Hi! I’m Vlad, and I’m CS PhD candidate at Cornell, advised by Claire Cardie. I work on machine learning & natural language processing, focusing on structure and sparsity. I am a scikit-learn “alum” and I develop the polylearn library for factorization machines and polynomial networks in Python.
SparseMAP: Differentiable sparse structured inference is accepted at ICML‘18! PyTorch implementation (dynet coming soon).
Released code for our NIPS‘17 paper on A regularized framework for sparse and structured neural attention.