arXiv research

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

Develops NPMC method for noisy labels, improving multiclass classification accuracy.

This work analyzes label embedding for large multiclass classification problems.

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

Study computable multiclass learning within PAC framework.

Study shows SQ hardness for multiclass linear classification with random noise.

Extracts geometric information from point-clouds for multiclass classification.

Study optimal rates for multiclass classification, resolving open questions.

The C-bound, introduced in Lacasse et al., gives a tight upper bound on the risk of a binary majority vote classifier. In this work, we present a first step towards extending this work to more complex outputs, by providing generalizations of the C-bound to the multiclass and multi-label settings.

New algorithm improves multiclass classification regret bound.

Learnable multiclass hypothesis classes don't always have a sample compression scheme of fixed size.

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

New loss function calibrates WW-hinge loss for multiclass SVM.

In this paper, we propose online algorithms for multiclass classification using partial labels. We propose two variants of Perceptron called Avg Perceptron and Max Perceptron to deal with the partial labeled data. We also propose Avg Pegasos and Max Pegasos, which are extensions of Pegasos algorithm. We also provide mi…

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…

New algorithm tackles multiclass transductive online learning with unbounded labels.

We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each label within a given bag are known. This is a common situation in cases where per-data labeling is lengt…

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

Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two direc…

Distillation improves simple models by approximating complex labels.

New method reduces labeler costs by aggregating predictions from local classifiers.

Study improves online learning with adaptable agents in various settings.

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…

We present a graph-based variational algorithm for multiclass classification of high-dimensional data, motivated by total variation techniques. The energy functional is based on a diffuse interface model with a periodic potential. We augment the model by introducing an alternative measure of smoothness that preserves s…

Characterizes learnability of forgiving 0-1 loss functions in multiclass settings.

In multiclass classification, the goal is to learn how to predict a random label $Y$, valued in $\mathcal{Y}=\{1,\; \ldots,\; K \}$ with $K\geq 3$, based upon observing a r.v. $X$, taking its values in $\mathbb{R}^q$ with $q\geq 1$ say, by means of a classification rule $g:\mathbb{R}^q\to \mathcal{Y}$ with minimum prob…

Geometry-aware KDE model improves multiclass quantification.

A robust multiclass SVM tackles imbalanced data uncertainty.

Achieving advancements in automatic recognition of emotions that music can induce require considering multiplicity and simultaneity of emotions. Comparison of different machine learning algorithms performing multilabel and multiclass classification is the core of our work. The study analyzes the implementation of the G…

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

Sharp sample complexity for multiclass PAC learning with bandit feedback.

New algorithm learns multiclass concepts with finite Littlestone dimension.

A new KDE-based method improves multiclass quantification.

Study expands multiclass classification models with new rates and partial concept classes.

New truthful calibration errors improve model ranking in multiclass prediction.

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…

This work addresses two classification problems that fall under the heading of domain adaptation, wherein the distributions of training and testing examples differ. The first problem studied is that of class proportion estimation, which is the problem of estimating the class proportions in an unlabeled testing data set…

Research on predicting with lists of labels, characterizing learnability and providing algorithms.

New bounds show agnostic multiclass learning depends on two dimensions: Natarajan and Daniely-Shalev-Shwartz.

Proposes a stable classifier using inflated argmax for multiclass classification.

Paper tackles noisy labels for non-decomposable performance measures.

One-bit quantization and sparsification improve multiclass classification with strong regularization.

Data labeling is currently a time-consuming task that often requires expert knowledge. In research settings, the availability of correctly labeled data is crucial to ensure that model predictions are accurate and useful. We propose relatively simple machine learning-based models that achieve high performance metrics in…

Improved PAC learning algorithm for multiclass classification with bandit feedback.

Machine learning models are vulnerable to adversarial examples. An adversary modifies the input data such that humans still assign the same label, however, machine learning models misclassify it. Previous approaches in the literature demonstrated that adversarial examples can even be generated for the remotely hosted m…

We propose a framework for constructing and analyzing multiclass and multioutput classification metrics, i.e., involving multiple, possibly correlated multiclass labels. Our analysis reveals novel insights on the geometry of feasible confusion tensors -- including necessary and sufficient conditions for the equivalence…

Study resolves conjecture on overparameterized linear models' generalization.

There is a rapidly increasing interest in crowdsourcing for data labeling. By crowdsourcing, a large number of labels can be often quickly gathered at low cost. However, the labels provided by the crowdsourcing workers are usually not of high quality. In this paper, we propose a minimax conditional entropy principle to…