Ontologies are useful for automatic machine processing of domain knowledge as they represent it in a structured format.

Consequently, standard online convex optimization algorithms do not directly apply.

We give a sufficient criterion to ensure that the problem is well-conditioned.

In many learning applications, data are collected from multiple sources, each providing a batch of samples that by itself is insufficient to learn its input-output relationship. A common approach assumes that the sources fall in one of several unknown subgroups, each with an unknown input distribution and input-output relationship. We consider one of this setup's most fundamental and important manifestations where the output is a noisy linear combination of the inputs, and there are k subgroups, each with its own regression vector.

HRL lead to improved sample complexity, and how much of an improvement can it provide? Theoretical work on sample-complexity bound in Machine Learning has been integral to the development of the field.

Time perception is fundamental in our daily life. An important feature of time perception is temporal scaling (TS): the ability to generate temporal sequences (e.g., movements) with different speeds. However, it is largely unknown about the mathematical principle underlying TS in the brain.

Therefore, when trained on data generated by humans, we may not expect the artificial model to outperform the humans on their original objectives.

Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs).