Descent methods and line search: Finiteness of the line search algorithm

Related lectures (50)

Covers Markov games, their dynamics, equilibria, and applications in reinforcement learning.

Covers faster gradient descent methods and projected gradient descent for constrained optimization in machine learning.

Discusses variance reduction techniques in stochastic simulation, focusing on allocation strategies and replica generation algorithms.

Covers optimization algorithms, focusing on Proximal Gradient Descent and its variations.

Covers trust region methods, focusing on the framework and algorithms.

Discusses proximal gradient descent and its applications in optimizing machine learning algorithms.

Provides an overview of optimization techniques, focusing on gradient descent and properties of convex functions in machine learning.

Explores dynamic programming with Bellman-Ford, Dijkstra, greedy strategies, and activity scheduling problems.

Covers the LLL algorithm for reducing lattice bases to shorter and more orthogonal forms through iterative transformations.

Demonstrates dynamic programming to find the number of ways to make change using different coin denominations.

Introduces linear algebra, calculus, and optimization basics in Euclidean spaces, emphasizing the power of optimization as a modeling tool.

Covers semi-definite programming and optimization over positive semidefinite cones.

Explores approximate convergence, optimization theorems, and mirror descent in mathematical algorithms.

Covers optimization principles, including linear optimization, networks, and concrete research examples in transportation.

Covers single inequality or equality constraints and necessary optimality conditions in optimization problems.

Explores dynamic programming with the Steinitz sequence to optimize solutions efficiently.

Explores neural networks trained under Stochastic Gradient Descent, discussing hidden layers, square loss function, and particle evolution.

Covers the concept of finding an initial BFS and solving related optimization problems.

Covers extreme values, optimization conditions, feasible sets, and partition formation for optimization.

Covers deriving basic linear program representation, finding solutions, and exploring optimality.

Page 2 of 3