Stochastic Optimization and Adaptive Gradient Methods

Related lectures (24)

Page 1 of 3

Explores stochastic optimization algorithms and methods for convex problems with smooth and nonsmooth risks.

Explores adaptive gradient methods and their impact on optimization scenarios, including AdaGrad, ADAM, and RMSprop.

Covers the basics of linear algebra, including matrix operations and singular value decomposition.

Explores characteristic polynomials, similarity of matrices, and eigenvalues in linear transformations.

Covers linear equations, vectors, and matrices, exploring their fundamental concepts and applications.

Covers the concept of Singular Value Decomposition (SVD) for compressing information in matrices and images.

Explains the construction of U, verification of results, and interpretation of SVD in matrix decomposition.

Explores implicit bias, gradient descent, stability in optimization algorithms, and generalization bounds in machine learning.

Explores matrix factorization optimization, evaluation methods, and challenges in recommendation systems.

Covers linear systems, diagonal and triangular matrices, and LU factorization.