Eric Gan

Publication Activity (10 Years)

Years Active: 2023-2024
Publications (10 Years): 10

Top Topics

Computational Neuroscience

Training Samples

Selecting Features

Top Venues

Publications

Dang Nguyen, Paymon Haddad, Eric Gan, Baharan Mirzasoleiman
Make the Most of Your Data: Changing the Training Data Distribution to Improve In-distribution Generalization Performance. CoRR (2024)
Yihao Xue, Eric Gan, Jiayi Ni, Siddharth Joshi, Baharan Mirzasoleiman
Investigating the Benefits of Projection Head for Representation Learning. ICLR (2024)
Yihao Xue, Eric Gan, Jiayi Ni, Siddharth Joshi, Baharan Mirzasoleiman
Investigating the Benefits of Projection Head for Representation Learning. CoRR (2024)
Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias. AISTATS (2024)
Ziming Liu, Eric Gan, Max Tegmark
Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability. Entropy 26 (1) (2024)
Ziming Liu, Eric Gan, Max Tegmark
Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability. CoRR (2023)
Lauren Watson, Eric Gan, Mohan Dantam, Baharan Mirzasoleiman, Rik Sarkar
Inference and Interference: The Role of Clipping, Pruning and Loss Landscapes in Differentially Private Stochastic Gradient Descent. CoRR (2023)
Yihao Xue, Siddharth Joshi, Eric Gan, Pin-Yu Chen, Baharan Mirzasoleiman
Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression. CoRR (2023)
Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias. CoRR (2023)
Yihao Xue, Siddharth Joshi, Eric Gan, Pin-Yu Chen, Baharan Mirzasoleiman
Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression. ICML (2023)