arXiv subjects

Sebastian Macaluso

Publications and source records attributed to Sebastian Macaluso.

15 recordsLinked to original sources

arXiv2026

Dual-Graph Multi-Agent Reinforcement Learning for Handover Optimization

HandOver (HO) control in cellular networks is governed by a set of HO control parameters that are traditionally configured through rule-based heuristics. A key parameter for HO optimization is the Cell Individual Offset (CIO), defined for each pair of neighboring cells and used to bias HO triggering decisions. At network scale, tuning CIOs becomes a tightly coupled problem: small changes can redirect mobility flows across multiple neighbors, and static rules often degrade under non-stationary traffic and mobility. We exploit the pairwise structure of CIOs by formulating HO optimization as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) on the network's dual graph. In this representation, each agent controls a neighbor-pair CIO and observes Key Performance Indicators (KPIs) aggregated over its local dual-graph neighborhood, enabling scalable decentralized decisions while preserving graph locality. Building on this formulation, we propose TD3-D-MA, a discrete Multi-Agent Reinforcement Learning (MARL) variant of the TD3 algorithm with a shared-parameter Graph Neural Network (GNN) actor operating on the dual graph and region-wise double critics for training, improving credit assignment in dense deployments. We evaluate TD3-D-MA in an ns-3 system-level simulator configured with real-world network operator parameters across heterogeneous traffic regimes and network topologies. Results show that TD3-D-MA improves network throughput over standard HO heuristics and centralized RL baselines, and generalizes robustly under topology and traffic shifts.

cs.NI↗

arXiv2025

Quantum Computing for Large-scale Network Optimization: Opportunities and Challenges

The complexity of large-scale 6G-and-beyond networks demands innovative approaches for multi-objective optimization over vast search spaces, a task often intractable. Quantum computing (QC) emerges as a promising technology for efficient large-scale optimization. We present our vision of leveraging QC to tackle key classes of problems in future mobile networks. By analyzing and identifying common features, particularly their graph-centric representation, we propose a unified strategy involving QC algorithms. Specifically, we outline a methodology for optimization using quantum annealing as well as quantum reinforcement learning. Additionally, we discuss the main challenges that QC algorithms and hardware must overcome to effectively optimize future networks.

cs.NI↗

arXiv2025

Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI

Artificial Intelligence (AI) is rapidly embedded in critical decision-making systems, however their foundational ``black-box'' models require eXplainable AI (XAI) solutions to enhance transparency, which are mostly oriented to experts, making no sense to non-experts. Alarming evidence about AI's unprecedented human values risks brings forward the imperative need for transparent human-centered XAI solutions. In this work, we introduce a domain-, model-, explanation-agnostic, generalizable and reproducible framework that ensures both transparency and human-centered explanations tailored to the needs of both experts and non-experts. The framework leverages Large Language Models (LLMs) and employs in-context learning to convey domain- and explainability-relevant contextual knowledge into LLMs. Through its structured prompt and system setting, our framework encapsulates in one response explanations understandable by non-experts and technical information to experts, all grounded in domain and explainability principles. To demonstrate the effectiveness of our framework, we establish a ground-truth contextual ``thesaurus'' through a rigorous benchmarking with over 40 data, model, and XAI combinations for an explainable clustering analysis of a well-being scenario. Through a comprehensive quality and human-friendliness evaluation of our framework's explanations, we prove high content quality through strong correlations with ground-truth explanations (Spearman rank correlation=0.92) and improved interpretability and human-friendliness to non-experts through a user study (N=56). Our overall evaluation confirms trust in LLMs as HCXAI enablers, as our framework bridges the above Gaps by delivering (i) high-quality technical explanations aligned with foundational XAI methods and (ii) clear, efficient, and interpretable human-centered explanations for non-experts.

cs.LG↗

arXiv2024

Variational Pseudo Marginal Methods for Jet Reconstruction in Particle Physics

Reconstructing jets, which provide vital insights into the properties and histories of subatomic particles produced in high-energy collisions, is a main problem in data analyses in collider physics. This intricate task deals with estimating the latent structure of a jet (binary tree) and involves parameters such as particle energy, momentum, and types. While Bayesian methods offer a natural approach for handling uncertainty and leveraging prior knowledge, they face significant challenges due to the super-exponential growth of potential jet topologies as the number of observed particles increases. To address this, we introduce a Combinatorial Sequential Monte Carlo approach for inferring jet latent structures. As a second contribution, we leverage the resulting estimator to develop a variational inference algorithm for parameter learning. Building on this, we introduce a variational family using a pseudo-marginal framework for a fully Bayesian treatment of all variables, unifying the generative model with the inference process. We illustrate our method's effectiveness through experiments using data generated with a collider physics generative model, highlighting superior speed and accuracy across a range of tasks.

cs.LG↗

arXiv2021

The Quantum Trellis: A classical algorithm for sampling the parton shower with interference effects

Simulations of high-energy particle collisions, such as those used at the Large Hadron Collider, are based on quantum field theory; however, many approximations are made in practice. For example, the simulation of the parton shower, which gives rise to objects called `jets', is based on a semi-classical approximation that neglects various interference effects. While there is a desire to incorporate interference effects, new computational techniques are needed to cope with the exponential growth in complexity associated to quantum processes. We present a classical algorithm called the quantum trellis to efficiently compute the un-normalized probability density over N-body phase space including all interference effects, and we pair this with an MCMC-based sampling strategy. This provides a potential path forward for classical computers and a strong baseline for approaches based on quantum computing.

hep-ph↗

arXiv2021

Reframing Jet Physics with New Computational Methods

We reframe common tasks in jet physics in probabilistic terms, including jet reconstruction, Monte Carlo tuning, matrix element - parton shower matching for large jet multiplicity, and efficient event generation of jets in complex, signal-like regions of phase space. We also introduce Ginkgo, a simplified, generative model for jets, that facilitates research into these tasks with techniques from statistics, machine learning, and combinatorial optimization. We review some of the recent research in this direction that has been enabled with Ginkgo. We show how probabilistic programming can be used to efficiently sample the showering process, how a novel trellis algorithm can be used to efficiently marginalize over the enormous number of clustering histories for the same observed particles, and how dynamic programming, A* search, and reinforcement learning can be used to find the maximum likelihood clustering in this enormous search space. This work builds bridges with work in hierarchical clustering, statistics, combinatorial optmization, and reinforcement learning.

hep-ph↗

arXiv2021

Exact and Approximate Hierarchical Clustering Using A*

Hierarchical clustering is a critical task in numerous domains. Many approaches are based on heuristics and the properties of the resulting clusterings are studied post hoc. However, in several applications, there is a natural cost function that can be used to characterize the quality of the clustering. In those cases, hierarchical clustering can be seen as a combinatorial optimization problem. To that end, we introduce a new approach based on A* search. We overcome the prohibitively large search space by combining A* with a novel \emph{trellis} data structure. This combination results in an exact algorithm that scales beyond previous state of the art, from a search space with $10^{12}$ trees to $10^{15}$ trees, and an approximate algorithm that improves over baselines, even in enormous search spaces that contain more than $10^{1000}$ trees. We empirically demonstrate that our method achieves substantially higher quality results than baselines for a particle physics use case and other clustering benchmarks. We describe how our method provides significantly improved theoretical bounds on the time and space complexity of A* for clustering.

cs.LG↗

arXiv2020

Hierarchical clustering in particle physics through reinforcement learning

Particle physics experiments often require the reconstruction of decay patterns through a hierarchical clustering of the observed final-state particles. We show that this task can be phrased as a Markov Decision Process and adapt reinforcement learning algorithms to solve it. In particular, we show that Monte-Carlo Tree Search guided by a neural policy can construct high-quality hierarchical clusterings and outperform established greedy and beam search baselines.

cs.AI↗

arXiv2020

Data Structures & Algorithms for Exact Inference in Hierarchical Clustering

Hierarchical clustering is a fundamental task often used to discover meaningful structures in data, such as phylogenetic trees, taxonomies of concepts, subtypes of cancer, and cascades of particle decays in particle physics. Typically approximate algorithms are used for inference due to the combinatorial number of possible hierarchical clusterings. In contrast to existing methods, we present novel dynamic-programming algorithms for \emph{exact} inference in hierarchical clustering based on a novel trellis data structure, and we prove that we can exactly compute the partition function, maximum likelihood hierarchy, and marginal probabilities of sub-hierarchies and clusters. Our algorithms scale in time and space proportional to the powerset of $N$ elements which is super-exponentially more efficient than explicitly considering each of the (2N-3)!! possible hierarchies. Also, for larger datasets where our exact algorithms become infeasible, we introduce an approximate algorithm based on a sparse trellis that compares well to other benchmarks. Exact methods are relevant to data analyses in particle physics and for finding correlations among gene expression in cancer genomics, and we give examples in both areas, where our algorithms outperform greedy and beam search baselines. In addition, we consider Dasgupta's cost with synthetic data.

cs.DS↗

arXiv2018

Pulling Out All the Tops with Computer Vision and Deep Learning

We apply computer vision with deep learning -- in the form of a convolutional neural network (CNN) -- to build a highly effective boosted top tagger. Previous work (the "DeepTop" tagger of Kasieczka et al) has shown that a CNN-based top tagger can achieve comparable performance to state-of-the-art conventional top taggers based on high-level inputs. Here, we introduce a number of improvements to the DeepTop tagger, including architecture, training, image preprocessing, sample size and color pixels. Our final CNN top tagger outperforms BDTs based on high-level inputs by a factor of $\sim 2$--3 or more in background rejection, over a wide range of tagging efficiencies and fiducial jet selections. As reference points, we achieve a QCD background rejection factor of 500 (60) at 50\% top tagging efficiency for fully-merged (non-merged) top jets with $p_T$ in the 800--900 GeV (350--450 GeV) range. Our CNN can also be straightforwardly extended to the classification of other types of jets, and the lessons learned here may be useful to others designing their own deep NNs for LHC applications.

hep-ph↗

arXiv2017

Cornering Natural SUSY at LHC Run II and Beyond

We derive the latest constraints on various simplified models of natural SUSY with light higgsinos, stops and gluinos, using a detailed and comprehensive reinterpretation of the most recent 13 TeV ATLAS and CMS searches with $\sim 15$ fb$^{-1}$ of data. We discuss the implications of these constraints for fine-tuning of the electroweak scale. While the most "vanilla" version of SUSY (the MSSM with $R$-parity and flavor-degenerate sfermions) with 10% fine-tuning is ruled out by the current constraints, models with decoupled valence squarks or reduced missing energy can still be fully natural. However, in all of these models, the mediation scale must be extremely low ($<100$ TeV). We conclude by considering the prospects for the high-luminosity LHC era, where we expect the current limits on particle masses to improve by up to $\sim 1$ TeV, and discuss further model-building directions for natural SUSY that are motivated by this work.

hep-ph↗

arXiv2016

Dark Matter and the Higgs in Natural SUSY

Null results from dark matter (DM) direct detection experiments and the 125 GeV Higgs both pose serious challenges to minimal supersymmetry. In this paper, we propose a simple extension of the MSSM that economically solves both problems: a "dark sector" consisting of a singlet and a pair of $SU(2)$ doublets. Loops of the dark sector fields help lift the Higgs mass to 125 GeV consistent with naturalness, while the lightest fermion in the dark sector can be viable thermal relic DM, provided that it is mostly singlet. The DM relic abundance is controlled by s-wave annihilation to tops and Higgsinos, leading to a tight relation between the relic abundance and the spin-dependent direct detection cross section. As a result, the model will be fully probed by the next generation of direct detection experiments. Finally we discuss the discovery potential at LHC Run II.

hep-ph↗

arXiv2015

Revealing Compressed Stops Using High-Momentum Recoils

Searches for supersymmetric top quarks at the LHC have been making great progress in pushing sensitivity out to higher mass, but are famously plagued by gaps in coverage around lower-mass regions where the decay phase space is closing off. Within the common stop-NLSP / neutralino-LSP simplified model, the line in the mass plane where there is just enough phase space to produce an on-shell top quark remains almost completely unconstrained. Here, we show that is possible to define searches capable of probing a large patch of this difficult region, with S/B ~ 1 and significances often well beyond 5 sigma. The basic strategy is to leverage the large energy gain of LHC Run 2, leading to a sizable population of stop pair events recoiling against a hard jet. The recoil not only re-establishes a MET signature, but also leads to a distinctive anti-correlation between the MET and the recoil jet transverse vectors when the stops decay all-hadronically. Accounting for jet combinatorics, backgrounds, and imperfections in MET measurements, we estimate that Run 2 will already start to close the gap in exclusion sensitivity with the first few 10s of inverse-fb. By 300/fb, exclusion sensitivity may extend from stop masses of 550 GeV on the high side down to below 200 GeV on the low side, approaching the "stealth" point at m(stop) = m(top) and potentially overlapping with limits from top pair cross section and spin correlation measurements.

hep-ph↗

arXiv2013

Deep inelastic scattering structure functions of holographic spin-1 hadrons with $N_f \geq 1$

Two-point current correlation functions of the large $N$ limit of supersymmetric and non-supersymmetric Yang-Mills theories at strong coupling are investigated in terms of their string theory dual models with quenched flavors. We consider non-Abelian global symmetry currents, which allow one to investigate vector mesons with $N_f > 1$. From the correlation functions we construct the deep inelastic scattering hadronic tensor of spin-one mesons, obtaining the corresponding eight structure functions for polarized vector mesons. We obtain several relations among the structure functions. Relations among some of their moments are also derived. Aspects of the sub-leading contributions in the $1/N$ and $N_f/N$ expansions are discussed. At leading order we find a universal behavior of the hadronic structure functions.

hep-th↗

arXiv2011

Deep Inelastic Scattering from Holographic Spin-One Hadrons

We study deep inelastic scattering structure functions from hadrons using different holographic dual models which describe the strongly coupled regime of gauge theories in the large $N$ limit. Particularly, we consider scalar and vector mesons obtained from holographic descriptions with fundamental degrees of freedom, corresponding to ${\cal {N}}=2$ supersymmetric and non-supersymmetric Yang-Mills theories. We explicitly obtain analytic expressions for the full set of eight structure functions, i.e., $F_1$, $F_2$, $g_1$, $g_2$, $b_1$, $b_2$, $b_3$, $b_4$, arising from the standard decomposition of the hadronic tensor of spin-one hadrons. We obtain the relations $2 F_1 = F_2$ and $2 b_1 = b_2$. In addition, we find $b_1 \sim {\cal {O}}(F_1)$ as suggested by Hoodbhoy, Jaffe and Manohar for vector mesons. Also, we find new relations among some of these structure functions.

hep-th↗