Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed preserves as much information about labels possible. Under this principle, two different methods have been proposed, i.e., (IB) and deterministic (DIB), gained significant progress in explaining the mechanisms deep algorithms. However, these theoretical empirical suc...

The information bottleneck (IB) method is a technique for extracting that relevant predicting the target random variable from source variable, which typically implemented by optimizing IB Lagrangian balances compression and prediction terms. However, hard to optimize, multiple trials tuning values of multiplier are required. Moreover, we show performance strictly decreases as gets stronger duri...

The bottleneck (BN) of a production line is a machine that impedes the system’s performance in the strongest manner. It has been shown in the previous work that the so-called downtime bottlenecks (DT-BNs) are of main industrial importance. In this paper, a method for DT-BN identification is developed in the framework of serial production lines with unreliable (Markovian) machines and finite buf...

Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then final label based on concept predictions. We extend CBMs interactive settings where model can query a human collaborator some concepts. develop an interaction policy that, at time, chooses which request so as maximally improve pr...