arXiv subjects

Fabio Parisi

Publications and source records attributed to Fabio Parisi.

3 recordsLinked to original sources

arXiv2026

Blind Noise Equalization for Large Data Matrices under General Variance Profiles

Low-rank approximation is a basic tool for inference from large and noisy data matrices. However, when noise variances differ across entries, a setting known as heteroskedasticity, the noise can distort the observed spectrum, producing spurious components and obscuring weak signals. To address these challenges, we develop BRINE (Blind Resolvent-based Iterative Noise Equalizer), a data-driven procedure that iteratively rescales rows and columns to equalize the average noise variance across both dimensions. Under suitable conditions, this procedure restores the Marchenko-Pastur law for the noise spectrum and can amplify signal components without prior knowledge of the signal or noise structure. A key idea underlying our approach is to equalize the diagonal entries of the data resolvent as a proxy for equalizing the unknown noise variances. At the population level, we identify a potential function that characterizes this equalization and motivates an iterative minimization procedure. We prove convergence of the iterations to the true equalizer for arbitrary positive variance profiles, with a geometric rate under mild conditions. The updates can be estimated directly from noisy data, and we establish probabilistic error bounds for the scaling factors. Simulations and experiments across diverse biological data modalities and preprocessing pipelines illustrate the effectiveness of our approach.

stat.ML↗

arXiv2013

Ranking and combining multiple predictors without labeled data

In a broad range of classification and decision making problems, one is given the advice or predictions of several classifiers, of unknown reliability, over multiple questions or queries. This scenario is different from the standard supervised setting, where each classifier accuracy can be assessed using available labeled data, and raises two questions: given only the predictions of several classifiers over a large set of unlabeled test data, is it possible to a) reliably rank them; and b) construct a meta-classifier more accurate than most classifiers in the ensemble? Here we present a novel spectral approach to address these questions. First, assuming conditional independence between classifiers, we show that the off-diagonal entries of their covariance matrix correspond to a rank-one matrix. Moreover, the classifiers can be ranked using the leading eigenvector of this covariance matrix, as its entries are proportional to their balanced accuracies. Second, via a linear approximation to the maximum likelihood estimator, we derive the Spectral Meta-Learner (SML), a novel ensemble classifier whose weights are equal to this eigenvector entries. On both simulated and real data, SML typically achieves a higher accuracy than most classifiers in the ensemble and can provide a better starting point than majority voting, for estimating the maximum likelihood solution. Furthermore, SML is robust to the presence of small malicious groups of classifiers designed to veer the ensemble prediction away from the (unknown) ground truth.

stat.ML↗

arXiv2013

TrAp: a Tree Approach for Fingerprinting Subclonal Tumor Composition

Revealing the clonal composition of a single tumor is essential for identifying cell subpopulations with metastatic potential in primary tumors or with resistance to therapies in metastatic tumors. Sequencing technologies provide an overview of an aggregate of numerous cells, rather than subclonal-specific quantification of aberrations such as single nucleotide variants (SNVs). Computational approaches to de-mix a single collective signal from the mixed cell population of a tumor sample into its individual components are currently not available. Herein we propose a framework for deconvolving data from a single genome-wide experiment to infer the composition, abundance and evolutionary paths of the underlying cell subpopulations of a tumor. The method is based on the plausible biological assumption that tumor progression is an evolutionary process where each individual aberration event stems from a unique subclone and is present in all its descendants subclones. We have developed an efficient algorithm (TrAp) for solving this mixture problem. In silico analyses show that TrAp correctly deconvolves mixed subpopulations when the number of subpopulations and the measurement errors are moderate. We demonstrate the applicability of the method using tumor karyotypes and somatic hypermutation datasets. We applied TrAp to SNV frequency profile from Exome-Seq experiment of a renal cell carcinoma tumor sample and compared the mutational profile of the inferred subpopulations to the mutational profiles of twenty single cells of the same tumor. Despite the large experimental noise, specific co-occurring mutations found in clones inferred by TrAp are also present in some of these single cells. Finally, we deconvolve Exome-Seq data from three distinct metastases from different body compartments of one melanoma patient and exhibit the evolutionary relationships of their subpopulations.

q-bio.GN↗