Vaishaal Shankar

Vaishaal Shankar


I broadly work on the foundations of machine learning -- specifically the study and analysis of empirical phenomena.
In particular I have studied the robustness of neural networks under various distribution shifts, and the connections between neural networks and classical kernel machines.

I currently work in a special projects team at Amazon.
Previously I spent 9 wonderful years at UC Berkeley, where I had the pleasure of working under Ben Recht

You can contact me at vs at vaishaal dot com


Taori, R., Dave, A., Shankar, V., Carlini, N., Recht, B., Schmidt, L. (2020). Measuring Robustness to Natural Distribution Shifts in Image Classification. arXiv preprint arXiv:2007.06444 pdf

Shankar, V.*, Dave, A.*, Roelofs, R., Ramanan, D., Recht, B., & Schmidt, L. (2019). Do Image Classifiers Generalize Across Time? arXiv preprint arXiv:1906.02168. pdf


Shankar, V., Krauth, K., Vodrahalli, K., Pu, Q., Jonas, E., Venkataraman, S., Stoica, I., Recht, B., & Ragan-Kelley, J. (2020). numpywren: serverless linear algebra. To Appear In Proceedings of ACM Symposium on Cloud Computing pdf

Shankar, V., Fang, A., Guo, W., Fridovich-Keil, S., Schmidt, L., Ragan-Kelley, J., & Recht, B. (2020). Neural Kernels Without Tangents. In Proceedings of International Conference on Machine Learning (ICML) pdf

Shankar, V*., Roelofs, B*, Mania, H., Fang, A., Recht, B., Schmidt, L. (2020). Evaluating Machine Accuracy on ImageNet. In Proceedings of International Conference on Machine Learning (ICML) 2020. pdf

Roelofs, R.,Fridovich-Keil, S. Miller, J., Shankar, V., Hardt, M., Recht, B., & Schmidt, L. (2019). A Meta-Analysis of Overfitting in Machine Learning. In Advances in Neural Information Processing Systems (pp. 9175-9185).

Recht, B., Roelofs, R., Schmidt, L. & Shankar, V.. (2019). Do ImageNet Classifiers Generalize to ImageNet?. Proceedings of the 36th International Conference on Machine Learning pdf

Jonas, E., Bobra, M., Shankar, V., Hoeksema, J. T., & Recht, B. (2018). Flare prediction using photospheric and coronal image data. Solar Physics, 293(3), 48.

Morrow, A., Shankar, V, Petersohn, D., Yosef, N., Recht, B., Joseph, A.D (2016, December). Convolutional Kitchen Sinks for Transcription Factor Binding Site Prediction. NIPS Workshop on Machine Learning in Computational Biology pdf talk

Shankar, V., Zhang, J., Chen, J., Dinh, C., Clements, M., & Zakhor, A. (2016, February). Approximate Subgraph Isomorphism for Image Localization. International Symposium on Electronic Imaging

Shankar, V., & Culler, D. (2015, March). A Modern Student Experience in Systems Programming. In Proceedings of the Second (2015) ACM Conference on Learning@ Scale (pp. 233-236). ACM.

Kantchelian, A., Tschantz, M. C., Afroz, S., Miller, B., Shankar, V., Bachwani, V., Bachwani, R., Joseph, A.D. & Tygar, J. D. (2015, October). Better malware ground truth: Techniques for weighting anti-virus vendor labels. In Proceedings of the Eigth ACM Workshop on Artificial Intelligence and Security (pp. 45-56). ACM.

Miller, B., Kantchelian, A., Tschantz, M.C., Afroz, S., Bahwani, R., Faizullabhoy, R., Huang, L., Shankar, V., Wu, T., Yiu, G., Joseph, A.D. & Tygar, J. D (2016 July). Reviewer Integration and Performance Measurement for Malware Detection. 13th Conference on Detection of Intrusions and Malware & Vulnerability Assessment

Tech Reports

Iliopoulos, F., Moulous, V., Shankar, V., & Simchowitz, M. Gradients for the Loss!.

Other Useful Stuff

Git for advanced beginners - Git slide deck I made a couple years ago

Tutorials - A list of tutorials on various mathy things curated by my good friend Achal Dave

Is Thirteen? - I have nothing to do with this but very useful tool.