arXiv subjects

Andrés Abeliuk

Publications and source records attributed to Andrés Abeliuk.

16 recordsLinked to original sources

arXiv2026

NeuralZip: Reusable Setup for Fast Lossless Compression

Lossless compression can reduce the storage and movement of model weights without changing their floating-point values, but repeated statistical analysis and code construction add computational overhead. We study whether the statistical structure of exponents can be prepared once and reused. For this, we introduce NeuralZip, which groups chunks with similar exponent distributions, shares Huffman codes, and selectively represents recurring exponent tuples using packed exponents, thereby achieving additional moderate compression ratios. A setup chooses these representations before subsequent encodings, while every encoding still processes the current tensor values. In floating-point model checkpoints, post-setup compression is 1.81-21.33$\times$ faster than the baselines and achieves exact bit-to-bit reconstruction. We show that this setup can be precomputed and transferred from another compatible architecture, preserving similar compression ratios and avoiding the need to amortize setup costs. Therefore, compression adaptation is transferable and reusable. Training checkpoints demonstrate continued reuse as the weights evolve. Finally, GPU experiments reduce active memory usage by up to 27.5$\%$ while reproducing the logits exactly.

cs.LG↗

arXiv2026

Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research

Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural blind spot because the user is absent from the audit. In practice, LLMs are used in open-ended, personal interactions, during which the model implicitly represents the user and adjusts its responses accordingly. When identical requests yield different responses depending on who is asking, bias manifests not in how the model describes others but in how it treats its interlocutor. We propose Situated Interaction Auditing (SIA), a user-centered framework for studying how user profile signals -- implicit sociodemographic markers, writing style, and stated identity -- systematically shape LLM response quality, content, and tone. We demonstrate the framework through a case study that intersects gender and socioeconomic status signals across multiple task domains and outline a research agenda for SIA as a new mission for natural language processing.

cs.CY↗

arXiv2026

Measuring the Predictability of Recommender Systems using Structural Complexity Metrics

Recommender Systems (RS) shape the filtering and curation of online content, yet we have limited understanding of how predictable their recommendation outputs are. We propose data-driven metrics that quantify the predictability of recommendation datasets by measuring the structural complexity of the user-item interaction matrix. High complexity indicates intricate interaction patterns that are harder to predict; low complexity indicates simpler, more predictable structures. We operationalize structural complexity via data perturbations, using singular value decomposition (SVD) to assess how stable the latent structure remains under perturbations. Our hypothesis is that random perturbations minimally affect highly organized data, but cause substantial structural disruption in intrinsically complex data. By analyzing prediction errors on perturbed interactions, we derive metrics that quantify this sensitivity at both the dataset and the interaction levels, yielding a principled measure of inherent predictability. Experiments on real-world datasets show that our structural complexity metrics correlate with the performance of state-of-the-art recommendation algorithms. We also demonstrate structure-aware data selection: in low-data settings, models trained on a carefully chosen subset of interactions with low structural perturbation error consistently outperform models trained on the full dataset. Thus, structural complexity serves both as a precise diagnostic of dataset complexity and as a principled foundation for efficient, data-centric training of RS.

cs.IR↗

arXiv2025

Networks Multiscale Entropy Analysis

Understanding the structural complexity and predictability of complex networks is a central challenge in network science. Although recent studies have revealed a relationship between compression-based entropy and link prediction performance, existing methods focus on single-scale representations. This approach often overlooks the rich hierarchical patterns that can exist in real-world networks. In this study, we introduce a multiscale entropy framework that extends previous entropy-based approaches by applying spectral graph reduction. This allows us to quantify how structural entropy evolves as the network is gradually coarsened, capturing complexity across multiple scales. We apply our framework to real-world networks across biological, economic, social, technological, and transportation domains. The results uncover consistent entropy profiles across network families, revealing three structural regimes$\unicode{x2013}$stable, increasing, and hybrid$\unicode{x2013}$that align with domain-specific behaviors. Compared to single-scale models, multiscale entropy significantly improves our ability to determine network predictability. This shows that considering structural information across scales provides a more complete characterization of network complexity. Together, these results position multiscale entropy as a powerful and scalable tool for characterizing, classifying, and assessing the structure of complex networks.

cs.SI↗

arXiv2025

Impact of Price Inflation on Algorithmic Collusion Through Reinforcement Learning Agents

Algorithmic pricing is increasingly shaping market competition, raising concerns about its potential to compromise competitive dynamics. While prior work has shown that reinforcement learning (RL)-based pricing algorithms can lead to tacit collusion, less attention has been given to the role of macroeconomic factors in shaping these dynamics. This study examines the role of inflation in influencing algorithmic collusion within competitive markets. By incorporating inflation shocks into a RL-based pricing model, we analyze whether agents adapt their strategies to sustain supra-competitive profits. Our findings indicate that inflation reduces market competitiveness by fostering implicit coordination among agents, even without direct collusion. However, despite achieving sustained higher profitability, agents fail to develop robust punishment mechanisms to deter deviations from equilibrium strategies. The results suggest that inflation amplifies non-competitive dynamics in algorithmic pricing, emphasizing the need for regulatory oversight in markets where AI-driven pricing is prevalent.

cs.LG↗

arXiv2025

Zero-Shot Decision Tree Construction via Large Language Models

This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART) principles. Traditional decision tree induction methods rely heavily on labeled data to recursively partition data using criteria such as information gain or the Gini index. In contrast, we propose a method that uses the pre-trained knowledge embedded in LLMs to build decision trees without requiring training data. Our approach leverages LLMs to perform operations essential for decision tree construction, including attribute discretization, probability calculation, and Gini index computation based on the probabilities. We show that these zero-shot decision trees can outperform baseline zero-shot methods and achieve competitive performance compared to supervised data-driven decision trees on tabular datasets. The decision trees constructed via this method provide transparent and interpretable models, addressing data scarcity while preserving interpretability. This work establishes a new baseline in low-data machine learning, offering a principled, knowledge-driven alternative to data-driven tree construction.

cs.LG↗

arXiv2025

Fairness in LLM-Generated Surveys

Large Language Models (LLMs) excel in text generation and understanding, especially in simulating socio-political and economic patterns, serving as an alternative to traditional surveys. However, their global applicability remains questionable due to unexplored biases across socio-demographic and geographic contexts. This study examines how LLMs perform across diverse populations by analyzing public surveys from Chile and the United States, focusing on predictive accuracy and fairness metrics. The results show performance disparities, with LLM consistently outperforming on U.S. datasets. This bias originates from the U.S.-centric training data, remaining evident after accounting for socio-demographic differences. In the U.S., political identity and race significantly influence prediction accuracy, while in Chile, gender, education, and religious affiliation play more pronounced roles. Our study presents a novel framework for measuring socio-demographic biases in LLMs, offering a path toward ensuring fairer and more equitable model performance across diverse socio-cultural contexts.

cs.CY↗

arXiv2024

QuickCent: a fast and frugal heuristic for harmonic centrality estimation on scale-free networks

We present a simple and quick method to approximate network centrality indexes. Our approach, called QuickCent, is inspired by so-called fast and frugal heuristics, which are heuristics initially proposed to model some human decision and inference processes. The centrality index that we estimate is the harmonic centrality, which is a measure based on shortest-path distances, so infeasible to compute on large networks. We compare QuickCent with known machine learning algorithms on synthetic data generated with preferential attachment, and some empirical networks. Our experiments show that QuickCent is able to make estimates that are competitive in accuracy with the best alternative methods tested, either on synthetic scale-free networks or empirical networks. QuickCent has the feature of achieving low error variance estimates, even with a small training set. Moreover, QuickCent is comparable in efficiency -- accuracy and time cost -- to those produced by more complex methods. We discuss and provide some insight into how QuickCent exploits the fact that in some networks, such as those generated by preferential attachment, local density measures such as the in-degree, can be a proxy for the size of the network region to which a node has access, opening up the possibility of approximating centrality indices based on size such as the harmonic centrality. Our initial results show that simple heuristics and biologically inspired computational methods are a promising line of research in the context of network measure estimations.

cs.SI↗

arXiv2020

Moral Framing and Ideological Bias of News

News outlets are a primary source for many people to learn what is going on in the world. However, outlets with different political slants, when talking about the same news story, usually emphasize various aspects and choose their language framing differently. This framing implicitly shows their biases and also affects the reader's opinion and understanding. Therefore, understanding the framing in the news stories is fundamental for realizing what kind of view the writer is conveying with each news story. In this paper, we describe methods for characterizing moral frames in the news. We capture the frames based on the Moral Foundation Theory. This theory is a psychological concept which explains how every kind of morality and opinion can be summarized and presented with five main dimensions. We propose an unsupervised method that extracts the framing Bias and the framing Intensity without any external framing annotations provided. We validate the performance on an annotated twitter dataset and then use it to quantify the framing bias and partisanship of news.

cs.CY↗

arXiv2020

Learning Behavioral Representations from Wearable Sensors

Continuous collection of physiological data from wearable sensors enables temporal characterization of individual behaviors. Understanding the relation between an individual's behavioral patterns and psychological states can help identify strategies to improve quality of life. One challenge in analyzing physiological data is extracting the underlying behavioral states from the temporal sensor signals and interpreting them. Here, we use a non-parametric Bayesian approach to model sensor data from multiple people and discover the dynamic behaviors they share. We apply this method to data collected from sensors worn by a population of hospital workers and show that the learned states can cluster participants into meaningful groups and better predict their cognitive and psychological states. This method offers a way to learn interpretable compact behavioral representations from multivariate sensor signals.

cs.LG↗

arXiv2020

Challenges in Forecasting Malicious Events from Incomplete Data

The ability to accurately predict cyber-attacks would enable organizations to mitigate their growing threat and avert the financial losses and disruptions they cause. But how predictable are cyber-attacks? Researchers have attempted to combine external data -- ranging from vulnerability disclosures to discussions on Twitter and the darkweb -- with machine learning algorithms to learn indicators of impending cyber-attacks. However, successful cyber-attacks represent a tiny fraction of all attempted attacks: the vast majority are stopped, or filtered by the security appliances deployed at the target. As we show in this paper, the process of filtering reduces the predictability of cyber-attacks. The small number of attacks that do penetrate the target's defenses follow a different generative process compared to the whole data which is much harder to learn for predictive models. This could be caused by the fact that the resulting time series also depends on the filtering process in addition to all the different factors that the original time series depended on. We empirically quantify the loss of predictability due to filtering using real-world data from two organizations. Our work identifies the limits to forecasting cyber-attacks from highly filtered data.

cs.CR↗

arXiv2020

Quantifying the Effects of Recommendation Systems

Recommendation systems today exert a strong influence on consumer behavior and individual perceptions of the world. By using collaborative filtering (CF) methods to create recommendations, it generates a continuous feedback loop in which user behavior becomes magnified in the algorithmic system. Popular items get recommended more frequently, creating the bias that affects and alters user preferences. In order to visualize and compare the different biases, we will analyze the effects of recommendation systems and quantify the inequalities resulting from them.

cs.IR↗

arXiv2020

Predictability limit of partially observed systems

Applications from finance to epidemiology and cyber-security require accurate forecasts of dynamic phenomena, which are often only partially observed. We demonstrate that a system's predictability degrades as a function of temporal sampling, regardless of the adopted forecasting model. We quantify the loss of predictability due to sampling, and show that it cannot be recovered by using external signals. We validate the generality of our theoretical findings in real-world partially observed systems representing infectious disease outbreaks, online discussions, and software development projects. On a variety of prediction tasks---forecasting new infections, the popularity of topics in online discussions, or interest in cryptocurrency projects---predictability irrecoverably decays as a function of sampling, unveiling fundamental predictability limits in partially observed systems.

cs.CY↗

arXiv2019

Discovering patterns of online popularity from time series

How is popularity gained online? Is being successful strictly related to rapidly becoming viral in an online platform or is it possible to acquire popularity in a steady and disciplined fashion? What are other temporal characteristics that can unveil the popularity of online content? To answer these questions, we leverage a multi-faceted temporal analysis of the evolution of popular online contents. Here, we present dipm-SC: a multi-dimensional shape-based time-series clustering algorithm with a heuristic to find the optimal number of clusters. First, we validate the accuracy of our algorithm on synthetic datasets generated from benchmark time series models. Second, we show that dipm-SC can uncover meaningful clusters of popularity behaviors in a real-world Twitter dataset. By clustering the multidimensional time-series of the popularity of contents coupled with other domain-specific dimensions, we uncover two main patterns of popularity: bursty and steady temporal behaviors. Moreover, we find that the way popularity is gained over time has no significant impact on the final cumulative popularity.

cs.LG↗

arXiv2019

Characterizing Activity on the Deep and Dark Web

The deep and darkweb (d2web) refers to limited access web sites that require registration, authentication, or more complex encryption protocols to access them. These web sites serve as hubs for a variety of illicit activities: to trade drugs, stolen user credentials, hacking tools, and to coordinate attacks and manipulation campaigns. Despite its importance to cyber crime, the d2web has not been systematically investigated. In this paper, we study a large corpus of messages posted to 80 d2web forums over a period of more than a year. We identify topics of discussion using LDA and use a non-parametric HMM to model the evolution of topics across forums. Then, we examine the dynamic patterns of discussion and identify forums with similar patterns. We show that our approach surfaces hidden similarities across different forums and can help identify anomalous events in this rich, heterogeneous data.

cs.CY↗

arXiv2019

Price of Anarchy in Algorithmic Matching of Romantic Partners

Algorithmic-matching sites offer users access to an unprecedented number of potential mates. However, they also pose a principal-agent problem with a potential moral hazard. The agent's interest is to maximize usage of the Web site, while the principal's interest is to find the best possible romantic partners. This creates a conflict of interest: optimally matching users would lead to stable couples and fewer singles using the site, which is detrimental for the online dating industry. Here, we borrow the notion of Price-of-Anarchy from game theory to quantify the decrease in social efficiency of online dating sites caused by the agent's self-interest. We derive theoretical bounds on the price-of-anarchy, showing it can be bounded by a constant that does not depend on the number of users of the dating site. This suggests that as online dating sites grow, their potential benefits scale up without sacrificing social efficiency. Further, we performed experiments involving human subjects in a matching market, and compared the social welfare achieved by an optimal matching service against a self-interest matching algorithm. We show that by introducing competition among dating sites, the selfish behavior of agents aligns with its users, and social efficiency increases.

cs.GT↗