This paper introduces a new learning paradigm, called Learning Using Statistical Invariants (LUSI), which is different from the classical one. In a classical paradigm, the learning machine constructs a classification rule that minimizes the probability of expected error; it is data-driven model of learning. In the LUSI paradigm, in order to construct the desired classification function, a learning
![Rethinking statistical learning theory: learning using statistical invariants - Machine Learning](https://cdn-ak-scissors.b.st-hatena.com/image/square/79a2daa4156cc25a3e378029ea4efb3b7b58ebc8/height=288;version=1;width=512/https%3A%2F%2Fstatic-content.springer.com%2Fimage%2Fart%253A10.1007%252Fs10994-018-5742-0%2FMediaObjects%2F10994_2018_5742_Fig1_HTML.png)