activity
20172026
most citedTransformers with Sparse Attention for Granger Causality

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2024★ 1 cited

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…

cs.LG2024

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…

cs.LG2023

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…

cs.LG2022

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…

cs.LG2021

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…

cs.LG2020

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…