Harikrishna Narasimhan | DeepAI

AI Chat

Featured Co-authors

Michael I. Jordan
283 publications
Shuai Li
104 publications
Prateek Jain
87 publications
Sanjiv Kumar
74 publications
Praneeth Netrapalli
55 publications
Oluwasanmi Koyejo
52 publications
David C. Parkes
47 publications
Abhishek Kumar
41 publications
Aditya Krishna Menon
35 publications
Purushottam Kar
32 publications
Ankit Singh Rawat
31 publications

∙ 07/06/2023

When Does Confidence-Based Cascade Deferral Suffice?

Cascades are a classical strategy to enable inference cost to vary adapt...

0 Wittawat Jitkrittum, et al. ∙

∙ 01/29/2023

Learning to reject meets OOD detection: Are all abstentions created equal?

Learning to reject (L2R) and out-of-distribution (OOD) detection are two...

3 Harikrishna Narasimhan, et al. ∙

∙ 10/18/2022

Consistent Multiclass Algorithms for Complex Metrics and Constraints

We present consistent algorithms for multiclass learning with complex pe...

0 Harikrishna Narasimhan, et al. ∙

∙ 06/13/2022

Robust Distillation for Worst-class Performance

Knowledge distillation has proven to be an effective technique in improv...

12 Serena Wang, et al. ∙

∙ 07/23/2021

Implicit Rate-Constrained Optimization of Non-decomposable Objectives

We consider a popular family of constrained optimization problems arisin...

0 Abhishek Kumar, et al. ∙

∙ 07/09/2021

Training Over-parameterized Models with Non-decomposable Objectives

Many modern machine learning applications come with complex and nuanced ...

0 Harikrishna Narasimhan, et al. ∙

∙ 06/04/2021

Churn Reduction via Distillation

In real-world systems, models are frequently updated as more data become...

0 Heinrich Jiang, et al. ∙

∙ 02/18/2021

Optimizing Black-box Metrics with Iterative Example Weighting

We consider learning to optimize a classification metric defined by a bl...

0 Gaurush Hiranandani, et al. ∙

∙ 02/13/2021

Distilling Double Descent

Distillation is the technique of training a "student" model based on exa...

0 Andrew Cotter, et al. ∙

∙ 11/03/2020

Quadratic Metric Elicitation with Application to Fairness

Metric elicitation is a recent framework for eliciting performance metri...

0 Gaurush Hiranandani, et al. ∙

∙ 06/23/2020

Fair Performance Metric Elicitation

What is a fair performance metric? We consider the choice of fairness me...

0 Gaurush Hiranandani, et al. ∙

∙ 02/21/2020

Robust Optimization for Fairness with Noisy Protected Groups

Many existing fairness criteria for machine learning involve equalizing ...

6 Serena Wang, et al. ∙

∙ 02/20/2020

Optimizing Black-box Metrics with Adaptive Surrogates

We address the problem of training models with black-box and hard-to-opt...

0 Qijia Jiang, et al. ∙

∙ 09/06/2019

Optimizing Generalized Rate Metrics through Game Equilibrium

We present a general framework for solving a large class of learning pro...

0 Harikrishna Narasimhan, et al. ∙

∙ 06/12/2019

Pairwise Fairness for Ranking and Regression

We present pairwise metrics of fairness for ranking and regression model...

0 Harikrishna Narasimhan, et al. ∙

∙ 06/12/2017

Optimal Auctions through Deep Learning

Designing an auction that maximizes expected revenue is an intricate tas...

0 Paul Dütting, et al. ∙

∙ 05/13/2016

Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve

The area under the ROC curve (AUC) is a widely used performance measure ...

0 Harikrishna Narasimhan, et al. ∙

∙ 05/13/2016

Online Optimization Methods for the Quantification Problem

The estimation of class prevalence, i.e., the fraction of a population t...

0 Purushottam Kar, et al. ∙

∙ 05/26/2015

Surrogate Functions for Maximizing Precision at the Top

The problem of maximizing precision at the top of a ranked list, often d...

0 Purushottam Kar, et al. ∙

∙ 05/26/2015

Optimizing Non-decomposable Performance Measures: A Tale of Two Classes

Modern classification problems frequently present mild to severe label i...

0 Harikrishna Narasimhan, et al. ∙

∙ 01/01/2015

Consistent Classification Algorithms for Multi-class Non-Decomposable Performance Metrics

We study consistency of learning algorithms for a multi-class performanc...

0 Harish G. Ramaswamy, et al. ∙

∙ 10/24/2014

Online and Stochastic Gradient Methods for Non-decomposable Loss Functions

Modern applications in sensitive domains such as biometrics and medicine...

0 Purushottam Kar, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world