7 citations · 20 across the 12 of their papers we have counts for
15 papers
The Blind Spot Paradox: When Adaptive Classifiers Defeat Drift Detectors
Raphaël Minato, Fabrice Popineau, Arpad Rimmel +1
Monitoring concept drift from an adaptive classifier's error stream creates an operational conflict with the model's own update loop. When internal adaptation outpaces evidence acc…
Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization
José Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel +1
A family of tabular anomaly detectors trains a neural map toward a fixed target under squared-error loss and scores anomalies by the test-time residual; contraction matching, one-s…
Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
José Lucas De Melo Costa, Seong Woo Ahn, Fabrice Popineau +2
Joint-Embedding Predictive Architectures (JEPAs) are prone to representation collapse, typically mitigated through empirical heuristics. We develop an early-training stability theo…
Shifted S-templates and improved lower bounds for Schur numbers
Nils Bengone, Amine Brouk, Max Grinsztajn +4
We present an extension of the template-based approach for Schur numbers developed by Rowley. This new form of template construction, which we call shifted S-templates, was discove…
Knowledge-Informed Local Causal Discovery of Optimal Adjustment Sets
Seong Woo Ahn, Alessandro Leite, José Lucas De Melo Costa +3
Local causal discovery is a scalable alternative to global structure learning. However, it can struggle to identify valid adjustment sets in data-scarce settings because of finite-…
High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models
José Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel +1
Recent Tabular Foundation Models (TFMs) have demonstrated state-of-the-art predictive performance, often surpassing Gradient-Boosted Decision Trees (GBDTs). However, the trustworth…
T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data
Hugo Thimonier, José Lucas De Melo Costa, Fabrice Popineau +2
Self-supervision is often used for pre-training to foster performance on a downstream task by constructing meaningful representations of samples. Self-supervised learning (SSL) gen…
Retrieval Augmented Deep Anomaly Detection for Tabular Data
Hugo Thimonier, Fabrice Popineau, Arpad Rimmel +1
Deep learning for tabular data has garnered increasing attention in recent years, yet employing deep models for structured data remains challenging. While these models excel with u…
Comparative Evaluation of Anomaly Detection Methods for Fraud Detection in Online Credit Card Payments
Hugo Thimonier, Fabrice Popineau, Arpad Rimmel +2
This study explores the application of anomaly detection (AD) methods in imbalanced learning tasks, focusing on fraud detection using real online credit card payment data. We asses…
Benchmarking Robustness of Deep Reinforcement Learning approaches to Online Portfolio Management
Marc Velay, Bich-Liên Doan, Arpad Rimmel +2
Deep Reinforcement Learning approaches to Online Portfolio Selection have grown in popularity in recent years. The sensitive nature of training Reinforcement Learning agents implie…
Beyond Individual Input for Deep Anomaly Detection on Tabular Data
Hugo Thimonier, Fabrice Popineau, Arpad Rimmel +1
Anomaly detection is vital in many domains, such as finance, healthcare, and cybersecurity. In this paper, we propose a novel deep anomaly detection method for tabular data that le…
TracInAD: Measuring Influence for Anomaly Detection
Hugo Thimonier, Fabrice Popineau, Arpad Rimmel +2
As with many other tasks, neural networks prove very effective for anomaly detection purposes. However, very few deep-learning models are suited for detecting anomalies on tabular…
New lower bounds for Schur and weak Schur numbers
Romain Ageron, Paul Casteras, Thibaut Pellerin +3
This article provides new lower bounds for both Schur and weak Schur numbers by exploiting a "template"-based approach. The concept of "template" is also generalized to weak Schur…
Fixed-parameter tractability of counting small minimum -cuts
Pierre Bergé, Benjamin Mouscadet, Arpad Rimmel +1
The parameterized complexity of counting minimum cuts stands as a natural question because Ball and Provan showed its #P-completeness. For any undirected graph and two di…
On Simulated Annealing Dedicated to Maximin Latin Hypercube Designs
Pierre Bergé, Kaourintin Le Guiban, Arpad Rimmel +1
The goal of our research was to enhance local search heuristics used to construct Latin Hypercube Designs. First, we introduce the \textit{1D-move} perturbation to improve the spac…