Center for Foundations of Data Science Poster Session
The Data Science Institute at Columbia University's Center for Foundations of Data Science conducts core data science research to support and amplify fields central to New York’s technology economy. The Center hosted a poster presentation on Wednesday, February 5 during which Columbia professors and students showcased current research projects using data techniques, including machine learning, information extraction, and natural language processing.
A First-Order Approach to Accelerated Value Iteration
- Capturing Choice Overload via Generalized Markov Chain Model
- Efficiently avoiding saddle points with zero order methods: No gradients required
- Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training
- Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games
Unsupervised Sparse-view Backprojection via Convolutional and Spatial Transformer Networks
Pictured: Graduate student Giannis Karamanolakis (left) and Professor Daniel Hsu (right).