Related papers: Out of Distribution Generalization in Machine Lear…

Deep neural networks can obtain impressive performance on various tasks under the assumption that their training domain is identical to their target domain. Performance can drop dramatically when this assumption does not hold. One…

Statistical machine learning theory often tries to give generalization guarantees of machine learning models. Those models naturally underlie some fluctuation, as they are based on a data sample. If we were unlucky, and gathered a sample…

Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the…

Machine learning algorithms typically assume independent and identically distributed samples in training and at test time. Much work has shown that high-performing ML classifiers can degrade significantly and provide overly-confident, wrong…

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is…

Distribution shifts on graphs -- the data distribution discrepancies between training and testing a graph machine learning model, are often ubiquitous and unavoidable in real-world scenarios. Such shifts may severely deteriorate the…

Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of distribution shifts…

Out-of-distribution detection is one of the most critical issue in the deployment of machine learning. The data analyst must assure that data in operation should be compliant with the training phase as well as understand if the environment…

Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We posit that this phenomenon is caused by a mismatch…

The recent achievements of Deep Learning rely on the test data being similar in distribution to the training data. In an ideal case, Deep Learning models would achieve Out-of-Distribution (OoD) Generalization, i.e. reliably make predictions…

Out-of-distribution (OOD) generalization is a challenging machine learning problem yet highly desirable in many high-stake applications. Existing methods suffer from overly pessimistic modeling with low generalization confidence. As…

Algorithmic generalization in machine learning refers to the ability to learn the underlying algorithm that generates data in a way that generalizes out-of-distribution. This is generally considered a difficult task for most machine…

Machine learning (ML) models are typically optimized for their accuracy on a given dataset. However, this predictive criterion rarely captures all desirable properties of a model, in particular how well it matches a domain expert's…

As training datasets grow larger, we aspire to develop models that generalize well to any diverse test distribution, even if the latter deviates significantly from the training data. Various approaches like domain adaptation, domain…

Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generations wireless systems. This led to a large body of research work that applies ML techniques to solve problems in different layers of the…

Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and their respective impacts. Literature evidence from…

A major challenge in machine learning is resilience to out-of-distribution data, that is data that exists outside of the distribution of a model's training data. Training is often performed using limited, carefully curated datasets and so…

A wide variety of problems in machine learning, including exemplar clustering, document summarization, and sensor placement, can be cast as constrained submodular maximization problems. Unfortunately, the resulting submodular optimization…

Machine Learning (ML) has been a foundational topic in artificial intelligence (AI), providing both theoretical groundwork and practical tools for its exciting advancements. From ResNet for visual recognition to Transformer for…

There are many computer vision applications including object segmentation, classification, object detection, and reconstruction for which machine learning (ML) shows state-of-the-art performance. Nowadays, we can build ML tools for such…