I am a CS Ph.D. student in The Center For Language and Speech Processing at the Johns Hopkins University. Currently, I am interested in solving problems posted on StackOverflow among other structured-predictiony things. I graduated from IIT Delhi in August 2011 with dual degrees in EE and IT. After graduation, I worked for a year at Goldman Sachs as a Core Ops Strat and then joined Aspiring Minds as an RnD engineer.

At CLSP, my advisor is Benjamin Van Durme and I have worked with Raman Arora, Jason Eisner and James Spall.

# Selected Publications

- Weighting Finite-State Transductions With Neural Context, Pushpendre Rastogi, Ryan Cotterell, Jason Eisner. NAACL(2016) [bib] [pdf] [slides] [code]
- Efficient Implementation of Enhanced Adaptive Simultaneous Perturbation Algorithms, Pushpendre Rastogi, Jingyi Jhu, James Spall. CISS(2016) [bib] [code] [pdf]
- Multiview LSA: Representation Learning Via Generalized CCA, Pushpendre Rastogi, Benjamin Van Durme and Raman Arora, NAACL(2015) [pdf], [data+code], [bib], [poster], [supplementary]
- Augmenting FrameNet Via PPDB, Pushpendre Rastogi and Benjamin Van Durme, Events Workshop at ACL(2014), [pdf], [data], [poster] [bib]
- Stationarity Condition for Fractional Sampling Filters. Pushpendre Rastogi (Master's theses)[pdf]
- More at Google Scholar.

# Posts

- Searchable PDF version of the Penn Treebank Bracketing Guideline
- Matrix Decompositions
- Beginners analysis for optimization in Data Science.
- The impossibility of specifying the number of samples needed in a validation set using t-distributions for regression with unbounded loss
- Edge Prediction in Semantic Graphs
- Induction and Recursion
- Understanding Logistic Regression II
- Convex Neural Networks?
- Online Sample Complexity Bound Calculator
- Understanding_logistic_regression
- Class Diagram Portion From Uml
- Multiview LSA Motivation and Proofs
- Mathematical Notation Glossary
- Eigenvalue Problems