PhD in physics from the University of Wisconsin-Milwaukee working on quantum field theory in curved spacetime. He was an assistant professor of computer science at Cornell University where he primarily worked on semantics of concurrent programming languages.

Since 1990 he was a professor at McGill University's School of Computer Science and for the last 25 years he has been working on many aspects of Markov processes: process equivalence, logical characterization, approximation and metrics. Recently he has worked on using metrics to enhance representation learning. He has also published papers in physics, quantum information and pure mathematics. Prakash is a Core Academic Member at Mila - Quebec Institute of Artificial Intelligence. He is a Fellow of the Royal Society of Canada and a Fellow of the Association for Computing Machinery (ACM).

Current Students

Master's Research - McGill University
Co-supervisor :

Publications

Augmenting Human Selves Through Artificial Agents – Lessons From the Brain
Georg Northoff
Maia Fraser
John Griffiths
Dimitris A. Pinotsis
Rosalyn Moran
Karl Friston
Much of current artificial intelligence (AI) and the drive toward artificial general intelligence (AGI) focuses on developing machines for f… (see more)unctional tasks that humans accomplish. These may be narrowly specified tasks as in AI, or more general tasks as in AGI – but typically these tasks do not target higher-level human cognitive abilities, such as consciousness or morality; these are left to the realm of so-called “strong AI” or “artificial consciousness.” In this paper, we focus on how a machine can augment humans rather than do what they do, and we extend this beyond AGI-style tasks to augmenting peculiarly personal human capacities, such as wellbeing and morality. We base this proposal on associating such capacities with the “self,” which we define as the “environment-agent nexus”; namely, a fine-tuned interaction of brain with environment in all its relevant variables. We consider richly adaptive architectures that have the potential to implement this interaction by taking lessons from the brain. In particular, we suggest conjoining the free energy principle (FEP) with the dynamic temporo-spatial (TSD) view of neuro-mental processes. Our proposed integration of FEP and TSD – in the implementation of artificial agents – offers a novel, expressive, and explainable way for artificial agents to adapt to different environmental contexts. The targeted applications are broad: from adaptive intelligence augmenting agents (IA’s) that assist psychiatric self-regulation to environmental disaster prediction and personal assistants. This reflects the central role of the mind and moral decision-making in most of what we do as humans.
Towards an AAK Theory Approach to Approximate Minimization in the Multi-Letter Case
We study the approximate minimization problem of weighted finite automata (WFAs): given a WFA, we want to compute its optimal approximation … (see more)when restricted to a given size. We reformulate the problem as a rank-minimization task in the spectral norm, and propose a framework to apply Adamyan-Arov-Krein (AAK) theory to the approximation problem. This approach has already been successfully applied to the case of WFAs and language modelling black boxes over one-letter alphabets \citep{AAK-WFA,AAK-RNN}. Extending the result to multi-letter alphabets requires solving the following two steps. First, we need to reformulate the approximation problem in terms of noncommutative Hankel operators and noncommutative functions, in order to apply results from multivariable operator theory. Secondly, to obtain the optimal approximation we need a version of noncommutative AAK theory that is constructive. In this paper, we successfully tackle the first step, while the second challenge remains open.
Bisimulation metrics and norms for real-weighted automata
Borja Balle
Pascale Gourdeau
Continuous MDP Homomorphisms and Homomorphic Policy Gradient
Riemannian Diffusion Models
Chin-Wei Huang
Milad Aghajohari
Diffusion models are recent state-of-the-art methods for image generation and likelihood estimation. In this work, we generalize continuous-… (see more)time diffusion models to arbitrary Riemannian manifolds and derive a variational framework for likelihood estimation. Computationally, we propose new methods for computing the Riemannian divergence which is needed for likelihood estimation. Moreover, in generalizing the Euclidean case, we prove that maximizing this variational lower-bound is equivalent to Riemannian score matching. Empirically, we demonstrate the expressive power of Riemannian diffusion models on a wide spectrum of smooth manifolds, such as spheres, tori, hyperboloids, and orthogonal groups. Our proposed method achieves new state-of-the-art likelihoods on all benchmarks.
Extracting Weighted Automata for Approximate Minimization in Language Modelling
Optimal Spectral-Norm Approximate Minimization of Weighted Finite Automata
We address the approximate minimization problem for weighted finite automata (WFAs) with weights in …
MICo: Improved representations via sampling-based state similarity for Markov decision processes
We present a new behavioural distance over the state space of a Markov decision process, and demonstrate the use of this distance as an effe… (see more)ctive means of shaping the learnt representations of deep reinforcement learning agents. While existing notions of state similarity are typically difficult to learn at scale due to high computational cost and lack of sample-based algorithms, our newly-proposed distance addresses both of these issues. In addition to providing detailed theoretical analyses, we provide empirical evidence that learning this distance alongside the value function yields structured and informative representations, including strong results on the Arcade Learning Environment benchmark.
MICo: Learning improved representations via sampling-based state similarity for Markov decision processes
We present a new behavioural distance over the state space of a Markov decision process, and demonstrate the use of this distance as an eff… (see more)ective means of shaping the learnt representations of deep reinforcement learning agents. While existing notions of state similarity are typically difficult to learn at scale due to high computational cost and lack of sample-based algorithms, our newly-proposed distance addresses both of these issues. In addition to providing detailed theoretical analysis
A Study of Policy Gradient on a Class of Exactly Solvable Models
Gavin McCracken
Colin Daniels
Rosie Zhao
Anna M. Brandenberger
Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the e… (see more)volution of the policy parameters, for a special class of exactly solvable POMDPs, as a continuous-state Markov chain, whose transition probabilities are determined by the gradient of the distribution of the policy's value. Our approach relies heavily on random walk theory, specifically on affine Weyl groups. We construct a class of novel partially observable environments with controllable exploration difficulty, in which the value distribution, and hence the policy parameter evolution, can be derived analytically. Using these environments, we analyze the probabilistic convergence of policy gradient to different local maxima of the value function. To our knowledge, this is the first approach developed to analytically compute the landscape of policy gradient in POMDPs for a class of such environments, leading to interesting insights into the difficulty of this problem.
Bisimulation metrics and norms for real-weighted automata
Borja Balle
Pascale Gourdeau
A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms
We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate it… (see more)s effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD(