Publications
-
ICLR 2026
Implicit Regularization of SGD Reduces Shortcut Learning
Nahal Mirzaie, Alireza Alipanah, Ali Abbasi, Amirmahdi Farzane, Hossein Jafarinia, Erfan Sobhaei, Mahdi Ghaznavi, Amir Najafi, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Shows how the implicit regularization of SGD, controlled by learning rate and batch size, suppresses reliance on spurious features while preserving accuracy.
International Conference on Learning Representations (ICLR), 2026
-
TMLR 2026
Bridging Reasoning to Learning: Unmasking Illusions Using Complexity Out-of-Distribution Generalization
Mahdi Samiei, Arash Marioriyad, Arman Tahmasebi-Zadeh, Mohamadreza Fereydooni, Mahdi Ghaznavi, Mahdieh Soleymani Baghshah
Frames reasoning as generalization to problems whose solutions require greater representational or computational complexity than the training examples.
Transactions on Machine Learning Research (TMLR), 2026
-
ICML HiLD 2025
The Silent Helper: How Implicit Regularization Enhances Group Robustness
Nahal Mirzaie, Mahdi Ghaznavi, Hamed Oyarhoseini, Alireza Alipanah, Erfan Sobhaei, Ali Abbasi, Mahdieh Soleymani Baghshah
Studies how the implicit bias of optimization can improve worst-group performance even when group annotations are unavailable.
ICML Workshop on High-dimensional Learning Dynamics (HiLD), 2025
-
ICLR SCSL 2025
Exploiting What Trained Models Learn for Making Them Robust to Spurious Correlations without Group Annotations
Mahdi Ghaznavi, Hadi Asadollahzadeh, Fahimeh Hosseini Noohdani, Soroush Vafaie Tabar, Hosein Hasani, Mahdieh Soleymani Baghshah
Uses information already encoded by trained models to reduce shortcut reliance without requiring group labels during training.
ICLR Workshop on Spurious Correlation and Shortcut Learning (SCSL), 2025