Partial monitoring is a general model for online learning with limited feedback: a learner chooses actions in a sequential manner while an opponent chooses outcomes. In every round, the learner suffers some loss and receives some feedback based on the action and the outcome.

We study an online learning setting where the player is temporarily deprived of feedback each time it switches to a different action. Such model of adaptive feedback naturally occurs in scenarios where the environment reacts to the player's actions and requires some time to recover and stabilize after the algorithm switches actions. This motivates a variant of the multi-armed bandit problem, which we call the blinded multi-armed bandit, in which no feedback is given to the algorithm whenever it switches arms. We develop efficient online learning algorithms for this problem and prove that they guarantee the same asymptotic regret as the optimal algorithms for the standard multi-armed bandit problem. This result stands in stark contrast to another recent result, which states that adding a switching cost to the standard multi-armed bandit makes it substantially harder to learn, and provides a direct comparison of how feedback and loss contribute to the difficulty of an online learning problem. We also extend our results to the general prediction framework of bandit linear optimization, again attaining near-optimal regret bounds.

While there has been rapid progress in understanding the learning dynamics of neural networks, most such work focuses on the networks' ability to fit input-output relationships. However, many machine learning problems require learning representations with general utility.

In addition, new knowledge is further incorporated into the selected blocks.

Self-training has shown great potential in semi-supervised learning.

In the case of, e.g., object classification in images collected by

Stochastic classifiers arise in a number of machine learning problems, and have become especially prominent of late, as they often result from constrained optimization problems, e.g. for fairness, churn, or custom losses.

Humans can quickly learn new tasks from just a handful of examples by preserving rich representations of experience [1].