arXiv subjects

Jericho Cain

Publications and source records attributed to Jericho Cain.

7 recordsLinked to original sources

arXiv2026

Gauge Freedom and Metric Dependence in Neural Representation Spaces

Neural network representations are often analyzed as vectors in a fixed Euclidean space. However, their coordinates are not uniquely defined. If a hidden representation is transformed by an invertible linear map, the network function can be preserved by applying the inverse transformation to downstream weights. Representations are therefore defined only up to invertible linear transformations. We study neural representation spaces from this geometric viewpoint and treat them as vector spaces with a gauge freedom under the general linear group. Within this framework, commonly used similarity measures such as cosine similarity become metric-dependent quantities whose values can change under coordinate transformations that leave the model function unchanged. This provides a common interpretation for several observations in the literature, including cosine-similarity instability, anisotropy in embedding spaces, and the appeal of representation comparison methods such as SVCCA and CKA. Experiments on multilayer perceptrons and convolutional networks confirm that inserting invertible transformations into trained models can substantially distort cosine similarity and nearest-neighbor structure while leaving predictions unchanged. These results indicate that analysis of neural representations should focus either on quantities that are invariant under this gauge freedom or on explicitly chosen canonical coordinates.

cs.LG↗

arXiv2026

Global Structure in Learned Latent Representations of Confusion-Limited LISA Data

Machine learning methods in gravitational wave data analyses depend on the choice of representation and on how structure within that representation is used. Building on previous work using continuous wavelet transform (CWT) autoencoder representations for confusion-limited LISA simulation, we investigate whether source resolvability information is better characterized by local latent geometry or by global latent density. We study this question in a controlled benchmark with data generation and preprocessing held fixed. Using CWT representations of synthetic confusion-limited LISA segments, we compare geometry based one-class scoring with likelihood-based latent models along with their morphology augmented variants. Likelihood-based scoring consistently outperforms local manifold-distance methods across three independent seeds, achieving ROC-AUC $0.8555 \pm 0.0181$ and PR-AUC $0.9219\pm 0.0118$, compared with ROC-AUC $0.7663\pm 0.0450$ and PR-AUC $0.8667\pm 0.0255$ for the geometry baseline. These results suggest that resolvability information in learned latent representations is not fully captured by local latent geometry but instead reflects global properties of the latent distribution. More broadly, this work contributes to representation-aware methods for confusion-foreground characterization in LISA and motivates future studies of coordinate invariance and intrinsic geometry in learned latent spaces.

gr-qc↗

arXiv2026

Detectability Scaling Laws for Environmental Phase Modulation in Gravitational-Wave Signals

Environmental effects such as hierarchical triple motion can introduce cumulative phase modulation in gravitational-wave signals through time-dependent line-of-sight acceleration. Whether such smooth time-warp distortions are observable depends jointly on deformation strength and signal-to-noise ratio (SNR), yet this relationship has not been quantified in a template-free framework. We study the detectability of these distortions using time-frequency representations derived from the continuous wavelet transform. Instead of reconstruction error alone, we analyze trajectory-level statistics, in particular the evolution of the power-weighted frequency centroid. We find that environmental modulation can be detected using a single-sample statistic referenced to an isolated-binary distribution, without requiring matched templates. Across a grid of cumulative phase distortions and SNR, detection performance collapses onto a single scaling parameter defined as Lambda = Delta phi x SNR. The ROC-AUC follows an approximately sigmoid transition in this parameter. Moderate distortions are detectable even at low SNR, whereas smaller distortions require higher SNR. These results indicate that smooth environmental phase modulation is not generically absorbed by intrinsic waveform variability; instead, detectability is governed by a simple scaling between cumulative phase distortion and signal strength.

gr-qc↗

arXiv2026

Signal Decomposition Reveals Structure in Insider Threat Detection under Sparse Temporal Data

Insider threat detection is difficult because malicious behavior is rare, irregular, and buried in long periods of inactivity. In enterprise audit data, most windows contain little activity, while attacks appear intermittently and range from brief events to sustained campaigns. Standard reconstruction-based models are therefore dominated by inactive regions and tend to learn baseline behavior rather than meaningful deviations. We separate activity presence from magnitude. Each window is decomposed into a binary mask indicating whether activity occurs and a value matrix capturing its intensity. A dual-channel autoencoder reconstructs both, with value loss applied only where activity is present, directing learning toward sparse structure. Using the CERT r5.2 dataset as a controlled setting, we examine how anomaly signal changes with temporal configuration. Short attacks are detected mainly through presence; longer attacks introduce a magnitude component; noise degrades magnitude reliability and shifts detection back toward presence. The balance between channels is not fixed and follows the data. At the campaign level, signal concentrates in a small number of anomalous windows. Simple aggregation that emphasizes extreme scores is sufficient to recover extended activity without explicit sequence modeling. Effective detection depends less on model complexity and more on aligning representation and objective with sparse temporal structure.

cs.CR↗

arXiv2025

Manifold Learning for Source Separation in Confusion-Limited Gravitational-Wave Data

The Laser Interferometer Space Antenna (LISA) will observe gravitational waves in a regime that differs sharply from what ground-based detectors such as LIGO handle. Instead of searching for rare signals buried in loud instrumental noise, LISA's main challenge is that its data stream contains millions of unresolved galactic binaries. These blend into a confusion background, and the task becomes identifying sources that stand out from that signal population. We explore whether manifold-learning tools can help with this separation problem. We built a CNN autoencoder trained on the confusion background and used its reconstruction error, while also taking advantage of geometric structure in the latent space by adding a manifold-based normalization term to the anomaly score. The model was trained on synthetic LISA data with instrumental noise and confusion background, and tested on datasets with injected resolvable sources such as massive black hole binaries, extreme mass ratio inspirals, and individual galactic binaries. A grid search over $\alpha$ and $\beta$ in the combined score $\alpha \cdot \mathrm{AE}_{\mathrm{error}} + \beta \cdot \mathrm{manifold}_{\mathrm{norm}}$ found optimal performance near $\alpha = 0.5$ and $\beta = 2.0$, indicating that latent-space geometry provides more discriminatory information than reconstruction error alone. With this combination, the method achieves an AUC of $0.752$, precision $0.81$, and recall $0.61$, a $35\%$ improvement over the autoencoder alone. These results suggest that manifold-learning techniques could complement LISA data-analysis pipelines in identifying resolvable sources within confusion-limited data.

physics.gen-ph↗

arXiv2025

Template-Free Gravitational Wave Detection with CWT-LSTM Autoencoders: A Case Study of Run-Dependent Calibration Effects in LIGO Data

Gravitational wave detection requires sophisticated signal processing to identify weak astrophysical signals buried in instrumental noise. Traditional matched filtering approaches face computational challenges with diverse signal morphologies and non-stationary noise. This work presents an unsupervised deep learning methodology integrating CWT preprocessing with LSTM autoencoder architecture for template-free gravitational wave detection. The CWT time-frequency decomposition captures chirp evolution and transient characteristics essential for compact binary coalescence identification. We train and evaluate our model on LIGO H1 data comprising of detector noise and confirmed gravitational wave events from the GWTC-4.0 catalog. During development, we discovered that reconstruction errors from multi-run training (O1-O4) clustered by observing run rather than astrophysical parameters, revealing systematic batch effects from GWOSC's evolving calibration procedures. We adopted single-run (O4) training, which eliminated these batch effects and improved recall from 52% to 96% while maintaining 97% precision. The final model achieves strong performance on O4 test data: 97.0% precision, 96.1% recall, and ROC-AUC 0.994 (102 signals, 399 noise segments). The reconstruction error distribution shows clean unimodal separation between noise (mean 0.48) and signals (mean 0.77), with only 4 missed detections and 3 false alarms. This unsupervised, template-free approach demonstrates that anomaly detection can achieve performance competitive with supervised methods. While the template-free nature of this approach suggests sensitivity to signals outside existing template banks, this capability remains to be validated. Our identification and resolution of cross-run batch effects provides methodological guidance for future machine learning applications to multi-epoch gravitational wave datasets.

astro-ph.IM↗

arXiv2024

Anomaly Detection in OKTA Logs using Autoencoders

Okta logs are used today to detect cybersecurity events using various rule-based models with restricted look back periods. These functions have limitations, such as a limited retrospective analysis, a predefined rule set, and susceptibility to generating false positives. To address this, we adopt unsupervised techniques, specifically employing autoencoders. To properly use an autoencoder, we need to transform and simplify the complexity of the log data we receive from our users. This transformed and filtered data is then fed into the autoencoder, and the output is evaluated.

cs.LG↗