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 17 of 17 for “"Constrained Learning"”.
-
Constrained Learning And Inference
Data and learning have become core components of the information processing and autonomous systems upon which we increasingly rely on to select job applicants, analyze medical data, and drive cars. As these systems become ubiquitous, so does the need to curtail their behavior. Left untethered, they …
-
Geospatial Understanding of Foundation Models: Self-Supervision, Robustness, and Resource-Constrained Learning
… a 1% improvement. Finally, to enable resource-constrained learning, we introduce Hierarchical Attention Dis- tillation (HAD), a pretraining paradigm that transfers spatial and semantic representations from a large teacher foundation model to a compact student via multi-level attention across …
-
Constrained learning in the bandit setting: doubly optimistic strategies and fast rates
… that is faster than existing results. For the constrained multi-armed bandit problem, we achieve logarithmic regret for both the reward and safety risk; for linear and generalized linear bandit settings, we carry out a dual analysis based on linear programming sensitivity, identify the …
-
Physics-Constrained Learning for Scientific Discovery: Inference in Differential Equations and Inverse Design via Generative Models
… discovery increasingly relies on machine learning (ML), but many scientific problems involve sparse data, physical constraints, and large combinatorial search spaces. In these regimes, ML can suffer from generalization and robustness issues, including generating outputs that violate …
-
LEARNING WITH POINTWISE CONSTRAINTS
… implications, it becomes necessary to develop learning frameworks that express requirements with finer granularity than an expected risk. This dissertation addresses this issue through the study of pointwise constrained learning. The central premise is that many learning requirements are better …
-
Regional Learning Opportunities : A Story of Place-Based Learning Among Adults in West Virginia
Place-based learning has been shown to be effective for use with traditional-aged students, but not much research has been conducted to connect the use of place-based learning with adults, particularly in rural areas of Appalachia. Because of the lack of information concerning this topic, a …
-
Learning with classical and quantum information constraints
… for proving the fundamental limit of information-constrained learning and designs sample-optimal algorithms under settings of practical interest. We consider various information constraints, including privacy and communication constraints on classical computers, and inherent randomness governed by …
-
GRAPH NEURAL NETWORKS FOR COMMUNICATION IN MULTI-AGENT SYSTEMS
… channel conditions and formulate it as a constrained learning problem. We propose a novel State Augmentation strategy to achieve faster convergence and achieve decentralized implementation using GNNs. The state augmentation based optimization framework leverages graph convolutions to …
-
Child Development Theory as a Mediator of Novice Teachers' Ethnotheories to Increase Learning and Justice in the Classroom
… as a mediator of classroom practice to increase learning and justice in diverse educational contexts (Daiute, 2014). I found that the unconscious use of ethnotheories reproduced injustice by subordinating children's needs to teacher's experiences and constrained learning through silencing, …
-
The Impact of Instructors’ Assessment Design on Undergraduate Student Motivation and Learning Approach within STEM Problem-Solving Learning Environments
… of PS skills is an important aspect of student learning in STEM undergraduate programs, typically assessed via test-based assessments. Students will adapt their learning approach based on how they perceive assessment and therefore may not always employ effective PS approaches. This thesis …
-
A study of object creators in JavaScript
… objects. In JavaScript, object behaviour is less constrained. Learning how JavaScript programmers create objects can help us understand whether the programmers employ the notion of ``classes'', like those in Java, in JavaScript. In other words, we are trying to compare the creation of objects in …
-
ONLINE DECISION MAKING WITH UNKNOWN CONSTRAINTS
… concerns have arisen with the growth of machine learning, necessitating mitigation efforts to ensure algorithms adhere to trustworthiness standards. In this dissertation, we study problems where safety constraints are potentially unknown and are strictly enforced. In the first part of the …
-
Learning Optimal Resource Allocations In Wireless Systems
The goal of this thesis is to develop a learning framework for solving resource allocation problems in wireless systems. Resource allocation problems are as widespread as they are challenging to solve, in part due to the limitations in finding accurate models for these complex systems. While both …
-
Machine Learning and Quantum Computing for Optimization Problems in Power Systems
… many optimization problems such as security-constrained unit commitment, economic dispatch, optimal power flow, optimal planning, etc. Although traditional optimization solvers and software have been successful so far in solving these problems, there is a growing need to accelerate the …
-
Pessimistic-Optimistic Bandit Learning with Applications to Communication Networks
… approach to solving extensions to constrained bandit learning, motivated by various communication network and other resource allocation applications. In particular, we study the cases where feedback is delayed, the case where there is a cost to switching bandit arms, and the case of …
-
Novel neural architectures & algorithms for efficient inference
In the last decade, the machine learning universe embraced deep neural networks (DNNs) wholeheartedly with the advent of neural architectures such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), transformers, etc. These models have empowered many applications, such as …
-
Knowing Who to Trust and What to Believe in the Presence of Conflicting Information
… trust decision via the Generalized and Constrained Fact-Finding frameworks while still maintaining the relative simplicity and tractability of standard fact-finders. Ultimately, we introduce Latent Trust Analysis, a new type of probabilistic trust model that provides the first strongly …