Possible advisorsa guess from early papers, not confirmed

• Mehul Motani

  Possible advisor · last author on 5 of their early first-author papers, 2022–2026

  Suggested from co-authorship

Is this you? Claim this profile to confirm or dismiss it.

• Understanding Deep Neural Networks Using Sliced Mutual Information

  Shelvia Wongso, Rohan Ghosh, Mehul Motani

  IEEE International Symposium on Information Theory (ISIT) · 2022

  8
• Pointwise Sliced Mutual Information for Neural Network Explainability

  Shelvia Wongso, Rohan Ghosh, Mehul Motani

  IEEE International Symposium on Information Theory (ISIT) · 2023

  4
• Evolutionary Symbolic Regression: Mechanisms from the Perspectives of Morphology and Adaptability

  Kei Sen Fong, Shelvia Wongso, Mehul Motani

  Proceedings of the Companion Conference on Genetic and Evolutionary Computation · 2023

  This work creates a depth-aware mathematical language model trained on terminal walks of expression trees, as a replacement to man-made heuristics in SR algorithms, and introduces mechanisms from two perspectives: morphology and adaptability.

  3
• Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference

  Jasraj Singh, Shelvia Wongso, Jérémie Houssineau, Badr-Eddine Chérief-Abdellatif

  HAL (Le Centre pour la Communication Scientifique Directe) · 2025

  This work develops a principled formulation for performing possibilistic VI by establishing a maxitive analogue of the classical Donsker-Varadhan formulation, enabling it to derive a learning rule for possibilistic VI with exponential-family candidates and practical update rules for neural-network training, giving rise to a family of optimizers termed CBOpt.

  2
• Bridging Adversarial and Information-Theoretic Fairness via Robustness

  Shelvia Wongso, Rohan Ghosh, Mehul Motani

  Zenodo (CERN European Organization for Nuclear Research) · 2026

  –
• Sliced Information Plane for Analysis of Deep Neural Networks

  Shelvia Wongso, Rohan Ghosh, Mehul Motani

  2025

  –