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 20 of 25 for “"Online convex optimization"”.
-
Generalized implicit online convex optimization
Online learning is a setting where the learner receives an arbitrary sequence of loss functions, selects points before knowing the loss functions, and is evaluated on the values of the loss functions on the points it selects. The goal is to minimize the regret, which is the difference between the …
-
An Online Convex Optimization Approach for Network Slicing
… policy. This work explores the application of online convex optimization (OCO) in network slicing, leveraging its adaptive nature for real-time decision-making in time-variant costs and dynamic network conditions. Emphasis is placed on optimizing resource allocation for communication and …
-
Online convex optimization and its application to online portfolio selection
… and need to be understood and processed quickly. Online learning is concerned with the task of making decisions on-the-fly as observations are received. Online learning has attracted a lot of attention due to the recent emergence of large-scale applications such as online web advertisement …
-
Advances in online convex optimization, games, and problems with bandit feedback
… sequential decision making through the lens of Online Learning. Online Learning is a very powerful and general framework for multi-period decision making. Due to its simple formulation and effectiveness it has become a tool of daily use in multibillion companies. Moreover, due to its beautiful …
-
Unconstrained online convex optimization: regularization in the adversarial setting and beyond
… can be resolved simultaneously: we develop online convex optimization algorithms on an unconstrained domain that adapt to the unknown problem scale while operating under inexact gradient feedback. We consider two models of gradient inexactness: a stochastic model, where each gradient is …
-
Online Convex Optimization in Changing Environments and its Application to Resource Allocation
… on-the-fly in order to capture the changes. Online Convex Optimization (OCO) is a popular framework that matches the above sequential data processing requirement. Applications using OCO include online routing, online auctions, online classification and regression, as well as online resource …
-
DISTRIBUTED AND DELAYED ONLINE LEARNING
… design and analysis of distributed and delayed online learning algorithms. First, we introduce delayed online learning, where model updates rely on feedback arriving with variable delays. We study the online learning problem with curved losses and delayed feedback, designing algorithms that …
-
Online Optimization for Demand Response
… uncertainty of loads. In this thesis, we design online optimization-based algorithms for demand response. Using the performance-guaranteed frameworks we develop, we can utilize flexible loads for demand response in real-time while accounting for uncertainty. We first design online convex …
-
Improving Online Mirror Descent for Convex Optimization in Dynamic Environments
… cost functions vary over time. For example, in online machine learning, data samples arrive dynamically, so that the learning model is progressively updated. It is difficult to capture such dynamics in an offline setting, while online optimization techniques naturally accommodate unpredictable …
-
Online algorithm design via smoothing with application to online experiment selection
… three topics, namely, the design and analysis of online convex optimization algorithms, convergence rate analysis of proximal gradient homotopy algorithm for structured convex problems, and application of computational methods for study of brain cells in the visual cortex of the primate brain. In …
-
Sequential Decision Making at Scale: Theory and Applications
This thesis bridges the gap between traditional online optimization and adjacent decision-making literatures to solve complex resource allocation problems in large-scale systems. Novel methodologies are introduced by integrating stochastic optimal control, spectral perturbation analysis, …
-
Regret bounds without Lipschitz continuity : online learning with relative-Lipschitz losses
Online convex optimization (OCO) is a powerful algorithmic framework that has extensive applications in different areas. Regret is a commonly-used measurement for the performance of algorithms in this framework. Lipschitz continuity of the cost functions is commonly assumed in order to obtain …
-
Towards new perspectives on stochastic optimization: bridging theory and practice
Optimization theory is a cornerstone of machine learning. At the core of training deep neural networks lies the optimization of a loss function. However, despite the success of widely-used empirical optimizers and advancements in theoretical frameworks, a notable gap between theory and practice …
-
Temporal aspects of adaptive online learning: continuity and representation
Adaptive online learning, in a very broad sense, is the study of sequential decision making beyond the worst case. Compared to their classical minimax counterparts, adaptive algorithms typically require less manual tuning, while provably performing better in benign environments, or with prior …
-
On Safety in Sequential Decision Learning
… safety, we develop the SO-PGD algorithm for online convex optimization, which maintains linear safety constraints using only noisy feedback. The algorithm achieves sublinear regret while ensuring constraint satisfaction, with extensions to multi-agent scenarios and certain non-convex …
-
Exploiting smoothness in statistical learning, sequential prediction, and stochastic optimization
… several years, the intimate connection between convex optimization and learning problems, in both statistical and sequential frameworks, has shifted the focus of algorithmic machine learning to examine this interplay. In particular, on one hand, this intertwinement brings forward new challenges …
-
Probabilistic design in the operation of service systems
… practicality and insights. Chapter 3 studies an online convex optimization problem where the decision variable is a probability measure, motivated by matching spatial supply with demand in a geographical setting. Using optimal transport theory, we propose an online Wasserstein gradient descent …
-
Fast algorithms for Bayesian variable selection
… to be loaded into computer memory. We propose an online algorithm for the logistic regression, under the framework of online convex optimization. Our algorithm is fast, and achieves similar accuracy (log-loss) as the state-of-art algorithm (Follow-the-Regularized-Proximal algorithm).
-
Online Learning and Optimization in Communication Networks
In this thesis, I propose new online learning and optimization approaches to evaluate and design communication networks by investigating unknown system variation, feedback delay, and communication efficiency over time. The results of this thesis provide new analytical insights and design guidelines …
-
Fast algorithms for minimally supervised learning
… design. Building on regret minimization and online convex optimization, we derive near-optimal guarantees for A-, D-, E-, V-, and G-optimal objectives. Using matrix inequalities and spectral arguments, including applications of the Golden--Thompson inequality, we establish performance bounds …
Page 1 of 2