Timezone: »
Poster
Multidimensional Shape Constraints
Maya Gupta · Erez Louidor · Oleksandr Mangylov · Nobu Morioka · Taman Narayan · Sen Zhao
Wed Jul 15 11:00 AM -- 11:45 AM & Wed Jul 15 10:00 PM -- 10:45 PM (PDT) @ None #None
We propose new multi-input shape constraints across four intuitive categories: complements, diminishers, dominance, and unimodality constraints. We show these shape constraints can be checked and even enforced when training machine-learned models for linear models, generalized additive models, and the nonlinear function class of multi-layer lattice models. Toy examples and real-world experiments illustrate how the different shape constraints can be used to increase interpretability and better regularize machine-learned models.
Author Information
Maya Gupta (Google)
Erez Louidor (Google)
Oleksandr Mangylov (Google Research)
Nobu Morioka (Google Research)
Taman Narayan (Google)
Sen Zhao (Google Research)
More from the Same Authors
-
2020 Poster: Optimizing Black-box Metrics with Adaptive Surrogates »
Qijia Jiang · Olaoluwa Adigun · Harikrishna Narasimhan · Mahdi Milani Fard · Maya Gupta -
2020 Poster: Deep k-NN for Noisy Labels »
Dara Bahri · Heinrich Jiang · Maya Gupta -
2019 Poster: Metric-Optimized Example Weights »
Sen Zhao · Mahdi Milani Fard · Harikrishna Narasimhan · Maya Gupta -
2019 Poster: Shape Constraints for Set Functions »
Andrew Cotter · Maya Gupta · Heinrich Jiang · Erez Louidor · James Muller · Taman Narayan · Serena Wang · Tao Zhu -
2019 Oral: Shape Constraints for Set Functions »
Andrew Cotter · Maya Gupta · Heinrich Jiang · Erez Louidor · James Muller · Taman Narayan · Serena Wang · Tao Zhu -
2019 Oral: Metric-Optimized Example Weights »
Sen Zhao · Mahdi Milani Fard · Harikrishna Narasimhan · Maya Gupta