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 12 of 12 for “"Theoretical machine learning"”.
-
Market making through reinforcement learning and Wasserstein DRO : an entropy-regularized approach
… making by integrating advanced methods from theoretical machine learning. The first part introduces essential tools in modern machine learning, including reinforcement learning and Wasserstein distributionally robust optimization (DRO), along with background on classical market making …
-
Generalization bounds and size generalization for graph neural networks
Graph neural networks (GNNs) are a class of machine learning models that relax the independent and identically distributed (i.i.d.) assumption between data points that underlies most machine learning models. Theoretical understanding of these models involves analyzing generalization bounds, a …
-
PROVABLE AND PRACTICAL ALGORITHMS FOR NON-CONVEX PROBLEMS IN MACHINE LEARNING
Machine learning has become one of the most exciting research areas in the world, with various applications. However, there exists a noticeable gap between theory and practice. On one hand, a simple algorithm like stochastic gradient descent (SGD) works very well in practice, without satisfactory …
-
Contributions to Unsupervised and Semi-Supervised Learning
This thesis studies two problems in theoretical machine learning. The first part of the thesis investigates the statistical stability of clustering algorithms. In the second part, we study the relative advantage of having unlabeled data in classification problems. Clustering stability was proposed …
-
ONLINE LEARNING, UNIFORM CONVERGENCE, AND A THEORY OF INTERPRETABILITY
This doctoral thesis covers various aspects of theoretical machine learning relative to two of its most fundamental paradigms: batch learning and online learning. In particular, we address the role of feedback models for multiple online learning problems, the sample complexity for uniform …
-
Practical learning in a private and noisy world
This thesis studies two fundamental settings in theoretical machine learning where worst-case formulations impose sharp computational hardness barriers: learning under privacy constraints and learning under noise. In both settings, we show that carefully chosen relaxations of the standard models, …
-
Active learning under the Bernstein condition for general losses
We study online active learning under the Bernstein condition for bounded general losses and offer a solution for online variance estimation. Our suggested algorithm is based on IWAL (Importance Weighted Active Learning) which utilizes the online variance estimation technique to shrink the …
-
On the theory of Lipschitz continuous machine learning
<p>The field of machine learning theory plays an essential role in establishing the mathematical foundations and performance boundaries of data-driven modelling techniques. By providing a rigorous analysis of the underlying properties of an algorithm, theoretical machine learning guides the …
-
A METHODOLOGY FOR MODELING EMERGENCE IN COMPLEX SYSTEMS
… At the same time, rapid new developments in machine learning (ML) have allowed a sea change in extracting information from disparate datasets to make useful for human decision-making. This dissertation develops and studies novel ML methods to understand the emergent properties of complex …
-
Efficient algorithms for distributed learning, optimization and belief systems over networks
… system is composed of independent agents, machines, processing units, etc., where interactions between them are usually constrained by a network structure. In contrast to centralized approaches where all information and computation resources are available at a single location, agents on a …
-
Algorithmic approaches for efficiency and explainability in learning problems
… the development of supervised and unsupervised machine learning algorithms with an emphasis on two fundamental aspects: computational efficiency and explainability. The need for efficient and explainable models is particularly crucial in high-stakes domains such as healthcare, education, and …
-
Advanced neural network methods for atomistic materials chemistry
Machine learned force fields (MLFFs) are functions trained to map the positions of atoms within a material or molecule to the potential energy and atomic forces generated by expensive, quantum-mechanical calculations. Their high accuracy and low cost are enabling faithful simulations of matter at …