Search Results for author:
Found 19 papers, 4 papers with code
Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial Corruptions
In this paper, we initiate the study of robustness in rank aggregation under the popular Bradley-Terry-Luce (BTL) model for pairwise comparisons.
On the Effect of Image Resolution on Semantic Segmentation
We have rigorously tested our method using leading-edge semantic segmentation datasets.
Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures
Most work on learning from noisy labels has focused on standard loss-based performance measures.
MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries
This work introduces the task of multimodal medical question summarization for codemixed input in a low-resource setting.
Consistent Multiclass Algorithms for Complex Metrics and Constraints
We present consistent algorithms for multiclass learning with complex performance metrics and constraints, where the objective and constraints are defined by arbitrary functions of the confusion matrix.
Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class
When H is the class of linear models, the class F consists of certain piecewise linear scoring functions that are characterized by the same number of parameters as in the linear case, and minimization over which can be performed using an adaptation of the min-pooling idea from neural network training.
Choice Bandits
Here we study a natural generalization, that we term \emph{choice bandits}, where the learner plays a set of up to $k \geq 2$ arms and receives limited relative feedback in the form of a single multiway choice among the pulled arms, drawn from an underlying multiway choice model.
Convex Calibrated Surrogates for the Multi-Label F-Measure
In particular, the F-measure explicitly balances recall (fraction of active labels predicted to be active) and precision (fraction of labels predicted to be active that are actually so), both of which are important in evaluating the overall performance of a multi-label classifier.
Accelerated Spectral Ranking
In this paper, we design a provably faster spectral ranking algorithm, which we call accelerated spectral ranking (ASR), that is also consistent under the MNL/BTL models.
Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions
Recent work on deriving $O(\log T)$ anytime regret bounds for stochastic dueling bandit problems has considered mostly Condorcet winners, which do not always exist, and more recently, winners defined by the Copeland set, which do always exist.
Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve
Increasingly, however, in several applications, ranging from ranking to biometric screening to medicine, performance is measured not in terms of the full area under the ROC curve, but in terms of the \emph{partial} area under the ROC curve between two false positive rates.
Consistent Algorithms for Multiclass Classification with a Reject Option
We consider the problem of $n$-class classification ($n\geq 2$), where the classifier can choose to abstain from making predictions at a given cost, say, a factor $\alpha$ of the cost of misclassification.
Consistent Classification Algorithms for Multi-class Non-Decomposable Performance Metrics
In this paper, we provide a unified framework for analysing a multi-class non-decomposable performance metric, where the problem of finding the optimal classifier for the performance metric is viewed as an optimization problem over the space of all confusion matrices achievable under the given distribution.
Online Decision-Making in General Combinatorial Spaces
Here we study a general setting where costs may be linear in any suitable low-dimensional vector representation of elements of the decision space.
On the Statistical Consistency of Plug-in Classifiers for Non-decomposable Performance Measures
In this work, we consider plug-in algorithms that learn a classifier by applying an empirically determined threshold to a suitable `estimate' of the class probability, and provide a general methodology to show consistency of these methods for any non-decomposable measure that can be expressed as a continuous function of true positive rate (TPR) and true negative rate (TNR), and for which the Bayes optimal classifier is the class probability function thresholded suitably.
Convex Calibration Dimension for Multiclass Loss Matrices
We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficient conditions for a surrogate loss to be calibrated with respect to a loss matrix in this setting.
On the Relationship Between Binary Classification, Bipartite Ranking, and Binary Class Probability Estimation
It is known that a good binary CPE model can be used to obtain a good binary classification model (by thresholding at 0. 5), and also to obtain a good bipartite ranking model (by using the CPE model directly as a ranking model); it is also known that a binary classification model does not necessarily yield a CPE model.
Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses
The design of convex, calibrated surrogate losses, whose minimization entails consistency with respect to a desired target loss, is an important concept to have emerged in the theory of machine learning in recent years.
Classification Calibration Dimension for General Multiclass Losses
We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficient conditions for a surrogate loss to be classification calibrated with respect to a loss matrix in this setting.
