Timezone: »
We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to satisfy non-linear rate constraints such as predictive parity fairness, distribution divergences or churn ratios. We extend previous two-player game approaches for constrained optimization to an approach with three players to decouple the classifier rates from the non-linear objective, and seek to find an equilibrium of the game. Our approach generalizes many existing algorithms, and makes possible new algorithms with more flexibility and tighter handling of non-linear rate constraints. We provide convergence guarantees for convex functions of rates, and show how our methodology can be extended to handle sums-of-ratios of rates. Experiments on different fairness tasks confirm the efficacy of our approach.
Author Information
Harikrishna Narasimhan (Google Research)
Andrew Cotter (Google)
Maya Gupta (Google)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Poster: Optimizing Generalized Rate Metrics with Three Players »
Thu. Dec 12th 06:45 -- 08:45 PM Room East Exhibition Hall B + C #51
More from the Same Authors
-
2022 Poster: Post-hoc estimators for learning to defer to an expert »
Harikrishna Narasimhan · Wittawat Jitkrittum · Aditya Menon · Ankit Rawat · Sanjiv Kumar -
2021 Poster: Training Over-parameterized Models with Non-decomposable Objectives »
Harikrishna Narasimhan · Aditya Menon -
2020 Poster: Approximate Heavily-Constrained Learning with Lagrange Multiplier Models »
Harikrishna Narasimhan · Andrew Cotter · Yichen Zhou · Serena Wang · Wenshuo Guo -
2020 Poster: Fair Performance Metric Elicitation »
Gaurush Hiranandani · Harikrishna Narasimhan · Sanmi Koyejo -
2020 Poster: Consistent Plug-in Classifiers for Complex Objectives and Constraints »
Shiv Kumar Tavker · Harish Guruprasad Ramaswamy · Harikrishna Narasimhan -
2020 Poster: Robust Optimization for Fairness with Noisy Protected Groups »
Serena Wang · Wenshuo Guo · Harikrishna Narasimhan · Andrew Cotter · Maya Gupta · Michael Jordan -
2019 Poster: On Making Stochastic Classifiers Deterministic »
Andrew Cotter · Maya Gupta · Harikrishna Narasimhan -
2019 Oral: On Making Stochastic Classifiers Deterministic »
Andrew Cotter · Maya Gupta · Harikrishna Narasimhan -
2018 Poster: Diminishing Returns Shape Constraints for Interpretability and Regularization »
Maya Gupta · Dara Bahri · Andrew Cotter · Kevin Canini -
2018 Poster: To Trust Or Not To Trust A Classifier »
Heinrich Jiang · Been Kim · Melody Guan · Maya Gupta -
2017 Poster: Deep Lattice Networks and Partial Monotonic Functions »
Seungil You · David Ding · Kevin Canini · Jan Pfeifer · Maya Gupta -
2016 Poster: Launch and Iterate: Reducing Prediction Churn »
Mahdi Milani Fard · Quentin Cormier · Kevin Canini · Maya Gupta -
2016 Poster: Fast and Flexible Monotonic Functions with Ensembles of Lattices »
Mahdi Milani Fard · Kevin Canini · Andrew Cotter · Jan Pfeifer · Maya Gupta -
2016 Poster: Satisfying Real-world Goals with Dataset Constraints »
Gabriel Goh · Andrew Cotter · Maya Gupta · Michael P Friedlander