24 citations · 157 across the 42 of their papers we have counts for
7 papers · 1 filter
Memory Constrained Dynamic Subnetwork Update for Transfer Learning
Aël Quélennec, Pavlo Mozharovskyi, Van-Tam Nguyen +1
On-device neural network training faces critical memory constraints that limit the adaptation of pre-trained models to downstream tasks. We present MeDyate, a theoretically-grounde…
Study of Training Dynamics for Memory-Constrained Fine-Tuning
Aël Quélennec, Nour Hezbri, Pavlo Mozharovskyi +2
Memory-efficient training of deep neural networks has become increasingly important as models grow larger while deployment environments impose strict resource constraints. We propo…
Self-Supervised Learning of Graph Representations for Network Intrusion Detection
Lorenzo Guerra, Thomas Chapuis, Guillaume Duc +2
Detecting intrusions in network traffic is a challenging task, particularly under limited supervision and constantly evolving attack patterns. While recent works have leveraged gra…
Data Depth as a Risk
Arturo Castellanos, Pavlo Mozharovskyi
Data depths are score functions that quantify in an unsupervised fashion how central is a point inside a distribution, with numerous applications such as anomaly detection, multiva…
Kernel Trace Distance: Quantum Statistical Metric between Measures through RKHS Density Operators
Arturo Castellanos, Anna Korba, Pavlo Mozharovskyi +1
Distances between probability distributions are a key component of many statistical machine learning tasks, from two-sample testing to generative modeling, among others. We introdu…
Model-Free Kernel Conformal Depth Measures Algorithm for Uncertainty Quantification in Regression Models in Separable Hilbert Spaces
Marcos Matabuena, Rahul Ghosal, Pavlo Mozharovskyi +2
Depth measures are powerful tools for defining level sets in emerging, non--standard, and complex random objects such as high-dimensional multivariate data, functional data, and ra…
Massive parallelization of projection-based depths
Leonardo Leone, Pavlo Mozharovskyi, David Bounie
This article introduces a novel methodology for the massive parallelization of projection-based depths, addressing the computational challenges of data depth in high-dimensional sp…