2 citations · 4 across the 11 of their papers we have counts for
12 papers
A Deep Learning Earth System Model Simulation of Indian Monsoon Intraseasonal and Interannual Variability
Bijit Kumar Banerjee, Devabrat Sharma, R. I. Sujith +6
With the data-driven artificial intelligence/machine learning (AI/ML) models having demonstrated their ability to extend the prediction horizon of large-scale weather at a fraction…
Transformers with Sparse Attention for Granger Causality
Riya Mahesh, Rahul Vashisht, Chandrashekar Lakshminarayanan
Temporal causal analysis means understanding the underlying causes behind observed variables over time. Deep learning based methods such as transformers are increasingly used to ca…
Half-Space Feature Learning in Neural Networks
Mahesh Lorik Yadav, Harish Guruprasad Ramaswamy, Chandrashekar Lakshminarayanan
There currently exist two extreme viewpoints for neural network feature learning -- (i) Neural networks simply implement a kernel method (a la NTK) and hence no features are learne…
Approximate Linear Programming for Decentralized Policy Iteration in Cooperative Multi-agent Markov Decision Processes
Lakshmi Mandal, Chandrashekar Lakshminarayanan, Shalabh Bhatnagar
In this work, we consider a cooperative multi-agent Markov decision process (MDP) involving m agents. At each decision epoch, all the m agents independently select actions in order…
Explicitising The Implicit Intrepretability of Deep Neural Networks Via Duality
Chandrashekar Lakshminarayanan, Amit Vikram Singh, Arun Rajkumar
Recent work by Lakshminarayanan and Singh [2020] provided a dual view for fully connected deep neural networks (DNNs) with rectified linear units (ReLU). It was shown that (i) the…
Disentangling deep neural networks with rectified linear units using duality
Chandrashekar Lakshminarayanan, Amit Vikram Singh
Despite their success deep neural networks (DNNs) are still largely considered as black boxes. The main issue is that the linear and non-linear operations are entangled in every la…
Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning
Chandrashekar Lakshminarayanan, Amit Vikram Singh
Rectified linear unit (ReLU) activations can also be thought of as 'gates', which, either pass or stop their pre-activation input when they are 'on' (when the pre-activation input…
Deep Gated Networks: A framework to understand training and generalisation in deep learning
Chandrashekar Lakshminarayanan, Amit Vikram Singh
Understanding the role of (stochastic) gradient descent (SGD) in the training and generalisation of deep neural networks (DNNs) with ReLU activation has been the object study in th…
Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging
Chandrashekar Lakshminarayanan, Csaba Szepesvári
We consider -dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely…
A Linearly Relaxed Approximate Linear Program for Markov Decision Processes
Chandrashekar Lakshminarayanan, Shalabh Bhatnagar, Csaba Szepesvari
Approximate linear programming (ALP) and its variants have been widely applied to Markov Decision Processes (MDPs) with a large number of states. A serious limitation of ALP is tha…
A Generalized Reduced Linear Program for Markov Decision Processes
Chandrashekar Lakshminarayanan, Shalabh Bhatnagar
Markov decision processes (MDPs) with large number of states are of high practical interest. However, conventional algorithms to solve MDP are computationally infeasible in this sc…
Approximate Dynamic Programming based on Projection onto the (min,+) subsemimodule
Chandrashekar Lakshminarayanan, Shalabh Bhatnagar
We develop a new Approximate Dynamic Programming (ADP) method for infinite horizon discounted reward Markov Decision Processes (MDP) based on projection onto a subsemimodule. We ap…