Optimality of Convergence Rates: Accelerated Gradient Descent

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Explores convexity, Jacobians, subdifferentials, and convergence rates in optimization and function analysis.

By Quoc Tran-Dinh explores accelerated algorithms for monotone inclusions, covering optimization models, challenges, and new algorithms.

Explores VC dimension, gradient descent, convex sets, and Lipschitz functions in convex optimization.

Explores iterative descent methods in optimization, gradient descent, local minima, and convergence principles.

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

Covers basics on optimization, including norms, Lipschitz continuity, and convexity concepts.

The session explains how momentum accelerates gradient descent, presents the theory of nonlinear conjugate gradients on manifolds, compares several beta‑rule updates, discusses line‑search and preconditioner choices, and shows how to employ the Manopt library for Riemannian optimization without explicit Hessians.

Covers the fundamentals of multilayer neural networks and deep learning.

Discusses interpreting convergence plots in optimization, identifying bugs based on convergence rates, and understanding optimization algorithms.

Covers optimization basics, including metrics, norms, convexity, gradients, and logistic regression, with a focus on strong convexity and convergence rates.

Explores linear models, regression, multi-output prediction, classification, non-linearity, and gradient-based optimization.

Covers coordinate descent, a method for optimizing functions by updating one coordinate at a time.

Explores convex optimization, convex functions, and their properties, including strict convexity and strong convexity, as well as different types of convex functions like linear affine functions and norms.

Covers information measures like entropy and Kullback-Leibler divergence.

Covers optimization methods without constraints, including gradient and line search in the quadratic case.

Explores the multilayer perceptron model, training, optimization, data preprocessing, activation functions, backpropagation, and regularization.

Introduces linear and logistic regression, covering parametric models, multi-output prediction, non-linearity, gradient descent, and classification applications.

Introduces preconditioning in optimization problems and explains steepest descent iteration.

Covers the semester project on numerics, focusing on adaptive algorithms and multistep methods.

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