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 4 of 4 for “"Finite-sum optimization"”.
-
Stochastic algorithms for distributed optimization and machine learning
… decisions. It has strong ties to the field of optimization, in the way the latter provides methods and theory. While data tends to be collected in a distributed fashion, the standard machine learning models require centralizing the training data on one machine or in a data center, which incurs …
-
STUDY OF STOCHASTIC POLYAK STEP-SIZES FOR STOCHASTIC OPTIMIZATION
… descent (SGD) is commonly used in solving finite sum optimization problems. The main parameter one needs to choose for this algorithm is the step-size. Adaptive step sizes are particularly appealing as generally they do not rely on the parameter of functions such as smoothness constant or …
-
A Modern Treatise on Variational Inequality Problems: Structures, Algorithms, and Iteration Complexities
… with the modern research trends in both VI and optimization. We start from the first-order methods, where acceleration has been established in algorithms such as extra-gradient method, optimistic gradient descent ascent method, and dual extrapolation method. These methods are known as optimal in …
-
Frank-Wolfe Methods for Optimization and Machine Learning
… and projections on several sets commonly used in optimization, providing a rigorous support to the use of FW. We also propose two methods for projecting onto the lp-ball and the Birkhoff polytope respectively, and we analyze their complexity. Computational experiments for the l1-ball and the …