One way of explaining the success of such simple algorithms is by analyzing the optimization landscape and show that all local minima are...

This course will be your guide to learning how to use the power of theory, math and python to create linear regression and logistic regression, two of most popular and useful machine learning models from scratch. This course is designed for folks with some programming experience or experienced developers looking to make the jump to data science and machine learning, I'll teach you how to dive deep into the math behind the linear models in an easy and understandable way. Once, you have understood the inner workings of the linear models and uncovered the black box, you are ready to code everything from the ground up without using any fancy ready made machine learning libraries and yes you will be taught that too! The course is beneficial for understanding the machine learning concepts deeply rather than just using some library to get results, it will guide you in the right direction for learning many other machine learning and deep learning algorithms, as this course covers all the basics required, you will be well on your way to becoming an expert Data Scientist! Since this course goes deep into the math and has coding from scratch, a basic to intermediate knowledge of coding is a must, also good idea of derivatives(calculus), linear algebra(matrix multiplication) and basic probability is required to get the full out of this course.

We consider sequential prediction with expert advice when the data are generated stochastically, but the distributions generating the data may vary arbitrarily among some constraint set. We quantify relaxations of the classical I.I.D. assumption in terms of possible constraint sets, with I.I.D. at one extreme, and an adversarial mechanism at the other. The Hedge algorithm, long known to be minimax optimal for in the adversarial regime, has recently been shown to also be minimax optimal in the I.I.D. setting. We show that Hedge is sub-optimal between these extremes, and present a new algorithm that is adaptively minimax optimal with respect to our relaxations of the I.I.D. assumption, without knowledge of which setting prevails.