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 43 for “"Distribution Shifts"”.
-
Building Reliable AI under Distribution Shifts
… deployed in real-world settings where distribution shifts—differences between training and deployment data—can significantly impact their reliability. These shifts affect models in multiple ways, leading to degraded generalization, fairness collapse, loss of robustness, and new safety …
-
Reliable and efficient machine learning under distribution shifts
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-12-01
-
TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE
… and unreliability when processing inputs under distribution shifts. This thesis systematically studies the robustness to distribution shifts for ML models from a data-centric perspective. First, we closely examine the effect of low-quality data on model generalization. We theoretically show that …
-
Distribution Shifts and Declines in Autonomous Consumption: A Great Recipe for a Great Recession
… Great Depression: the dramatic shift in income distribution and the sudden drop in autonomous (or wealth-based) consumption. Accordingly the present study examines first, the role of income distribution shifts to demonstrate the fact that such a shift placed a significantly larger share of U.S. …
-
Topics in offline statistical reinforcement learning: addressing challenges in continuous actions, distribution shifts, and unmeasured confounding
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-08-01
-
Exploring Fisheries Species Distribution Shifts in Response to Freshwater Inflow Through the Bonnet Carré Spillway Using Species Distribution Models
… of seasonal Maximum Entropy (MaxEnt) species distribution models are constructed, validated, and performance-assessed to explore how BCS openings might affect <em>Brevoortia patronus</em>, <em>Cynoscion nebulosus</em>, and <em>Farfantepenaeus aztecus</em> in the space of the MSS and …
-
Probing, Improving, and Verifying Machine Learning Model Robustness
… models turn out to be brittle when faced with distribution shifts, making them hard to rely on in real-world deployment. This motivates developing methods that enable us to detect and alleviate such model brittleness, as well as to verify that our models indeed meet desired robustness …
-
Robust Inference via Optimal Transport Ambiguity Sets
… driving. This challenge is exacerbated by distribution shift, in which the true data–generating distribution diverges from the nominal distribution on which our statistical methods were trained. In this thesis, we formalize distribution shifts via ambiguity sets—metric neighborhoods in the …
-
Controlled training data generation with diffusion models
… the model, they are not informed of the target distribution, which can be inefficient. Therefore, we introduce the second feedback mechanism that guides the generation process towards a certain target distribution. We call the method combining these two mechanisms Guided Adversarial Prompts. We …
-
Uncertainty-aware learning from sparse, unlabelled, and out-of-distribution time series
… exhibit limited generalisability under out-of-distribution conditions, which arise due to heterogeneity across hospitals, sensors, and patient populations. Such factors limit the use of real-world time series in deep learning applications, and are consequential in healthcare as unreliable …
-
Heterogeneous machine learning with decentralized data
… data, where multiple clients with distinct data distributions jointly train or adapt machine learning models under the coordination of a central server. Throughout the process, clients’ private data never leave their local devices. This paradigm underlies numerous real-world applications, such as …
-
Impacts of climate driven range changes on the genetics and morphology of butterflies
… responses of butterflies to climate induced distribution shifts in terms of patterns of genetic diversity at expanding and contracting range margins, the relative importance of genes versus environment on adaptations to dispersal and local adaptation to temperature during range expansion. …
-
Transfer learning and robustness for natural language processing
… low-resource tasks/datasets and unseen data with distribution shifts imposes great challenges to the reliability of NLP models and prevent them from being massively applied in the wild. This dissertation aims to address these two issues.
-
Data Acquisition for Domain Adaptation of Closed-Box Models
… as closed boxes, but they may suffer from distribution shifts in new domains. Prior techniques cannot address this problem, because they are either impractical to use or against the property of closed-box models. Instead, we propose to acquire extra data to construct a "padding" model to …
-
Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
Distribution shift is a major source of failure for machine learning models. However, evaluating model reliability under distribution shift can be challenging, especially since it may be difficult to acquire counterfactual examples that exhibit a specified shift. In this work, we introduce the …
-
A Variational Lower Bound to Mitigate Batch Effect in Molecular Representations
… a versatile framework and resolves general distribution shifts and issues of data fairness by minimizing correlation with spurious features or removing sensitive attributes.
-
Trustworthy transfer learning
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms
-
Robust Flight Navigation with Liquid Neural Networks
… beyond their training environment under drastic distribution shifts. To this end, we design an imitation learning framework utilizing liquid neural networks, a brain-inspired class of continuous-time neural models that are causal and adapt to changing conditions. We observe that liquid agents …
-
Towards Out-of-distribution Problem for Reinforcement Learning
… from the curse of dimensionality and poor out-of-distribution generalization of current probabilistic models. Current machine learning models requires data points to be independently identically distributed which is often not satisfied in real-world applications. This mismatch damages the direct …
-
El problema de la generalización de los algoritmos de aprendizaje profundo para el análisis de imagen médica: investigación utilizando imágenes radiográficas
… datos, dando lugar a lo que se ha denominado distribution shifts (DS).
Page 1 of 3