Online machine learning is an effective way for observation-based learning when a static
dataset is not available. However, it can be challenging in real-world applications, especially …

Online learning for multi-class classification is a well-studied topic in machine learning. The
standard multi-class classification online learning setting assumes continuous availability of …

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 …

In many real-life classification problems, we may not get exact class labels for training
samples. One such example is bandit feedback in multiclass classification. In this setting, we …

Online learning is a fundamental paradigm for learning from continuous data stream.
Tradition online learning approaches usually assume that the feature space of data stream …

This paper addresses the problem of multiclass classification with corrupted or noisy bandit
feedback. In this setting, the learner may not receive true feedback. Instead, it receives …

Online active learning algorithms reduce human labeling costs by querying only a subset of
informative incoming instances from the data stream to update the classification model …

Have you ever wondered why your feed gets filled with movies or similar web series after
watching a movie on Netflix? This happens because Netflix uses a recommendation system …

Online learning is a very well worked learning paradigm that has both theoretical as well as
practical appeal. Online learning aims to make a sequence of accurate predictions given the …

Bandit problems constitute a sequential dynamic allocation problem. The pulling agent has
to explore its environment (ie the arms) to gather information on the one hand, and it has to …