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 13 of 13 for “"Stochastic convex optimization"”.
-
Advanced Decomposition Methods in Stochastic Convex Optimization
Při práci s úlohami stochastického programování se často setkáváme s optimalizačními problémy, které jsou příliš rozsáhlé na to, aby byly zpracovány pomocí rutinních metod matematického programování. Nicméně, v některých případech mají tyto problémy vhodnou strukturu, umožňující použití …
-
Unconstrained online convex optimization: regularization in the adversarial setting and beyond
… solution, and receive gradient feedback that is stochastic, corrupted, or both. This thesis studies whether these two difficulties can be resolved simultaneously: we develop online convex optimization algorithms on an unconstrained domain that adapt to the unknown problem scale while operating …
-
Stochastic Optimization and Learning: An Adaptive and Resource-Efficient Approach
This dissertation focuses on stochastic optimization and learning where the underlying probabilistic models are unknown and the decision maker optimizes their actions over time through sequential interactions with the unknown environment. The first part of this dissertation is on stochastic …
-
Advancing Differentially Private Optimization: Efficiency, Utility, and Applications
… minimization (DP-ERM) and differentially private stochastic (convex) optimization (DP-SCO). Our goal is to design more efficient algorithms for these problems while achieving better and optimal privacy-utility trade-offs. The thesis is structured into five parts: (1) Part I focuses on improving …
-
Automating Stochastic Optimal Control
Stochastic Optimal Control is an elegant and general framework for specifying and solving control problems. However, a number of issues have impeded its adoption in practical situations. In this thesis, we describe algorithmic and theoretical developments that address some of these issues. In the …
-
Towards private and efficient optimization methods for machine learning
… algorithms for various settings, including Non-convex Empirical Risk Minimization (ERM), Stochastic Convex Optimization (SCO), and Stochastic Linear Bandits. We begin by exploring the general Non-convex Optimization landscape, which is central to modern ML, and discuss the challenges involved in …
-
Convex optimization under inexact first-order information
… complexity analysis of the algorithms to solve convex programming problems under inexact first-order information. In the first part of this thesis we focus on the general non-smooth convex minimization under a stochastic oracle. We start by introducing an important algorithmic advancement in …
-
Information-Theoretic Measures of Generalization in Machine Learning
… in studying the generalization error of Stochastic Gradient Langevin Dynamics (SGLD). Our numerical analyses show that the obtained bounds are the first non-vacuous generalization guarantees for SGLD and its full-batch counterpart for modern deep-learning datasets and architectures. …
-
On the resolution of misspecification in stochastic optimization, variational inequality, and game-theoretic problems
… much of the research in the field of optimization algorithms has assumed that problem parameters are correctly specified. Recent efforts under the robust optimization framework have relaxed this assumption by allowing unknown parameters to vary in a prescribed uncertainty set and by …
-
New Accelerated Methods for Optimization and Reinforcement Learning
… 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 for reinforcement learning, accompanied by improved computational …
-
Stochastic approximation schemes for stochastic optimization and variational problems: adaptive steplengths, smoothing, and regularization
Stochastic approximation (SA) methods, first proposed by Robbins and Monro in 1951 for root- finding problems, have been widely used in the literature to solve problems arising from stochastic convex optimization, stochastic Nash games and more recently stochastic variational inequalities. Several …
-
Adaptive algorithms for online learning in non-stationary environments
… complexity for group distributionally robust optimization (GDRO) and novel data-dependent best-of-both-worlds regret upper bounds for multi-armed bandits. In summary, this thesis provides mathematically-grounded adaptive algorithms that achieve state-of-the-art performance guarantees in …