Consistent Multiclass Algorithms for Complex Performance Measures

By Harikrishna Narasimhan, Harish Guruprasad Ramaswamy, Aadirupa Saha, Shivani Agarwal. 2015

68 citations recorded by the source corpus.

Subfields: Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical Learning Theory

1. Daniel Alabi
2. Harikrishna Narasimhan
3. Nicole Immorlica
4. Adam Tauman Kalai

Citations in the corpus

• On Structured Prediction Theory with Calibrated Convex Surrogate Losses (2017, neutral): “[32] provide a consistent algorithm for arbitrary multi-class loss defined by a function of the confusion matrix.”
• Learning with Complex Loss Functions and Constraints (2018, methodology): “Our approach builds on the framework of Narasimhan et al. (2015) for unconstrained problems with complex loss functions [27].”
• Unleashing Linear Optimizers for Group-Fair Learning and Optimization (2018, methodology): “Our work builds on a line of linear reductions in algorithms and fair machine learning (e.g., Jaggi, 2013; Kalai and Vempala, 2005; Narasimhan et al., 2015; Agarwal et al., 2017; Dwork et al., 2018).”
• Cross-Entropy Loss Functions: Theoretical Analysis and Applications (2023, unknown): “…2004b; Chen & Sun, 2006; Chen & Xiang, 2006; Tewari & Bartlett, 2007; Liu, 2007; Dogan et al., 2016; Wang & Scott, 2020; Ramaswamy & Agarwal, 2012; Narasimhan et al., 2015; Agarwal & Agarwal, 2015; Williamson et al., 2016; Ramaswamy & Agarwal, 2016; Finocchiaro et al., 2019; Frongillo & Waggoner,…”