arXiv subjects

Jakub Truszkowski

Publications and source records attributed to Jakub Truszkowski.

8 recordsLinked to original sources

arXiv2025

Optimizing Product Provenance Verification using Data Valuation Methods

Determining and verifying product provenance remains a critical challenge in global supply chains, particularly as geopolitical conflicts and shifting borders create new incentives for misrepresentation of commodities, such as hiding the origin of illegally harvested timber or stolen agricultural products. Stable Isotope Ratio Analysis (SIRA), combined with Gaussian process regression-based isoscapes, has emerged as a powerful tool for geographic origin verification. While these models are now actively deployed in operational settings supporting regulators, certification bodies, and companies, they remain constrained by data scarcity and suboptimal dataset selection. In this work, we introduce a novel deployed data valuation framework designed to enhance the selection and utilization of training data for machine learning models applied in SIRA. By quantifying the marginal utility of individual samples using Shapley values, our method guides strategic, cost-effective, and robust sampling campaigns within active monitoring programs. By prioritizing high-informative samples, our approach improves model robustness and predictive accuracy across diverse datasets and geographies. Our framework has been implemented and validated in a live provenance verification system currently used by enforcement agencies, demonstrating tangible, real-world impact. Through extensive experiments and deployment in a live provenance verification system, we show that this system significantly enhances provenance verification, mitigates fraudulent trade practices, and strengthens regulatory enforcement of global supply chains.

cs.LG↗

arXiv2025

Chasing the Timber Trail: Machine Learning to Reveal Harvest Location Misrepresentation

Illegal logging poses a significant threat to global biodiversity, climate stability, and depresses international prices for legal wood harvesting and responsible forest products trade, affecting livelihoods and communities across the globe. Stable isotope ratio analysis (SIRA) is rapidly becoming an important tool for determining the harvest location of traded, organic, products. The spatial pattern in stable isotope ratio values depends on factors such as atmospheric and environmental conditions and can thus be used for geographic origin identification. We present here the results of a deployed machine learning pipeline where we leverage both isotope values and atmospheric variables to determine timber harvest location. Additionally, the pipeline incorporates uncertainty estimation to facilitate the interpretation of harvest location determination for analysts. We present our experiments on a collection of oak (Quercus spp.) tree samples from its global range. Our pipeline outperforms comparable state-of-the-art models determining geographic harvest origin of commercially traded wood products, and has been used by European enforcement agencies to identify harvest location misrepresentation. We also identify opportunities for further advancement of our framework and how it can be generalized to help identify the origin of falsely labeled organic products throughout the supply chain.

cs.LG↗

arXiv2021

Learning partial correlation graphs and graphical models by covariance queries

We study the problem of recovering the structure underlying large Gaussian graphical models or, more generally, partial correlation graphs. In high-dimensional problems it is often too costly to store the entire sample covariance matrix. We propose a new input model in which one can query single entries of the covariance matrix. We prove that it is possible to recover the support of the inverse covariance matrix with low query and computational complexity. Our algorithms work in a regime when this support is represented by tree-like graphs and, more generally, for graphs of small treewidth. Our results demonstrate that for large classes of graphs, the structure of the corresponding partial correlation graphs can be determined much faster than even computing the empirical covariance matrix.

math.ST↗

arXiv2020

Computing the probability of gene trees concordant with the species tree in the multispecies coalescent

The multispecies coalescent process models the genealogical relationships of genes sampled from several species, enabling useful predictions about phenomena such as the discordance between the gene tree and the species phylogeny due to incomplete lineage sorting. Conversely, knowledge of large collections of gene trees can inform us about several aspects of the species phylogeny, such as its topology and ancestral population sizes. A fundamental open problem in this context is how to efficiently compute the probability of a gene tree topology, given the species phylogeny. Although a number of algorithms for this task have been proposed, they either produce approximate results, or, when they are exact, they do not scale to large data sets. In this paper, we present some progress towards exact and efficient computation of the probability of a gene tree topology. We provide a new algorithm that, given a species tree and the number of genes sampled for each species, calculates the probability that the gene tree topology will be concordant with the species tree. Moreover, we provide an algorithm that computes the probability of any specific gene tree topology concordant with the species tree. Both algorithms run in polynomial time and have been implemented in Python. Experiments show that they are able to analyse data sets where thousands of genes are sampled, in a matter of minutes to hours.

q-bio.PE↗

arXiv2020

Unsupervised Multilingual Alignment using Wasserstein Barycenter

We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the much simplified bilingual setting, by picking one of the input languages as the pivot language that we transit through. However, it is well-known that transiting through a poorly chosen pivot language (such as English) may severely degrade the translation quality, since the assumed transitive relations among all pairs of languages may not be enforced in the training process. Instead of going through a rather arbitrarily chosen pivot language, we propose to use the Wasserstein barycenter as a more informative "mean" language: it encapsulates information from all languages and minimizes all pairwise transportation costs. We evaluate our method on standard benchmarks and demonstrate state-of-the-art performances.

cs.CL↗

arXiv2012

Fast reconstruction of phylogenetic trees using locality-sensitive hashing

We present the first sub-quadratic time algorithm that with high probability correctly reconstructs phylogenetic trees for short sequences generated by a Markov model of evolution. Due to rapid expansion in sequence databases, such very fast algorithms are becoming necessary. Other fast heuristics have been developed for building trees from very large alignments (Price et al, and Brown et al), but they lack theoretical performance guarantees. Our new algorithm runs in $O(n^{1+γ(g)}\log^2n)$ time, where $γ$ is an increasing function of an upper bound on the branch lengths in the phylogeny, the upper bound $g$ must be below$1/2-\sqrt{1/8} \approx 0.15$, and $γ(g)<1$ for all $g$. For phylogenies with very short branches, the running time of our algorithm is close to linear. For example, if all branch lengths correspond to a mutation probability of less than 0.02, the running time of our algorithm is roughly $O(n^{1.2}\log^2n)$. Via a prototype and a sequence of large-scale experiments, we show that many large phylogenies can be reconstructed fast, without compromising reconstruction accuracy.

q-bio.PE↗

arXiv2012

Comparative Analysis of Probabilistic Models for Activity Recognition with an Instrumented Walker

Rollating walkers are popular mobility aids used by older adults to improve balance control. There is a need to automatically recognize the activities performed by walker users to better understand activity patterns, mobility issues and the context in which falls are more likely to happen. We design and compare several techniques to recognize walker related activities. A comprehensive evaluation with control subjects and walker users from a retirement community is presented.

cs.AI↗

arXiv2010

Fast error-tolerant quartet phylogeny algorithms

We present an algorithm for phylogenetic reconstruction using quartets that returns the correct topology for $n$ taxa in $O(n \log n)$ time with high probability, in a probabilistic model where a quartet is not consistent with the true topology of the tree with constant probability, independent of other quartets. Our incremental algorithm relies upon a search tree structure for the phylogeny that is balanced, with high probability, no matter what the true topology is. Our experimental results show that our method is comparable in runtime to the fastest heuristics, while still offering consistency guarantees.

q-bio.PE↗