Publications
Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks.
Proceedings of 2020 SDM Conference.
(2020). HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision.
Proceedings of ICCV 2019.
(2019). Homogenization of material properties in additively manufactured structures.
US Patent 10353378.
(2019). Hessian-based Analysis of Large Batch Training and Robustness to Adversaries.
Proceedings of the 2018 NeurIPS Conference. 4954-4964.
(2018).
(2018). A High Performance Packet Core for Next Generation Cellular Networks..
Proceedings of the Conference of the ACM Special Interest Group on Data Communication SIGNCOMM '17.
(2017). Homogenization of material properties in additively manufactured structures.
Computer-Aided Design. 78, 71-82.
(2016). Host of Troubles: Multiple Host Ambiguities in HTTP Implementations.
Proceedings of ACM CCS.
(2016). How neural network depth compensates for HMM conditional independence assumptions in DNN-HMM acoustic models.
Proceedings of Interspeech 2016.
(2016).
(2015).
(2015).
Hacking Team and the Targeting of Ethiopian Journalists.
The Citizen Lab.
(2014). Hacking Team's US Nexus.
The Citizen Lab.
(2014). Here Be Web Proxies.
8362, 183-192.
(2014).
(2014). Historical Pedigree Reconstruction from Extant Populations Using PArtitioning of RElatives (PREPARE).
PLoS Computational Biology. 10(6),
(2014).
(2014).
(2014).
(2013).
(2013).
(2013).
(2013).
(2013).
(2013).
(2013).