CORTEXA
← Browse
arxivcs.LGcs.CE2026-07-01

Interpretable vs Learned Encoders for High-Cardinality Fraud Detection

Xiao Han, Jingjing Liu, Moxuan Zheng, Zhen Zhang, Chenyu Wu

A total of seven categorical encoding methods were tested on the IEEE-CIS fraud benchmark dataset (590,540 records, 3.5% positives, 8 high-cardinality columns). The encoders were evaluated using a stratified 5-fold cross-validation (CV) with three repetitions. Five of the encoders had identical frozen LightGBM learners in the downstream phase, allowing for controlled comparisons of their performance to each other. CatBoost and TabNet were included as comparisons across paradigms using different learners. The entity embeddings produced the highest AUC-ROC (0.9612), with a statistically significant tie with that of CatBoost (0.9602) and statistically superior to tier group encoding (0.9548), whereas target encoding was only 0.0023 worse than tier group encoding and the auditor-friendly tier boundaries were maintained. Off-the-shelf TabNet did not outperform tree-based pipelines and collapsed under data scarcity. On AUC-PR, CatBoost leads (0.822 vs. 0.793); no encoder dominated both metrics. Per-column analysis confirmed the embedding advantage arises from joint multi-column representation.

View free PDFSource page

Related papers

arxivcs.ARcs.CEcs.ETcs.LGphysics.app-ph2026-07-29

Investigating reservoir computing for branch predictionin pipelined processors using emerging CMOS memristor devices

Harvey Samuel George Johnson, Sendy Phang

This project aimed to develop a novel reservoir compute (RC) implementation framework targeting high-speed operation and integration with CMOS digital logic. With the target workload of branch prediction (BP) for multistage pipelined central pro-cessing unit (CPU) cores. For this…

View free PDFSource page
arxivcs.LGstat.ML2026-07-23

Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design

Martin Anthony, Kaveh Salehzadeh Nobari

An initial high-recall stage in an empirical pipeline decides which items pass to later review, labelling, or modelling, and relevant items it misses are lost to every subsequent stage. We study how many audit labels are needed to certify, with finite-sample validity, that this m…

View free PDFSource page
arxivcs.LGcs.AIstat.ML2026-07-23

Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks

Hossein Mobahi, Peter L. Bartlett

Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression, network compression offers a promising lens to analyze this knowledge. However, standard compression heuristics of…

View free PDFSource page
arxivcs.ROcs.AIcs.LG2026-07-22

Emergent Compositional Skills in Mixture-of-Experts VLAs

Shlok Shah, Rhiaan Jhaveri, Tharun Kumar Tiruppali Kalidoss, Chirayu Nimonkar, Ishaan Javali

We consider the problem of learning compositional robot policies end-to-end from expert demonstrations, without any pre-specified notion of task decomposition or hierarchy. We ask whether a VLA trained with a simplified Mixture-of-Experts (MoE) action head can emergently learn to…

View free PDFSource page
arxivcs.CVcs.LG2026-07-24

Bowel Obstruction Detection and Localization on Abdominal CT with Deep Learning

Moritz Vandenhirtz, Andrea Agostini, Dana Belde, Mélanie Roschewitz, Ismaiel Chikh Bakri, Tilo Niemann, et al.

Bowel obstruction is a common and potentially life-threatening gastrointestinal condition. In the face of rising diagnostic workloads, the automated diagnosis of bowel obstruction on CT scans supports radiologists by accelerating detection and improving patient outcomes. In this…

View free PDFSource page
arxivcs.LG2026-07-31

Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification

Anders Jonsson, Emilie Kaufmann, Gianmarco Tedeschi, Lorenzo Steccanella

We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel. HBPI-UCRL exploits the fact that a high-level transition corresponds to a multi-step transition at the low level. We introduce tw…

View free PDFSource page