Related papers: High Dimensional Binary Classification under Label…
Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight…
Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large. The impact of particular forms of normalization, however, has so far been investigated in limited…
Deep imbalanced regression (DIR), where the target values have a highly skewed distribution and are also continuous, is an intriguing yet under-explored problem in machine learning. While recent works have already shown that incorporating…
A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for…
Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels and cannot keep track of the predictive rules…
It has been hypothesized that label smoothing can reduce overfitting and improve generalization, and current empirical evidence seems to corroborate these effects. However, there is a lack of mathematical understanding of when and why such…
Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…
Linear discriminant analysis is a widely used method for classification. However, the high dimensionality of predictors combined with small sample sizes often results in large classification errors. To address this challenge, it is crucial…
Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by…
The vulnerability of models to data aberrations and adversarial attacks influences their ability to demarcate distinct class boundaries efficiently. The network's confidence and uncertainty play a pivotal role in weight adjustments and the…
We explore the problem of learning under selective labels in the context of algorithm-assisted decision making. Selective labels is a pervasive selection bias problem that arises when historical decision making blinds us to the true outcome…
Training neural network classifiers on datasets with label noise poses a risk of overfitting them to the noisy labels. To address this issue, researchers have explored alternative loss functions that aim to be more robust. The…
The learning from imbalanced data is a deeply studied problem in standard classification and, in recent times, also in multilabel classification. A handful of multilabel resampling methods have been proposed in late years, aiming to balance…
We study the open-set label shift problem, where the test data may include a novel class absent from training. This setting is challenging because both the class proportions and the distribution of the novel class are not identifiable…
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…
Over-parameterized deep models usually over-fit to a given training distribution, which makes them sensitive to small changes and out-of-distribution samples at inference time, leading to low generalization performance. To this end, several…
Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…
Among the three main components (data, labels, and models) of any supervised learning system, data and models have been the main subjects of active research. However, studying labels and their properties has received very little attention.…
Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to detect mislabeled instances and subject them to special…
Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing…