Role of Computation in Optimization

In course

Proident sit culpa nostrud ea quis elit sit. Cupidatat aliquip excepteur officia exercitation et duis enim velit qui do consequat. Exercitation incididunt irure quis esse tempor elit et fugiat ad cillum.

Description

This lecture covers the role of computation in optimization, focusing on gradient descent for both convex and nonconvex problems. Starting with the mathematics of data, the instructor explains the maximum-likelihood estimator and M-estimators. The lecture then delves into unconstrained minimization, approximate vs. exact optimality, and basic iterative strategies for optimization algorithms. Descent methods, including the gradient descent algorithm, are discussed in detail, along with the challenges faced in iterative optimization algorithms. The concepts of stationarity, local minima, and global optimality are explored, emphasizing the importance of convexity in optimization algorithms.

Instructor

Cillum officia ad voluptate et do sit amet sit consectetur. Mollit ipsum anim esse esse do voluptate exercitation ex reprehenderit eiusmod voluptate enim amet. Aute consectetur nostrud elit irure quis dolore aute consequat nulla exercitation ea enim. Nostrud magna ipsum sit proident do dolor ipsum occaecat dolore enim.

Official source

https://mediaspace.epfl.ch/media/0_jhcybkju

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Theoretical computer science

Algorithms and data structures: Combinatorial optimization

Related lectures (35)

Explores gradient descent methods for smooth convex and non-convex problems, covering iterative strategies, convergence rates, and challenges in optimization.

Explores Gradient Descent for Linear MSE in machine learning, covering computation, complexity, variants, Stochastic Gradient Descent, penalty functions, implementation issues, and non-convex optimization.

Explores adversarial machine learning, covering the generation of adversarial examples, robustness challenges, and techniques like Fast Gradient Sign Method.

Explores primal-dual optimization, minimax problems, and gradient descent-ascent methods for optimization algorithms.

Covers optimization methods, convergence guarantees, trade-offs, and variance reduction techniques in numerical optimization.