12 citations · 15 across the 8 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
Logit Attenuating Weight Normalization
Aman Gupta, Rohan Ramanath, Jun Shi +4
Over-parameterized deep networks trained using gradient-based optimizers are a popular choice for solving classification and ranking problems. Without appropriately tuned …
cs.AI2021
Efficient Vertex-Oriented Polytopic Projection for Web-scale Applications
Rohan Ramanath, S. Sathiya Keerthi, Yao Pan +2
We consider applications involving a large set of instances of projecting points to polytopes. We develop an intuition guided by theoretical and empirical analysis to show that whe…