arXiv subjects

Jeanie Schreiber

Publications and source records attributed to Jeanie Schreiber.

3 recordsLinked to original sources

arXiv2026

Topology of Shape and Data in Material Microstructures

One of the challenges in microstructure analysis is the rigorous quantification of the shape, size, and spatial arrangement of the microstructure beyond comparison of average values. We expound on formal principles combining Topological Data Analysis (TDA) and non-Euclidean distances between curves to motivate novel perspectives on the form and nature of pattern and shape in images. Specifically, TDA descriptors extracting persistent topological structures are combined with product submanifold learning of separable shape tensors (SST) to offer unique insights about electron backscatter diffraction (EBSD) images of material microstructures through the lens of a dual-parameter filtration. Beyond standard approaches, our methodology highlights how different choices or permutations of shape distances can lead to distinct notions of topological persistence, thereby broadening the interpretive scope of TDA. The resulting visualizations of feature extraction are designed to be both principled and explanatory, offering novel tools for modern imaging science with applications to material metrology. More broadly, this framework has strong potential to impact domains where precise quantification of topology and shape is critical for uncovering fundamental image patterns and features, and enables additional data-driven tools for microstructure analysis.

cond-mat.mtrl-sci↗

arXiv2026

Orthogonal Dendritic Intrinsic Networks: An Architecture for Significance-Ordered, Orthogonal Latent Spaces

Principal Component Analysis or PCA-like properties (orthogonality, variance ranking) are seldom realized in deep autoencoder architectures. In this work, we present ODIN (Orthogonal Dendritic Intrinsic Network), a novel autoencoder architecture that recovers PCA-like latent structure in a fully non-linear regime. By incorporating a set of geometric constraints directly into the training objective, ODIN encourages latent dimensions to be mutually orthogonal and ordered by explained variance, mirroring the interpretable decomposition of PCA while retaining the expressive power of deep networks. We provide theoretical grounding for these constraints and demonstrate their compatibility with standard encoder-decoder frameworks. We also establish empirical results for both synthetic and real world datasets, establishing a principled path toward interpretable, structured feature learning and dimensionality reduction.

cs.LG↗

arXiv2023

On-Manifold Projected Gradient Descent

This work provides a computable, direct, and mathematically rigorous approximation to the differential geometry of class manifolds for high-dimensional data, along with nonlinear projections from input space onto these class manifolds. The tools are applied to the setting of neural network image classifiers, where we generate novel, on-manifold data samples, and implement a projected gradient descent algorithm for on-manifold adversarial training. The susceptibility of neural networks (NNs) to adversarial attack highlights the brittle nature of NN decision boundaries in input space. Introducing adversarial examples during training has been shown to reduce the susceptibility of NNs to adversarial attack; however, it has also been shown to reduce the accuracy of the classifier if the examples are not valid examples for that class. Realistic "on-manifold" examples have been previously generated from class manifolds in the latent of an autoencoder. Our work explores these phenomena in a geometric and computational setting that is much closer to the raw, high-dimensional input space than can be provided by VAE or other black box dimensionality reductions. We employ conformally invariant diffusion maps (CIDM) to approximate class manifolds in diffusion coordinates, and develop the Nyström projection to project novel points onto class manifolds in this setting. On top of the manifold approximation, we leverage the spectral exterior calculus (SEC) to determine geometric quantities such as tangent vectors of the manifold. We use these tools to obtain adversarial examples that reside on a class manifold, yet fool a classifier. These misclassifications then become explainable in terms of human-understandable manipulations within the data, by expressing the on-manifold adversary in the semantic basis on the manifold.

cs.LG↗