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 19 of 19 for “"Spurious Correlations"”.
-
Towards externally valid machine learning: A spurious correlations perspective
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01
-
TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE
Machine learning (ML) models often rely on spurious correlations in the training data, leading to performance degradation and unreliability when processing inputs under distribution shifts. This thesis systematically studies the robustness to distribution shifts for ML models from a data-centric …
-
Rewriting the Rules of a Classifier
… existing classes to unseen variants, identify spurious correlations present in the dataset, mitigate the effects of spurious correlations, and introduce new classes. We find that our technique reduces the need for: computing resources, because we only re-train a single layer’s weights; new …
-
Towards Understanding Human-aligned Neural Representation in the Presence of Confounding Variables
… This solution is more likely to pick up on spurious features and low-level statistical patterns in the train data rather than semantic features and highlevel abstractions, resulting in poor Out-of-Distribution (OOD) performance. In this project we aim to broaden the current knowledge …
-
Learning Causal Representations for Generalization and Adaptation in Supervised, Imitation, and Reinforcement Learning
… generalization in supervised learning. Due to spurious correlations, predictive models often fail to generalize to environments whose distributions differ from the ones used at training time. To this end, we propose a framework, with theoretical guarantees under rather general assumptions over …
-
Compositions, logratios and geostatistics: An application to iron ore
… has occurred and this can be shown to produce spurious correlations. Compositional geostatistics is an approach developed to ensure that the constant sum constraint is respected in estimation while removing dependencies on the spurious correlations. This study tests the applicability of this …
-
Explanation Alignment: Quantifying the Correctness of Model Reasoning At Scale
… explanation alignment automatically identifies spurious correlations, such as model bias, and uncovers behavioral differences between nearly identical models. Further, we characterize the relationship between explanation alignment and model performance, evaluating the factors that impact …
-
DOMAIN KNOWLEDGE-GUIDED LEARNING FOR ROBUST MYOCARDIAL INFARCTION DETECTION FROM 12-LEAD ELECTROCARDIOGRAMS
… is trained on biased datasets, it may rely on spurious correlations associated with age rather than learning MI-relevant features. Third, prior work primarily addresses MI detection, stage classification, and localisation as separate tasks, while rarely integrating all three within a unified …
-
Gradient Subgroup Scanning for Distributionally and Outlier Robust Models
… certain subgroups, especially when there exist spurious correlations between the input data and label. Previous approaches for reducing the discrepancy between average and worst-group accuracies typically require expensive known subgroup annotations for either every training data point (as is …
-
Analysing and Mitigating Classification Bias for Text-based Foundation Models
… particularly regarding their susceptibility to spurious correlations and implicit model bias. This thesis analyses the forms of bias and spurious correlations that are present when NLP foundation models are applied to text classification tasks. We analyse particular biases present in the …
-
Phylogenetic Signals in Protein Data
… noise which is also one that is often ignored: spurious correlations induced by phylogeny. To this end, we introduce a novel method for disentangling phylogenetic noise from the relevant structural signals. This method is grounded in an extension to a well-known theorem in Random Matrix Theory. …
-
Graph Representation Learning for Drug Discovery
… regularization, which seeks to eliminate spurious correlations in biological assays. Second, we extend property prediction capabilities to combinations of molecules, enabling us to screen and discover synergistic drug therapies. Direct experimental data about combinations are extremely …
-
Relevance learning for redundant features
… settings where redundant factors are likely and spurious correlations exist.<br /><br /> Basing decisions about causal elements on feature selection is therefore inaccurate or wrong when not considering the presence of redundant but also relevant features. Most existing selection algorithms are …
-
Building Reliable AI under Distribution Shifts
… that contextual reasoning can help mitigate spurious correlations and improve robustness under domain shifts. We also assess the reliability of AI-generated content, revealing how image watermarks, designed for provenance tracking, often fail when subjected to real-world distortions and …
-
Transparent Analysis of Multi-Modal Embeddings
… the ambiguity of intrinsic evaluations and the spurious correlations of downstream results, creating more transparent and human interpretable models is necessary. This thesis proposes diverse studies to scrutinize the inner "cognitive models" of Embeddings, trained on various data sources and …
-
Three essays in corporate finance
… level. To disentangle investors' effects from spurious correlations, I employ a widely-adopted identification strategy based on the discontinuity in long-term ownerships around Russell 1000/2000 index thresholds. The effects are strongest among firms with more undervaluation. I also document a …
-
Hypothesis testing and causal inference with heterogeneous medical data
… data with only few observed samples, biases and spurious correlations are prevalent. These are called spurious because they do not contribute to the effect being studied. In this context, the modelling assumptions of existing statistical tests and causal inference methods are often found …
-
Efficient invariant feature subspace recovery for domain generalization
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Representation Learning Based Causal Inference in Observational Studies
… between treatment groups and (ii) to attenuate spurious correlations in training data to derive valid causal conclusions that generalize. By incorporating ideas from representation learning, adversarial matching, generative causal estimation, and invariant risk modeling, this dissertation …