相关论文: Online Bayesian Imbalanced Learning with Bregman-C…

We consider the problem of online learning in misspecified linear stochastic multi-armed bandit problems. Regret guarantees for state-of-the-art linear bandit algorithms such as Optimism in the Face of Uncertainty Linear bandit (OFUL) hold…

Long-tailed classification poses a challenge due to its heavy imbalance in class probabilities and tail-sensitivity risks with asymmetric misprediction costs. Recent attempts have used re-balancing loss and ensemble methods, but they are…

Data for face analysis often exhibit highly-skewed class distribution, i.e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances. To mitigate this issue, contemporary deep…

In this paper we address imbalanced binary classification (IBC) tasks. Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find…

Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To…

Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we…

Distributionally robust optimization (DRO) and invariant risk minimization (IRM) are two popular methods proposed to improve out-of-distribution (OOD) generalization performance of machine learning models. While effective for small models,…

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated.…

Improving the reliability of deployed machine learning systems often involves developing methods to detect out-of-distribution (OOD) inputs. However, existing research often narrowly focuses on samples from classes that are absent from the…

Deep learning models, especially convolutional neural networks, have achieved impressive results in medical image classification. However, these models often produce overconfident predictions, which can undermine their reliability in…

Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time. Distinct from other continual learning settings the learner is presented new samples…

Bayesian decision theory advocates the Bayes classifier as the optimal approach for minimizing the risk in machine learning problems. Current deep learning algorithms usually solve for the optimal classifier by \emph{implicitly} estimating…

Bayesian optimization (BO) is a widely used framework for optimizing expensive black-box functions, commonly based on Gaussian process (GP) surrogate models. Its effectiveness relies on uncertainty quantification that is both sharp…

Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies, especially in scenarios where exploration is costly or infeasible. Nevertheless, its performance…

To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (OCIL), where incoming…

Accurate probabilistic predictions can be characterized by two properties -- calibration and sharpness. However, standard maximum likelihood training yields models that are poorly calibrated and thus inaccurate -- a 90% confidence interval…

Multiple Instance learning (MIL) models have been extensively used in pathology to predict biomarkers and risk-stratify patients from gigapixel-sized images. Machine learning problems in medical imaging often deal with rare diseases, making…

Large neural networks pretrained on web-scale corpora are central to modern machine learning. In this paradigm, the distribution of the large, heterogeneous pretraining data rarely matches that of the application domain. This work considers…

An ever increasing volume of data is nowadays becoming available in a streaming manner in many application areas, such as, in critical infrastructure systems, finance and banking, security and crime and web analytics. To meet this new…

With the widespread adoption of deep learning in visual tasks, Class-Incremental Learning (CIL) has become an important paradigm for handling dynamically evolving data distributions. However, CIL faces the core challenge of catastrophic…