42 citations · 151 across the 16 of their papers we have counts for
17 papers
Implicit Rate-Constrained Optimization of Non-decomposable Objectives
Abhishek Kumar, Harikrishna Narasimhan, Andrew Cotter
We consider a popular family of constrained optimization problems arising in machine learning that involve optimizing a non-decomposable evaluation metric with a certain thresholde…
Training Over-parameterized Models with Non-decomposable Objectives
Harikrishna Narasimhan, Aditya Krishna Menon
Many modern machine learning applications come with complex and nuanced design goals such as minimizing the worst-case error, satisfying a given precision or recall target, or enfo…
Churn Reduction via Distillation
Heinrich Jiang, Harikrishna Narasimhan, Dara Bahri +2
In real-world systems, models are frequently updated as more data becomes available, and in addition to achieving high accuracy, the goal is to also maintain a low difference in pr…
Distilling Double Descent
Andrew Cotter, Aditya Krishna Menon, Harikrishna Narasimhan +3
Distillation is the technique of training a "student" model based on examples that are labeled by a separate "teacher" model, which itself is trained on a labeled dataset. The most…
Optimizing Black-box Metrics with Iterative Example Weighting
Gaurush Hiranandani, Jatin Mathur, Harikrishna Narasimhan +2
We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix. Such black-box learning settings are ubiquitous, for example, when…
Quadratic Metric Elicitation for Fairness and Beyond
Gaurush Hiranandani, Jatin Mathur, Harikrishna Narasimhan +1
Metric elicitation is a recent framework for eliciting classification performance metrics that best reflect implicit user preferences based on the task and context. However, availa…
Fair Performance Metric Elicitation
Gaurush Hiranandani, Harikrishna Narasimhan, Oluwasanmi Koyejo
What is a fair performance metric? We consider the choice of fairness metrics through the lens of metric elicitation -- a principled framework for selecting performance metrics tha…
Optimizing Black-box Metrics with Adaptive Surrogates
Qijia Jiang, Olaoluwa Adigun, Harikrishna Narasimhan +2
We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surroga…
Robust Optimization for Fairness with Noisy Protected Groups
Serena Wang, Wenshuo Guo, Harikrishna Narasimhan +3
Many existing fairness criteria for machine learning involve equalizing some metric across protected groups such as race or gender. However, practitioners trying to audit or enforc…
Optimizing Generalized Rate Metrics through Game Equilibrium
Harikrishna Narasimhan, Andrew Cotter, Maya Gupta
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…
Pairwise Fairness for Ranking and Regression
Harikrishna Narasimhan, Andrew Cotter, Maya Gupta +1
We present pairwise fairness metrics for ranking models and regression models that form analogues of statistical fairness notions such as equal opportunity, equal accuracy, and sta…
Online Optimization Methods for the Quantification Problem
Purushottam Kar, Shuai Li, Harikrishna Narasimhan +2
The estimation of class prevalence, i.e., the fraction of a population that belongs to a certain class, is a very useful tool in data analytics and learning, and finds applications…
Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve
Harikrishna Narasimhan, Shivani Agarwal
The area under the ROC curve (AUC) is a widely used performance measure in machine learning. Increasingly, however, in several applications, ranging from ranking to biometric scree…
Surrogate Functions for Maximizing Precision at the Top
Purushottam Kar, Harikrishna Narasimhan, Prateek Jain
The problem of maximizing precision at the top of a ranked list, often dubbed Precision@k (prec@k), finds relevance in myriad learning applications such as ranking, multi-label cla…
Optimizing Non-decomposable Performance Measures: A Tale of Two Classes
Harikrishna Narasimhan, Purushottam Kar, Prateek Jain
Modern classification problems frequently present mild to severe label imbalance as well as specific requirements on classification characteristics, and require optimizing performa…
Consistent Classification Algorithms for Multi-class Non-Decomposable Performance Metrics
Harish G. Ramaswamy, Harikrishna Narasimhan, Shivani Agarwal
We study consistency of learning algorithms for a multi-class performance metric that is a non-decomposable function of the confusion matrix of a classifier and cannot be expressed…
Online and Stochastic Gradient Methods for Non-decomposable Loss Functions
Purushottam Kar, Harikrishna Narasimhan, Prateek Jain
Modern applications in sensitive domains such as biometrics and medicine frequently require the use of non-decomposable loss functions such as precision@k, F-measure etc. Compared…