arXiv subjects

Daniel Mas Montserrat

Publications and source records attributed to Daniel Mas Montserrat.

16 recordsLinked to original sources

arXiv2026

A Tsallis-Entropy Lens on Genetic Variation

We introduce an information-theoretic generalization of the fixation statistic, the Tsallis-order $q$ F-statistic, $F_q$, which measures the fraction of Tsallis $q$-entropy lost within subpopulations relative to the pooled population. The family nests the classical variance-based fixation index $F_{\textbf{ST}}$ at $q{=}2$ and a Shannon-entropy analogue at $q{=}1$, whose absolute form equals the mutual information between alleles and population labels. By varying $q$ between these, $F_q$ acts as a spectral differentiator that up-weights rare variants at low $q$, while $q{>}1$ increasingly emphasizes common variants, providing a more fine-grained view of differentiation than $F_{\textbf{ST}}$ when allele-frequency spectra are skewed. On real data (865 Oceanian genomes with 1,823,000 sites) and controlled genealogical simulations (seeded from 1,432 founders from HGDP and 1000 Genomes panels, with 322,216 sites), we show that $F_q$ in One-vs-Rest (OVR) and Leave-One-Out (LOO) modes provides clear attribution of which subpopulations drive regional structure, and sensitively timestamps isolation-migration events and founder effects. $F_q$ serves as finer-resolution complement for simulation audits and population-structure summaries.

cs.IT↗

arXiv2026

iLTM: Integrated Large Tabular Model

Tabular data underpins decisions across science, industry, and public services. Despite rapid progress, advances in deep learning have not fully carried over to the tabular domain, where gradient-boosted decision trees (GBDTs) remain a default choice in practice. We present iLTM, an integrated Large Tabular Model that unifies tree-derived embeddings, dimensionality-agnostic representations, a meta-trained hypernetwork, multilayer perceptrons (MLPs), and retrieval within a single architecture. Pre-trained on more than 1,800 heterogeneous classification datasets, iLTM achieves consistently superior performance across tabular classification and regression tasks, from small datasets to large and high-dimensional tasks. After light fine-tuning, the meta-trained hypernetwork transfers to regression targets, matching or surpassing strong baselines. Extensive experiments show that iLTM outperforms well-tuned GBDTs and leading deep tabular models while requiring less task-specific tuning. By bridging the gap between tree-based and neural methods, iLTM offers a new framework for tabular foundation models for robust, adaptable, and scalable tabular learning.

cs.LG↗

arXiv2025

Efficient Chromosome Parallelization for Precision Medicine Genomic Workflows

Large-scale genomic workflows used in precision medicine can process datasets spanning tens to hundreds of gigabytes per sample, leading to high memory spikes, intensive disk I/O, and task failures due to out-of-memory errors. Simple static resource allocation methods struggle to handle the variability in per-chromosome RAM demands, resulting in poor resource utilization and long runtimes. In this work, we propose multiple mechanisms for adaptive, RAM-efficient parallelization of chromosome-level bioinformatics workflows. First, we develop a symbolic regression model that estimates per-chromosome memory consumption for a given task and introduces an interpolating bias to conservatively minimize over-allocation. Second, we present a dynamic scheduler that adaptively predicts RAM usage with a polynomial regression model, treating task packing as a Knapsack problem to optimally batch jobs based on predicted memory requirements. Additionally, we present a static scheduler that optimizes chromosome processing order to minimize peak memory while preserving throughput. Our proposed methods, evaluated on simulations and real-world genomic pipelines, provide new mechanisms to reduce memory overruns and balance load across threads. We thereby achieve faster end-to-end execution, showcasing the potential to optimize large-scale genomic workflows.

cs.DC↗

arXiv2025

Compressive Meta-Learning

The rapid expansion in the size of new datasets has created a need for fast and efficient parameter-learning techniques. Compressive learning is a framework that enables efficient processing by using random, non-linear features to project large-scale databases onto compact, information-preserving representations whose dimensionality is independent of the number of samples and can be easily stored, transferred, and processed. These database-level summaries are then used to decode parameters of interest from the underlying data distribution without requiring access to the original samples, offering an efficient and privacy-friendly learning framework. However, both the encoding and decoding techniques are typically randomized and data-independent, failing to exploit the underlying structure of the data. In this work, we propose a framework that meta-learns both the encoding and decoding stages of compressive learning methods by using neural networks that provide faster and more accurate systems than the current state-of-the-art approaches. To demonstrate the potential of the presented Compressive Meta-Learning framework, we explore multiple applications -- including neural network-based compressive PCA, compressive ridge regression, compressive k-means, and autoencoders.

cs.LG↗

arXiv2025

Feature Shift Localization Network

Feature shifts between data sources are present in many applications involving healthcare, biomedical, socioeconomic, financial, survey, and multi-sensor data, among others, where unharmonized heterogeneous data sources, noisy data measurements, or inconsistent processing and standardization pipelines can lead to erroneous features. Localizing shifted features is important to address the underlying cause of the shift and correct or filter the data to avoid degrading downstream analysis. While many techniques can detect distribution shifts, localizing the features originating them is still challenging, with current solutions being either inaccurate or not scalable to large and high-dimensional datasets. In this work, we introduce the Feature Shift Localization Network (FSL-Net), a neural network that can localize feature shifts in large and high-dimensional datasets in a fast and accurate manner. The network, trained with a large number of datasets, learns to extract the statistical properties of the datasets and can localize feature shifts from previously unseen datasets and shifts without the need for re-training. The code and ready-to-use trained model are available at https://github.com/AI-sandbox/FSL-Net.

cs.LG↗

arXiv2024

HyperFast: Instant Classification for Tabular Data

Training deep learning models and performing hyperparameter tuning can be computationally demanding and time-consuming. Meanwhile, traditional machine learning methods like gradient-boosting algorithms remain the preferred choice for most tabular data applications, while neural network alternatives require extensive hyperparameter tuning or work only in toy datasets under limited settings. In this paper, we introduce HyperFast, a meta-trained hypernetwork designed for instant classification of tabular data in a single forward pass. HyperFast generates a task-specific neural network tailored to an unseen dataset that can be directly used for classification inference, removing the need for training a model. We report extensive experiments with OpenML and genomic data, comparing HyperFast to competing tabular data neural networks, traditional ML methods, AutoML systems, and boosting machines. HyperFast shows highly competitive results, while being significantly faster. Additionally, our approach demonstrates robust adaptability across a variety of classification tasks with little to no fine-tuning, positioning HyperFast as a strong solution for numerous applications and rapid model deployment. HyperFast introduces a promising paradigm for fast classification, with the potential to substantially decrease the computational burden of deep learning. Our code, which offers a scikit-learn-like interface, along with the trained HyperFast model, can be found at https://github.com/AI-sandbox/HyperFast.

cs.LG↗

arXiv2023

Adversarial Learning for Feature Shift Detection and Correction

Data shift is a phenomenon present in many real-world applications, and while there are multiple methods attempting to detect shifts, the task of localizing and correcting the features originating such shifts has not been studied in depth. Feature shifts can occur in many datasets, including in multi-sensor data, where some sensors are malfunctioning, or in tabular and structured data, including biomedical, financial, and survey data, where faulty standardization and data processing pipelines can lead to erroneous features. In this work, we explore using the principles of adversarial learning, where the information from several discriminators trained to distinguish between two distributions is used to both detect the corrupted features and fix them in order to remove the distribution shift between datasets. We show that mainstream supervised classifiers, such as random forest or gradient boosting trees, combined with simple iterative heuristics, can localize and correct feature shifts, outperforming current statistical and neural network-based techniques. The code is available at https://github.com/AI-sandbox/DataFix.

cs.LG↗

arXiv2021

Manipulation Detection in Satellite Images Using Vision Transformer

A growing number of commercial satellite companies provide easily accessible satellite imagery. Overhead imagery is used by numerous industries including agriculture, forestry, natural disaster analysis, and meteorology. Satellite images, just as any other images, can be tampered with image manipulation tools. Manipulation detection methods created for images captured by "consumer cameras" tend to fail when used on satellite images due to the differences in image sensors, image acquisition, and processing. In this paper we propose an unsupervised technique that uses a Vision Transformer to detect spliced areas within satellite images. We introduce a new dataset which includes manipulated satellite images that contain spliced objects. We show that our proposed approach performs better than existing unsupervised splicing detection techniques.

eess.IV↗

arXiv2021

Saliency-Aware Class-Agnostic Food Image Segmentation

Advances in image-based dietary assessment methods have allowed nutrition professionals and researchers to improve the accuracy of dietary assessment, where images of food consumed are captured using smartphones or wearable devices. These images are then analyzed using computer vision methods to estimate energy and nutrition content of the foods. Food image segmentation, which determines the regions in an image where foods are located, plays an important role in this process. Current methods are data dependent, thus cannot generalize well for different food types. To address this problem, we propose a class-agnostic food image segmentation method. Our method uses a pair of eating scene images, one before start eating and one after eating is completed. Using information from both the before and after eating images, we can segment food images by finding the salient missing objects without any prior information about the food class. We model a paradigm of top down saliency which guides the attention of the human visual system (HVS) based on a task to find the salient missing objects in a pair of images. Our method is validated on food images collected from a dietary study which showed promising results.

cs.CV↗

arXiv2020

Generative Autoregressive Ensembles for Satellite Imagery Manipulation Detection

Satellite imagery is becoming increasingly accessible due to the growing number of orbiting commercial satellites. Many applications make use of such images: agricultural management, meteorological prediction, damage assessment from natural disasters, or cartography are some of the examples. Unfortunately, these images can be easily tampered and modified with image manipulation tools damaging downstream applications. Because the nature of the manipulation applied to the image is typically unknown, unsupervised methods that don't require prior knowledge of the tampering techniques used are preferred. In this paper, we use ensembles of generative autoregressive models to model the distribution of the pixels of the image in order to detect potential manipulations. We evaluate the performance of the presented approach obtaining accurate localization results compared to previously presented approaches.

cs.CV↗

arXiv2020

Deepfakes Detection with Automatic Face Weighting

Altered and manipulated multimedia is increasingly present and widely distributed via social media platforms. Advanced video manipulation tools enable the generation of highly realistic-looking altered multimedia. While many methods have been presented to detect manipulations, most of them fail when evaluated with data outside of the datasets used in research environments. In order to address this problem, the Deepfake Detection Challenge (DFDC) provides a large dataset of videos containing realistic manipulations and an evaluation system that ensures that methods work quickly and accurately, even when faced with challenging data. In this paper, we introduce a method based on convolutional neural networks (CNNs) and recurrent neural networks (RNNs) that extracts visual and temporal features from faces present in videos to accurately detect manipulations. The method is evaluated with the DFDC dataset, providing competitive results compared to other techniques.

cs.CV↗

arXiv2020

Manipulation Detection in Satellite Images Using Deep Belief Networks

Satellite images are more accessible with the increase of commercial satellites being orbited. These images are used in a wide range of applications including agricultural management, meteorological prediction, damage assessment from natural disasters, and cartography. Image manipulation tools including both manual editing tools and automated techniques can be easily used to tamper and modify satellite imagery. One type of manipulation that we examine in this paper is the splice attack where a region from one image (or the same image) is inserted (spliced) into an image. In this paper, we present a one-class detection method based on deep belief networks (DBN) for splicing detection and localization without using any prior knowledge of the manipulations. We evaluate the performance of our approach and show that it provides good detection and localization accuracies in small forgeries compared to other approaches.

eess.IV↗

arXiv2020

Addressing Ancestry Disparities in Genomic Medicine: A Geographic-aware Algorithm

With declining sequencing costs a promising and affordable tool is emerging in cancer diagnostics: genomics. By using association studies, genomic variants that predispose patients to specific cancers can be identified, while by using tumor genomics cancer types can be characterized for targeted treatment. However, a severe disparity is rapidly emerging in this new area of precision cancer diagnosis and treatment planning, one which separates a few genetically well-characterized populations (predominantly European) from all other global populations. Here we discuss the problem of population-specific genetic associations, which is driving this disparity, and present a novel solution--coordinate-based local ancestry--for helping to address it. We demonstrate our boosting-based method on whole genome data from divergent groups across Africa and in the process observe signals that may stem from the transcontinental Bantu-expansion.

q-bio.GN↗

arXiv2020

LAI-Net: Local-Ancestry Inference with Neural Networks

Local-ancestry inference (LAI), also referred to as ancestry deconvolution, provides high-resolution ancestry estimation along the human genome. In both research and industry, LAI is emerging as a critical step in DNA sequence analysis with applications extending from polygenic risk scores (used to predict traits in embryos and disease risk in adults) to genome-wide association studies, and from pharmacogenomics to inference of human population history. While many LAI methods have been developed, advances in computing hardware (GPUs) combined with machine learning techniques, such as neural networks, are enabling the development of new methods that are fast, robust and easily shared and stored. In this paper we develop the first neural network based LAI method, named LAI-Net, providing competitive accuracy with state-of-the-art methods and robustness to missing or noisy data, while having a small number of layers.

q-bio.GN↗

arXiv2019

Multi-View Matching Network for 6D Pose Estimation

Applications that interact with the real world such as augmented reality or robot manipulation require a good understanding of the location and pose of the surrounding objects. In this paper, we present a new approach to estimate the 6 Degree of Freedom (DoF) or 6D pose of objects from a single RGB image. Our approach can be paired with an object detection and segmentation method to estimate, refine and track the pose of the objects by matching the input image with rendered images.

cs.CV↗

arXiv2019

Class-Conditional VAE-GAN for Local-Ancestry Simulation

Local ancestry inference (LAI) allows identification of the ancestry of all chromosomal segments in admixed individuals, and it is a critical step in the analysis of human genomes with applications from pharmacogenomics and precision medicine to genome-wide association studies. In recent years, many LAI techniques have been developed in both industry and academic research. However, these methods require large training data sets of human genomic sequences from the ancestries of interest. Such reference data sets are usually limited, proprietary, protected by privacy restrictions, or otherwise not accessible to the public. Techniques to generate training samples that resemble real haploid sequences from ancestries of interest can be useful tools in such scenarios, since a generalized model can often be shared, but the unique human sample sequences cannot. In this work we present a class-conditional VAE-GAN to generate new human genomic sequences that can be used to train local ancestry inference (LAI) algorithms. We evaluate the quality of our generated data by comparing the performance of a state-of-the-art LAI method when trained with generated versus real data.

q-bio.GN↗