no code implementations • 15 Feb 2022 • Taman Narayan, Heinrich Jiang, Sen Zhao, Sanjiv Kumar
Much effort has been devoted to making large and more accurate models, but relatively little has been put into understanding which examples are benefiting from the added complexity.
no code implementations • 9 Feb 2021 • Taman Narayan, Serena Wang, Kevin Canini, Maya Gupta
We show that minimizing an expected pinball loss over a continuous distribution of quantiles is a good regularizer even when only predicting a specific quantile.
1 code implementation • 11 Sep 2018 • Andrew Cotter, Heinrich Jiang, Serena Wang, Taman Narayan, Maya Gupta, Seungil You, Karthik Sridharan
This new formulation leads to an algorithm that produces a stochastic classifier by playing a two-player non-zero-sum game solving for what we call a semi-coarse correlated equilibrium, which in turn corresponds to an approximately optimal and feasible solution to the constrained optimization problem.
no code implementations • 31 May 2018 • Andrew Cotter, Maya Gupta, Heinrich Jiang, James Muller, Taman Narayan, Serena Wang, Tao Zhu
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label.