Publications

2026

1. Imperfect Influence, Preserved Rankings: A Theory of TRAK for Data Attribution

   Han Tong, Shubhangi Ghosh, Haolin Zou, and 1 more author

   Submitted to ICML, 2026

2025

1. Signal-to-noise ratio aware minimax analysis of sparse linear regression

   Shubhangi Ghosh, Yilin Guo, Haolei Weng, and 1 more author

   Under review at IEEE Transactions on Information Theory, 2025

2024

1. A note on the minimax risk of sparse linear regression

   Yilin Guo, Shubhangi Ghosh, Haolei Weng, and 1 more author

   Major revisions, Electronic Journal of Statistics, 2024

2023

1. Independent Mechanism Analysis and the Manifold Hypothesis

   Shubhangi Ghosh, Luigi Gresele, Julius Kügelgen, and 2 more authors

   NeurIPS Workshop on Causal Representation Learning, 2023

2022

1. Probing the Robustness of Independent Mechanism Analysis for Representation Learning

   Joanna Sliwa, Shubhangi Ghosh, Vincent Stimper, and 2 more authors

   UAI Workshop on Causal Representation Learning, 2022
2. On Pitfalls of Identifiability in Unsupervised Learning. A Note on:" Desiderata for Representation Learning: A Causal Perspective"

   Shubhangi Ghosh, Luigi Gresele, Julius Kügelgen, and 2 more authors

   arXiv preprint arXiv:2202.06844, 2022

2018

1. A meta-cognitive recurrent fuzzy inference system with memory neurons (mcrfis-mn) and its fast learning algorithm for time series forecasting

   Subhrajit Samanta, Shubhangi Ghosh, and Suresh Sundaram

   In 2018 IEEE Symposium Series on Computational Intelligence (SSCI), 2018