Akhilan Boopathy

Most-cited papers

1. CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks

   Akhilan Boopathy, T. Weng, Pin-Yu Chen, Si-Jia Liu +1 more

   2018AAAI Conference on Artificial Intelligence146 citations Open access

   Semantic Scholar

   Save

2. PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach

   Lily Weng, Pin-Yu Chen, Lam M. Nguyen, M. Squillante +3 more

   2019International Conference on Machine Learning92 citations

   Semantic Scholar

   Save

3. Proper Network Interpretability Helps Adversarial Robustness in Classification

   Akhilan Boopathy, Si-Jia Liu, Gaoyuan Zhang, Cynthia Liu +3 more

   2020International Conference on Machine Learning76 citations

   Semantic Scholar

   Save

4. Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle

   Rylan Schaeffer, Mikail Khona, Zachary Robertson, Akhilan Boopathy +4 more

   2023arXiv.org57 citations Open access

   Semantic Scholar

   Save

5. How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective

   Akhilan Boopathy, I. Fiete

   2021International Conference on Machine Learning16 citations

   Semantic Scholar

   Save

6. Breaking Neural Network Scaling Laws with Modularity

   Akhilan Boopathy, Sunshine Jiang, William Yue, Jaedong Hwang +2 more

   2024International Conference on Learning Representations10 citations

   Semantic Scholar

   Save

7. Fast Training of Provably Robust Neural Networks by SingleProp

   Akhilan Boopathy, T. Weng, Si-Jia Liu, Pin-Yu Chen +2 more

   2021AAAI Conference on Artificial Intelligence9 citations Open access

   Semantic Scholar

   Save

8. Model-agnostic Measure of Generalization Difficulty

   Akhilan Boopathy, Kevin Liu, Jaedong Hwang, Shu Ge +2 more

   2023International Conference on Machine Learning8 citations Open access

   Semantic Scholar

   Save

9. Towards Exact Computation of Inductive Bias

   Akhilan Boopathy, William Yue, Jaedong Hwang, Abhiram Iyer +1 more

   2024International Joint Conference on Artificial Intelligence6 citations

   Semantic Scholar

   Save

10. Unified Neural Network Scaling Laws and Scale-time Equivalence

    Akhilan Boopathy, I. Fiete

    2024arXiv.org5 citations

    Semantic Scholar

    Save

11. Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity

    Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy +2 more

    2023arXiv.org5 citations

    Semantic Scholar

    Save

12. Resampling-free Particle Filters in High-dimensions

    Akhilan Boopathy, Aneesh Muppidi, Peggy Yang, Abhiram Iyer +2 more

    2024IEEE International Conference on Robotics and Automation3 citations Open access

    Semantic Scholar

    Save

13. Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building

    Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy +2 more

    2023Trans. Mach. Learn. Res.3 citations

    Semantic Scholar

    Save

14. Divergence at the Interpolation Threshold: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle

    Rylan Schaeffer, Zachary Robertson, Akhilan Boopathy, Mikail Khona +3 more

    3 citations

    Semantic Scholar

    Save

15. Rapid Learning without Catastrophic Forgetting in the Morris Water Maze

    Raymond Wang, Jaedong Hwang, Akhilan Boopathy, I. Fiete

    2024International Conference on Machine Learning2 citations

    Semantic Scholar

    Save

16. Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations

    Akhilan Boopathy, I. Fiete

    2021arXiv.org2 citations

    Semantic Scholar

    Save

17. Visual Interpretability Alone Helps Adversarial Robustness

    Akhilan Boopathy, Si-Jia Liu, Gaoyuan Zhang, Pin-Yu Chen +2 more

    20192 citations

    Semantic Scholar

    Save

18. Permutation Invariant Learning with High-Dimensional Particle Filters

    Akhilan Boopathy, Aneesh Muppidi, Peggy Yang, Abhiram Iyer +2 more

    2024arXiv.org1 citations

    Semantic Scholar

    Save

19. Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning in Image Classification

    Jaedong Hwang, Brian Cheung, Zhang-Wei Hong, Akhilan Boopathy +2 more

    20240 citations

    Semantic Scholar

    Save

20. Rapid Learning Without Catastrophic Forgetting in Multiple Morris Water Mazes

    Raymond Wang, Jaedong Hwang, Akhilan Boopathy, I. Fiete

    20232023 Conference on Cognitive Computational Neuroscience0 citations Open access

    Semantic Scholar

    Save

21. Neuro-Inspired Efficient Map Building via Fragmentation and Recall

    Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy +2 more

    2023arXiv.org0 citations Open access

    Semantic Scholar

    Save