arXiv research

New methods detect unfairness in multiclass classifiers using DCP.

Develops methods for valid and validated confidence sets in multiclass and multilabel prediction.

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…

FOLKLORE algorithm speeds up online multiclass logistic regression.

Study extends binary omniprediction to multiclass setting with improved sample complexity.

New framework for evaluating multiclass classifier calibration.

The paper predicts diseases using both clinical and genomics data.

Excessive reuse of holdout data can lead to overfitting. However, there is little concrete evidence of significant overfitting due to holdout reuse in popular multiclass benchmarks today. Known results show that, in the worst-case, revealing the accuracy of $k$ adaptively chosen classifiers on a data set of size $n$ al…

Extends boosting to multiclass online agnostic classification.

New truthful calibration errors improve model ranking in multiclass prediction.

A new method for multiclass calibration using vector quantization.

Proposes top-label calibration and M2B framework for multiclass to binary calibration.

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…

We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore the implications. We also show how the separation of concerns afforded by using …

Multiclass prediction is the problem of classifying an object into a relevant target class. We consider the problem of learning a multiclass predictor that uses only few features, and in particular, the number of used features should increase sub-linearly with the number of possible classes. This implies that features …

This work characterizes when a hypothesis class can be k-list learned.

New algorithm improves multiclass classification regret bound.

We present an efficient second-order algorithm with $\tilde{O}(\frac{1}η\sqrt{T})$ regret for the bandit online multiclass problem. The regret bound holds simultaneously with respect to a family of loss functions parameterized by $η$, for a range of $η$ restricted by the norm of the competitor. The family of loss funct…

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective multiplicative factor for inputs to the last softmax layer. On non-neural models the exist…

VR game data for P300 BCI with raccoon vs demon stimuli.

New Sauer inequality improves multiclass hypothesis class bounds.

Proposes MCLLO for assessing and recalibrating multiclass probability predictions.

Extracts geometric information from point-clouds for multiclass classification.

Study online learning with set-valued feedback, showing differences between deterministic and randomized approaches.

Novel analysis improves weighted majority vote in multiclass classification.

Develops a robust multiclass classification method for deep image classifiers.

We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness. Although several methods have been developed for this problem, recent challenging real-world applications require further performance…

We investigate the problem of multiclass classification with rejection, where a classifier can choose not to make a prediction to avoid critical misclassification. First, we consider an approach based on simultaneous training of a classifier and a rejector, which achieves the state-of-the-art performance in the binary …

Study resolves conjecture on overparameterized linear models' generalization.

We present online boosting algorithms for multiclass classification with bandit feedback, where the learner only receives feedback about the correctness of its prediction. We propose an unbiased estimate of the loss using a randomized prediction, allowing the model to update its weak learners with limited information. …

Paper analyzes risk bounds for in-context learning in multiclass classification.

Novel method for multiclass ROC curves using multidimensional Gini index.

Survey on assessing and improving classifier calibration for better decision making.

New research determines the optimal sample complexity for multiclass and list learning.

Combining Bayesian deep learning and split conformal prediction affects out-of-distribution coverage.

Unified binary and multiclass margin-based classification methods.

Sharp sample complexity for multiclass PAC learning with bandit feedback.

Optimal transport improves multivariate prediction uncertainty quantification.

We propose Rademacher complexity bounds for multiclass classifiers trained with a two-step semi-supervised model. In the first step, the algorithm partitions the partially labeled data and then identifies dense clusters containing $κ$ predominant classes using the labeled training examples such that the proportion of t…

Enhanced word embeddings boost multiclass text classification accuracy.

Study shows exponential error reduction in multiclass classification without bias-variance trade-off.

The paper analyzes how overparameterized models can generalize well in multiclass classification.

New method for multiclass classification reduces error bounds.

Study online multiclass classification under bandit feedback, extending previous results.

This work extends implicit bias analysis to multiclass classification using a new loss framework.

Paper studies multiclass classifiers from binary classifiers, proving methods and demonstrating advantages.

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

The paper extends multiple instance learning to multiclass and regression problems.