arXiv research

Paper bounds convergence rate of adversarial surrogate risk.

We present surrogate regret bounds for arbitrary surrogate losses in the context of binary classification with label-dependent costs. Such bounds relate a classifier's risk, assessed with respect to a surrogate loss, to its cost-sensitive classification risk. Two approaches to surrogate regret bounds are developed. The…

Randomizing the Fourier-transform (FT) phases of temporal-spatial data generates surrogates that approximate examples from the data-generating distribution. We propose such FT surrogates as a novel tool to augment and analyze training of neural networks and explore the approach in the example of sleep-stage classificat…

Paper establishes a universal growth rate for smooth surrogate losses in classification.

The paper studies consistency of surrogate loss procedures under constrained classifiers.

The paper explores trading off consistency and dimensionality in convex surrogates for multiclass classification.

Adversarial consistency depends on the uniqueness of adversarial Bayes classifiers.

Proposes a method for inference in high-dimensional classification with non-differentiable surrogate losses.

Study proposes a differentiable surrogate loss function for optimizing $F_β$ score in binary classification with imbalanced data.

Study on $H$-consistency bounds for machine learning surrogates.

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) m…

A new method SLIDE ensures fairness in AI models.

Study of loss functions for learning to defer, proving consistency.

This research analyzes the consistency of convex and nonconvex surrogate losses for adversarially robust classification.

Linear-Core Surrogates combine fast optimization and statistical efficiency in classification and structured prediction.

This research improves PAC-Bayesian bounds for classification tasks using convexified loss.

Enhanced $H$-consistency bounds derived under relaxed conditions.

New algorithms for multi-class classification with abstention.

Study on learning to defer to multiple experts with consistent surrogates and confidence calibration.

Gaptron algorithm reduces mistakes in online multiclass classification.

Complex classification performance metrics such as the F${}_β$-measure and Jaccard index are often used, in order to handle class-imbalanced cases such as information retrieval and image segmentation. These performance metrics are not decomposable, that is, they cannot be expressed in a per-example manner, which hinder…

In this dissertation, we focus on several important problems in structured prediction. In structured prediction, the label has a rich intrinsic substructure, and the loss varies with respect to the predicted label and the true label pair. Structured SVM is an extension of binary SVM to adapt to such structured tasks. I…

New active learning framework for multiclass classification beyond realizability assumption.

In this paper we refine the process of computing calibration functions for a number of multiclass classification surrogate losses. Calibration functions are a powerful tool for easily converting bounds for the surrogate risk (which can be computed through well-known methods) into bounds for the true risk, the probabili…

Conventional techniques for supervised classification constrain the classification rules considered and use surrogate losses for classification 0-1 loss. Favored families of classification rules are those that enjoy parametric representations suitable for surrogate loss minimization, and low complexity properties suita…

This paper develops convex surrogates for optimizing the multi-label F-measure.

The paper proposes a method to model non-smooth functions using clustering, classification, and Gaussian process modeling.

Improves disease progression prediction using auxiliary surrogate labels and health markers.

We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…

Study on top-$k$ classification with new loss functions and algorithms.

In this work we provide a theoretical framework for structured prediction that generalizes the existing theory of surrogate methods for binary and multiclass classification based on estimating conditional probabilities with smooth convex surrogates (e.g. logistic regression). The theory relies on a natural characteriza…

We study consistency properties of machine learning methods based on minimizing convex surrogates. We extend the recent framework of Osokin et al. (2017) for the quantitative analysis of consistency properties to the case of inconsistent surrogates. Our key technical contribution consists in a new lower bound on the ca…

This paper characterizes and designs loss functions for robust classification with abstention.

Symmetric losses improve classifier robustness from corrupted labels.

Optimizes hard-to-optimize metrics using adaptive surrogates.

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many predictions (e.g.\ rankings) as a point in $\mathbb{R}^d$, assigns the original loss val…

Establishes a condition for multiclass classification-calibration of Gamma-Phi losses.

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 $α$ of the cost of misclassification. Designing consistent algorithms for such $n$-class classification problems with a `reject option' is the main goal of t…

We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. 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 pro…

Paper introduces new loss functions for multi-class abstention learning.

Paper shows SVM can achieve super fast convergence rates.

Comment on entropy learning for dynamic treatment regimes.

Area under ROC (AUC) is an important metric for binary classification and bipartite ranking problems. However, it is difficult to directly optimizing AUC as a learning objective, so most existing algorithms are based on optimizing a surrogate loss to AUC. One significant drawback of these surrogate losses is that they …

The minimization of loss functions is the heart and soul of Machine Learning. In this paper, we propose an off-the-shelf optimization approach that can minimize virtually any non-differentiable and non-decomposable loss function (e.g. Miss-classification Rate, AUC, F1, Jaccard Index, Mathew Correlation Coefficient, etc…

Unified surrogate loss framework for multi-label learning with strong consistency guarantees.

New algorithm optimizes PAC-Bayes bound without surrogate loss.

Paper proposes a method to make image model explanations robust to distortions.

Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objective is to produce a classifier of relatively low risk, as measured under the 0-1 loss, ideally usin…