About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Optimization - Here we continue the optimization thread starting with the least square for regression.
I have added an example of a non-continuous function that has continuous partial derivatives.
- Also try to answer the following questions:
- What is the VC dimension of M?
- For a given continuous function construct a neural network that approximates it.
- A m*n matrix A defines a function from R^m to R^n by the multiplication Ax, x in R^n. What is the Jacobian of A?
Consider the Regression I image below.
How to turn non convex optimization problems to convex optimization problems and why.
Quadric form:
Given that the second order Taylor expansion of a function is a quadratic form it plays a central role in optimization.
Positive definite matrix:
The relation between positive definite of the Hessian and the Taylor expansion.
