arXiv subjects

Andrea Lampis

Publications and source records attributed to Andrea Lampis.

5 recordsLinked to original sources

arXiv2026

SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion

Polygenic risk scores and other genomic analyses require large individual-level genotype datasets, yet strict data access restrictions impede sharing. Synthetic genotype generation offers a privacy-preserving alternative, but most existing methods operate unconditionally, producing samples without phenotype alignment, or rely on unsupervised compression, creating a gap between statistical fidelity and downstream task utility. We present SNPgen, a two-stage conditional latent diffusion framework for generating phenotype-supervised synthetic genotypes. SNPgen combines GWAS-guided variant selection (1,024-2,048 trait-associated SNPs) with a variational autoencoder for genotype compression and a latent diffusion model conditioned on binary disease labels via classifier-free guidance. Evaluated on 458,724 UK Biobank individuals across four complex diseases (coronary artery disease, breast cancer, type 1 and type 2 diabetes), models trained on synthetic data matched real-data predictive performance in a train-on-synthetic, test-on-real protocol, approaching genome-wide PRS methods that use $2$-$6\times$ more variants. Privacy analysis confirmed zero identical matches, near-random membership inference (AUC $\approx 0.50$), preserved linkage disequilibrium structure, and high allele frequency correlation ($r \geq 0.95$) with source data. A controlled simulation with known causal effects verified faithful recovery of the imposed genetic association structure.

cs.LG↗

arXiv2026

Tracking charged $b$-hadrons: feasibility study of the use of inner trackers to improve $B^{+}_{(c)}$ reconstruction

A method to improve the reconstruction of charged b-hadron decays is proposed that uses energy deposits left by the hadron in tracking detectors close to the production point. Performances are shown for different detector configurations and different number of deposits reconstructed, as obtained in simulation, for $b$-hadrons produced in high energy proton-proton collisions. It is shown that up to few percent of the $B^+$ mesons could leave two deposits before decaying, depending on the detector configuration. The presented results can inform the design of future inner detectors. This method could increase significantly the physics reach of flavour physics at hadron colliders, opening it to decays with missing particles and vertex information that are otherwise unreconstructable.

hep-ex↗

arXiv2023

Bridging the Gap: Enhancing the Utility of Synthetic Data via Post-Processing Techniques

Acquiring and annotating suitable datasets for training deep learning models is challenging. This often results in tedious and time-consuming efforts that can hinder research progress. However, generative models have emerged as a promising solution for generating synthetic datasets that can replace or augment real-world data. Despite this, the effectiveness of synthetic data is limited by their inability to fully capture the complexity and diversity of real-world data. To address this issue, we explore the use of Generative Adversarial Networks to generate synthetic datasets for training classifiers that are subsequently evaluated on real-world images. To improve the quality and diversity of the synthetic dataset, we propose three novel post-processing techniques: Dynamic Sample Filtering, Dynamic Dataset Recycle, and Expansion Trick. In addition, we introduce a pipeline called Gap Filler (GaFi), which applies these techniques in an optimal and coordinated manner to maximise classification accuracy on real-world data. Our experiments show that GaFi effectively reduces the gap with real-accuracy scores to an error of 2.03%, 1.78%, and 3.99% on the Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets, respectively. These results represent a new state of the art in Classification Accuracy Score and highlight the effectiveness of post-processing techniques in improving the quality of synthetic datasets.

cs.CV↗

arXiv2021

Accurate modelling of 3D-trench silicon sensor with enhanced timing performance and comparison with test beam measurements

This paper presents the detailed simulation of a double-pixel structure for charged particle detection based on the 3D-trench silicon sensor developed for the TIMESPOT project and a comparison of the simulation results with measurements performed at $π-$M1 beam at PSI laboratory. The simulation is based on the combined use of several software tools (TCAD, GEANT4, TCoDe and TFBoost) which allow to fully design and simulate the device physics response in very short computational time, O(1-100 s) per simulated signal, by exploiting parallel computation using single or multi-thread processors. This allowed to produce large samples of simulated signals, perform detailed studies of the sensor characteristics and make precise comparisons with experimental results.

physics.ins-det↗

arXiv2020

Intrinsic time resolution of 3D-trench silicon pixels for charged particle detection

In the last years, high-resolution time tagging has emerged as the tool to tackle the problem of high-track density in the detectors of the next generation of experiments at particle colliders. Time resolutions below 50ps and event average repetition rates of tens of MHz on sensor pixels having a pitch of 50$μ$m are typical minimum requirements. This poses an important scientific and technological challenge on the development of particle sensors and processing electronics. The TIMESPOT initiative (which stands for TIME and SPace real-time Operating Tracker) aims at the development of a full prototype detection system suitable for the particle trackers of the next-to-come particle physics experiments. This paper describes the results obtained on the first batch of TIMESPOT silicon sensors, based on a novel 3D MEMS (micro electro-mechanical systems) design. Following this approach, the performance of other ongoing silicon sensor developments has been matched and overcome, while using a technology which is known to be robust against radiation degradation. A time resolution of the order of 20ps has been measured at room temperature suggesting also possible improvements after further optimisations of the front-end electronics processing stage.

physics.ins-det↗