Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 10 of 10 for “"accelerated gradient descent"”.
-
Preconditioned Nesterov’s Accelerated Gradient Descent Method and Its Applications to Nonlinear PDE
… foundation for the application of Nesterov’s accelerated gradient descent method (AGD) to the approximation of solutions of a wide class of partial differential equations (PDEs). This is achieved by proving the existence of an invariant set and exponential convergence rates when its …
-
Acceleration in first-order optimization methods: promenading beyond convexity or smoothness, and applications
… for the same problem. For example, Nesterov's Accelerated Gradient Descent improves over the gradient descent method for the optimization of smooth and convex functions. In this thesis, we investigate the acceleration phenomenon and its applications for three previously studied research …
-
New Accelerated Methods for Optimization and Reinforcement Learning
… we focus on the design and analysis of novel accelerated first-order algorithms for large-scale nonlinear and stochastic optimization, addressing key challenges such as stochasticity, nonconvexity, and uncertainty in problem structures and parameters. We also develop new accelerated methods …
-
Métodos de otimização aplicados à estatística
… study, in the field of optimization methods, the gradient descent, accelerated gradient descent, high-order accelerated gradient and Newton-Raphson and we study the theoretical convergence rates of the sequences generated by these methods. Second, we take as a case study, in the field of …
-
First-Order Algorithms for Convex Smooth Optimization Problems With Homogeneous Linear Constraints
… needed to reach a consensus. We show that an accelerated gradient descent algorithm can compute an $\varepsilon$-approximate solution with at most $\cO(\log(1/\varepsilon))$ matrix-vector multiplications. In the second project, we study convex smooth optimization with general homogeneous …
-
New Computational Geometry Methods for Some Fundamental Machine Learning Problems
… rank approximation problem by proposing a novel accelerated Alternative Minimization (ALM) framework with momentum. In our problem, the method needs to synchronically adjust the weights according to related constraints, while factorizing the input matrix. We first eliminate the normal ALM …
-
Theory and Results on Restarting Schemes for Accelerated First Order Methods
… function could be possibly non-smooth, proximal gradient methods are one of the main tools for these problems. These methods benefit from acceleration, which uses the memory of past iterates to add momentum to the algorithms. Such methods have a O(1/k^2) convergence rate in terms of function …
-
Control Theory-Inspired Acceleration of the Gradient-Descent Method: Centralized and Distributed
… data-driven modeling problems. The traditional gradient-descent method can solve optimization problems with differentiable cost functions. However, the speed of convergence of the gradient-descent method and its accelerated variants is highly influenced by the conditioning of the optimization …
-
Exploiting Problem Structure for Faster Optimization: A Trilinear Saddle Point Approach
… optimization. We introduce the single-loop Accelerated Constrained Gradient Descent (ACGD) method, which modifies Nesterov's celebrated Accelerated Gradient Descent (AGD) method by incorporating a linearly-constrained descent step. Lower complexity bounds are provided to establish the …
-
Designing optimization algorithms through the lens of online learning
… function only through local queries such as gradients and Hessians, which can often be efficiently computed via automatic differentiation in modern machine learning applications. Thus, a fundamental question is how many such oracle queries are required before reaching a desired accuracy. In …