4 papers
Training Guarantees of Neural Network Classification Two-Sample Tests by Kernel Analysis
Varun Khurana, Xiuyuan Cheng, Alexander Cloninger
We construct and analyze a neural network two-sample test to determine whether two datasets came from the same distribution (null hypothesis) or not (alternative hypothesis). We pe…
Behavior Optimized Image Generation
Varun Khurana, Yaman K Singla, Jayakumar Subramanian +4
The last few years have witnessed great success on image generation, which has crossed the acceptance thresholds of aesthetics, making it directly applicable to personal and commer…
Linearized Wasserstein dimensionality reduction with approximation guarantees
Alexander Cloninger, Keaton Hamm, Varun Khurana +1
We introduce LOT Wassmap, a computationally feasible algorithm to uncover low-dimensional structures in the Wasserstein space. The algorithm is motivated by the observation that ma…
Synthesizing Human Gaze Feedback for Improved NLP Performance
Varun Khurana, Yaman Kumar Singla, Nora Hollenstein +2
Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either explicit (e.g. ranking used in training languag…