OptML_course
OptML_course copied to clipboard
epfml
EPFL Course - Optimization for Machine Learning - CS-439
In Lemma 4.3, the easy direction (Exercise 29) can easily be proved. However, the other direction needs additional conditions, otherwise, it's not correct. For example, consider f(x) = -√x for...
In the proof, I found that after dividing both sides by  we can only conclude that the left part is ≤ 0 (since there is no guarantee that it...
In Chapter 2, there are many references to the gradient descent algorithm, but the following equation numbers are not (2.1) but (2.11).
In the lecture 11 slides about duality (page 6), shouldn't it be L(u) = - f*(-u) - g*(A^T u), instead of the expression given there? Thanks!
 In Lab 02, the `grad_norm_bound` value in the last section is computed incorrectly. It should be calculated as `(25 * np.linalg.norm(np.dot(A.T, A), 2) + np.linalg.norm(np.dot(A.T, b))) / A.shape[0]` in...
There is a typo in one of the helper files. Removing the `b` fixes it.
