2026
Graph State Networks — Persistent Nodewise Selective State Space Models
Arijit Dey. Transactions on Machine Learning Research (TMLR), 2026.
Persistent, nodewise selective state-space models for scalable graph representation learning.
Keywords: graph neural networks, state-space models, selective state, scalable graph learning.
Under review
Convergence of Asynchronous Stochastic Gradient Descent for Polyak–Łojasiewicz Functions
Arijit Dey, Bahman Gharesifard. Submitted to IEEE Transactions on Automatic Control.
Keywords: asynchronous optimization, stochastic gradient descent, Polyak–Łojasiewicz condition, convergence analysis.
A BibTeX entry and a short plain-language summary can be added per paper on request.