|
Probing and graph coloring techniques for trace estimation in Lattice QCD
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00394v1 Announce Type: cross Abstract: The computation of $\mathrm{Tr}[D^{-1}]$, where $D$ is the Wilson-Dirac matrix of Lattice QCD, is a fundamental and computationally demanding task with applications to disconnected hadronic correlation functions. Since $D^{-1}$ is a dense matrix of prohibitive size, its trace cannot be computed exactly, and one must resort to stochastic estimation via the Hutchinson estimator. The variance ....
|
|
arXiv:2606.00442v1 Announce Type: cross Abstract: Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep networks. Surprisingly, no previous work has exploited the curvature constraints that arise from well known weight-space symmetries in loss landscapes. By analytically averaging over group actions that leave the loss invariant, we construct struc....
|
|
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00467v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions. We investigate three dimensions of this interaction: (1) how an LLM's familiarity with data and task definitions affects performance, (2) the extent to which additional information in pro....
|
|
Constructive interpolation and generalization rates for neural ODEs: a control perspective
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00469v1 Announce Type: cross Abstract: We study supervised regression with neural ODEs (NODEs) from a control-theoretic perspective to derive explicit population-risk bounds. We focus on a widely used class of non-autonomous models with constant parameters and explicit time dependence, which we call semi-autonomous NODEs (SA-NODEs). We constructively prove that SA-NODEs are capable of \emph{exact} interpolation of admissible fin....
|
|
arXiv:2606.00480v1 Announce Type: cross Abstract: Continuous data assimilation seeks to estimate the state of a dynamical system from partial observations. In many applications, however, the state dynamics are unknown or prohibitively expensive to simulate at the required resolution, leading to model error. Motivated by this challenge and the increasing adoption of machine learning surrogates in data assimilation, this paper develops a uni....
|
|
Stochastic Analysis of Cybersecurity Defense Strategies Under Single Attack Scenario
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00481v1 Announce Type: cross Abstract: This research presents a novel stochastic framework for proactive cybersecurity defense timing under a single attack scenario. The approach models the defense process as a continuous observation mechanism in which the defense instant and the subsequent observation slot follow independent exponential distributions. Laplace-Carson transforms combined with first-excess theory yield the joint d....
|
|
arXiv:2606.00500v1 Announce Type: cross Abstract: We present a simple and efficient algorithm for robust approximate message passing (AMP) in the spiked matrix setting. In particular, let $\varepsilon$ be a sufficiently small constant, and suppose that $X \in \mathbb R^{n \times n}$ is a Gaussian matrix with a planted rank-$1$ spike, and $E \in \mathbb R^{n \times n}$ is an adversarially chosen matrix supported on an $\varepsilon n \times ....
|
|
Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00512v1 Announce Type: cross Abstract: In many modern machine learning pipelines, abundant pretrained representations serve as noisy proxy covariates, while task-specific labels remain scarce. We study semi-supervised regression in this setting, and propose a simple two stage estimator that learns kernel eigenfeatures from all proxy covariates and fits a ridge predictor on labeled data. We derive finite sample bounds showing tha..
|
|
In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00520v1 Announce Type: cross Abstract: Many stochastic gradient methods are believed not to converge when the noise in stochastic gradients has only a finite $p$-th moment for $p\in\left(1,2\right)$, a setting known as the heavy-tailed noise assumption. However, some recent studies have found that Stochastic Gradient Descent ($\textsf{SGD}$), without any modification to its update rule, can surprisingly converge in expectation f....
|
|
GNMR: Runtime Stability Control for Low-Precision Large Language Model Training
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00539v1 Announce Type: cross Abstract: Training stability is a key bottleneck in low-precision language model training: efficient low-cost paths can still produce short-lived numerical risks at a small set of operators. We formulate this as runtime stability control and present Gradient Norm-to-Mean Ratio (GNMR), a lightweight controller that compares each recoverable unit's current gradient norm with its historical mean. Togeth..
|
|
A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00563v1 Announce Type: cross Abstract: Selection bias is a common and often unavoidable aspect of real-world data that challenges the generalizability of machine learning models. When models trained on biased data are deployed in the broader target population, poor model generalization may lead to real harm, particularly in high-risk settings such as healthcare. This risk highlights the need for practitioners to reliably assess ....
|
|
Looped Transformers with Layer Normalization Provably Learn the Power Method
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00605v1 Announce Type: cross Abstract: Transformers have achieved remarkable success across a wide range of applications, and a growing body of work suggests that part of their strength comes from their ability to learn and execute algorithmic procedures. However, our understanding of how transformers learn such algorithms remains limited, especially in the presence of layer normalization (LN). In this work, we study principal c....
|
|
A Systematic Benchmark of Intraoperative Ultrasound-to-MR Synthesis for Brain Tumour Surgery
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00630v1 Announce Type: cross Abstract: Intraoperative ultrasound (ioUS) is a versatile, cost-effective modality in brain tumour surgery, but its interpretation is difficult: acquisition planes are non-standard, artefacts are modality-specific, and its appearance differs markedly from the preoperative MRI on which surgical-planning tools, segmentation models and the surgeon's experience rely. Synthesising MRI-like images from ioU....
|
|
Multi-Agent Conformal Prediction with Personalized Statistical Validity
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00717v1 Announce Type: cross Abstract: Uncertainty quantification is essential in high-stakes machine learning tasks. However, one of the principled solutions, conformal prediction, faces challenges under limited local calibration data, privacy constraints, and data heterogeneity. In multi-agent settings, existing works do not simultaneously and satisfactorily address these challenges with guarantees either limited to averages a....
|
|
Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deployment
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00741v1 Announce Type: cross Abstract: Transistor scaling is approaching a quantum-mechanical limit, as thin gate oxides induce electron leakage through quantum tunneling. Unlike conventional digital systems, AI inference can tolerate such errors provided their structure is modeled correctly. In this paper, we introduce quantum tunneling-aware machine learning (QTAML). We derive the deployment-time weight-error distribution from....
|
|
Bayesian estimation of spectral parameters of the 6.7-GHz methanol maser G339.884-1.259 from GRAO observations
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.00768v1 Announce Type: cross Abstract: Accurate decomposition of methanol maser spectra is essential for understanding high-mass star-forming regions, especially in complex blended spectra where small differences alter physical interpretation. Conventional Gaussian fitting often fails to capture non-Gaussian structure and lacks uncertainty quantification. We develop a Bayesian spectral decomposition framework using Gaussian, Lor....
|
|
arXiv:2606.01034v1 Announce Type: cross Abstract: We study when LLM judge panels should be calibrated with low-dimensional stackers versus joint output tables under finite human-label budgets. Low-dimensional stackers have small estimation cost but miss interactions, whereas joint-table calibrators can represent interactions but pay for cell counts and unseen patterns. We cast this tradeoff as a finite-calibration regime map and instantiat....
|
|
Non-Vacuous Certification of Transport MCMC via Oscillation-Controlled Normalizing Flows
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01078v1 Announce Type: cross Abstract: Transport MCMC trains a normalizing flow to precondition Metropolis--Hastings proposals, achieving high empirical efficiency on challenging posteriors; yet no prior work produces a numerically non-vacuous, rigorous spectral-gap bound for such samplers. We establish the first such bounds. For independence MH on the banana family we certify (\gamma^\ast = 0.828) at (D = 2) (covering in the or....
|
|
Revisiting Neural Processes via Fourier Transform and Volterra Series
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01172v1 Announce Type: cross Abstract: Modeling unknown latent functions from finite, irregularly sampled measurements is a recurring challenge across science and engineering. Neural processes (NPs), a family of probabilistic functional models, are promising solutions -- especially when endowed with domain-specific symmetries like translation equivariance, which improve sample efficiency and generalization. Yet existing translat....
|
|
Analysis of Ethnic Disparities in Autism Spectrum Disorder among Toddlers
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01217v1 Announce Type: cross Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by challenges in communication and behavior. This study examines the relationship between ethnicity and ASD traits, along with behavioural scores, sex and neonatal jaundice across three ethnic groups: White Europeans, Asians, and Middle Eastern individuals. We perform a logistic regression and show that ethnicity ..
|
|
Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01340v1 Announce Type: cross Abstract: We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic information to justify committed exploitation of the averaging distribution? We answer this question in closed form for Bayesian decision trees (BDTs) with Dirichlet-Multinomial leaf models and a Catalan-exponential tree-size prior (Schetinin&Jakaite, 2025), establishing a complete non-asym..
|
|
Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01432v1 Announce Type: cross Abstract: Accurate modeling of leaf spectral reflectance from physiological and biochemical traits is essential for advancing remote sensing applications in plant science and precision agriculture. Widely used radiative transfer models, such as PROSPECT-PRO, rely on generalized trait-reflectance relationships developed from a wide range of species, which may not fully capture the spectral behavior of....
|
|
Transferring Information Across Interventions in Causal Bayesian Optimization
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01457v1 Announce Type: cross Abstract: Bayesian optimization is a popular way to optimize expensive systems, where every experiment, simulation, or intervention costs time or money. In its standard form, it treats the variables we control as plain inputs to a black box and cannot tell apart mere correlation from a real cause and effect. Causal Bayesian optimization closes part of this gap by using a known causal graph together w....
|
|
The Information Content of Quasar Variability Light Curves: How Well Can we Infer Stochastic Model Parameters?
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01496v1 Announce Type: cross Abstract: Quasar variability, driven by multi-scale physical processing within a relativistic accretion disk, is commonly modelled with stochastic time series models. The simplest of these is the Damped Random Walk (DRW), also known as the Ornstein-Uhlenbeck (OU) process. Here, we demonstrate that, when fitting such a model to quasar light curve data, the mean of the light curve, $\mu$, should not be....
|
|
Fast Generalization after Interpolation via Critically Damped Momentum Optimization
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01521v1 Announce Type: cross Abstract: A central problem in machine learning is that models can achieve near-perfect training performance while generalizing substantially less well to unseen examples. This gap is especially acute in high-dimensional, low-sample regimes, where many interpolating solutions exist and optimization must implicitly select among minima with different generalization properties. Following recent theoreti....
|
|
Semi-Supervised Hyperbolic Hierarchical Clustering with Set-Level Structural Priors
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01525v1 Announce Type: cross Abstract: Semi-supervised hierarchical clustering aims to learn a tree structure consistent with data patterns and user-provided supervision. Supervision is usually given as leaf-level relations, such as pairwise must-link/cannot-link constraints or triplet-wise must-link-before constraints. Although useful for regulating local sample relations, such supervision does not directly indicate which sampl....
|
|
ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01619v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) enables LLM agents to improve continuously from environment rewards, yet the resulting policies do not systematically accumulate reusable strategies that generalize across tasks. Modular skills can provide such reusable strategies, yet existing skill-augmented RL methods decouple skill creation from policy optimization, risking adopting skills that confli....
|
|
arXiv:2606.01650v1 Announce Type: cross Abstract: We consider the problem of estimating the true Sharpe ratio of an asset selected for having the highest observed in-sample Sharpe ratio among many assets. We discuss estimators based on the polyhedral lemma, James Stein shrinkage, debiasing the expected maximum Sharpe ratio, thresholding and empirical Bayes. We test these estimators in simulations, computing bias and root mean square error ....
|
|
arXiv:2606.01655v1 Announce Type: cross Abstract: The Bayesian paradigm offers principled tools for sequential decision-making under uncertainty, but its reliance on a probabilistic model for all parameters can hinder the incorporation of complex structural constraints. We introduce a minimalist Bayesian framework that places a prior only on the location of the optimum, while eliminating nuisance parameters through profile likelihood. This..
|
|
arXiv:2606.01659v1 Announce Type: cross Abstract: This paper explores policy learning from observational data, focusing on a nonlinear welfare criterion in a binary treatment setting. The nonlinear criterion is inspired by scenarios where policymakers prioritize specific population segments. We model this criterion using a utility function that encompasses potential outcomes and intermediate parameters, with the latter capturing higher mom....
|
|
Feature leakage and the identifiability of direct-dependency entropy models of neural activity
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01661v1 Announce Type: cross Abstract: Biological neurons receive thousands of synaptic inputs on branching, electrically excitable dendrites, yet population activity is often modeled with direct input-output rules in which each input contributes independently to a scalar drive. We study what successful prediction by such models does, and does not, reveal about neural computation. For conditional maximum-entropy models that matc....
|
|
HS3: A Descriptive, Interoperable Serialization Standard for Statistical Models in High-Energy Physics
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01760v1 Announce Type: cross Abstract: Statistical models in high-energy physics formally encode the relationship between observed data, physics parameters of interest, and experimental and theoretical uncertainties. Likelihood-based inference is the central tool for precision measurements, effective field theory fits, and cross-analysis combinations. Consequently, there is an increasing need for machine-readable, descriptive, a....
|
|
Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01799v1 Announce Type: cross Abstract: We study $N$-armed stochastic dueling bandits under the Condorcet-winner assumption, where three widely adopted objectives are considered: best-arm identification (BAI), weak regret, and strong regret. We propose Tree-Guided Identify-Then-Exploit (TG-ITE), the first unified framework to tackle all these objectives to our knowledge. Without requiring stronger assumptions, we propose a shared....
|
|
Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01827v1 Announce Type: cross Abstract: Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicitly minimizing the sharpness of the loss landscape, SAM often improves generalization while delivering strong empirical performance. However, SAM and its variants, like most training algorithms, are sensitive to the choice of learning rate, whi....
|
|
Flow-Transformed Implicit Processes for Function-Space Variational Inference
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.01954v1 Announce Type: cross Abstract: Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging because their induced function-space distributions are typically not available in closed form. One practical strategy is to approximate the prior using a finit....
|
|
arXiv:2606.02055v1 Announce Type: cross Abstract: We study exact community recovery in the two-community stochastic block model on $n$ vertices under limited and noisy access to network data. The learner may query a noisy neighborhood oracle that reveals each true neighbor of a queried vertex independently with fixed probability and never returns non-neighbors, subject to a finite query budget. We consider both oracle-only access and a com....
|
|
Decision-calibrated prediction sets for robust power system operations
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.02081v1 Announce Type: cross Abstract: Robust optimization offers a tractable approach to balance operating costs and reliability in power systems dominated by weather-dependent renewable uncertainty, but its performance depends critically on the uncertainty set. Standard data-driven approaches often calibrate uncertainty sets to attain predictive coverage, which can produce unnecessarily large sets and costly operating decision....
|
|
When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.02106v1 Announce Type: cross Abstract: We present a single classification pipeline that combines an Equiangular Tight Frame (ETF) preprocessing stage with a tabular foundation model for in-context inference, applied identically across modalities once data is mapped to fixed vector representations. We evaluate it on 95 datasets spanning seven signal modalities -- vision, audio, speech, text, molecular, time-series, and tabular. T....
|
|
arXiv:2606.02223v1 Announce Type: cross Abstract: Estimating the generative mechanism of large-scale networks is a fundamental challenge in statistical machine learning. It requires the identification of the latent connectivity structure, which is in general an NP-hard combinatorial problem due to the absence of canonical node labels. We address this challenge by allowing for probabilistic couplings, thereby relaxing the assignment problem....
|
|
arXiv:2606.02234v1 Announce Type: cross Abstract: This paper clarifies the identifying assumptions underlying causal inference based on treatment changes rather than treatment levels, and their relationship to conventional identification strategies. We characterize two distinct structural models, with non-nested identifying assumptions, under which treatment-change identification is valid conditional on observed covariates. We demonstrate ....
|
|
Exponential thermalisation of viscous fluids on negatively curved manifolds
-
arxiv.org
-
2 days ago
-
eng
arXiv:2606.02286v1 Announce Type: cross Abstract: The deterministic incompressible Navier-Stokes equations are physically incomplete: any viscous fluid at finite temperature must exhibit thermal fluctuations whose form is dictated by the fluctuation-dissipation relation. We formulate the stochastic Navier-Stokes equations with the kinematically selected deformation Laplacian on compact Riemannian manifolds with strictly negative Ricci curv....
|
|
arXiv:2606.02340v1 Announce Type: cross Abstract: Paired-comparison data are naturally represented by tournaments, where transitivity corresponds to the existence of a global ranking consistent with all pairwise outcomes. Accordingly, the classical Kendall-Smith coefficient of consistency measures deviations from transitivity in a tournament by counting the number of circular triads (directed $3$-cycles). In this paper, we characterize the....
|
|
arXiv:2606.02351v1 Announce Type: cross Abstract: Bayesian optimization (BO) is a popular and effective approach for tuning expensive, noisy experiments, but requires the formulation of an explicit objective function. Preferential BO (PBO) removes this requirement by learning from pairwise human feedback, yet existing methods struggle to efficiently optimize beyond low- and medium-dimensional problems due to their global search approaches.....
|
|
arXiv:2606.02363v1 Announce Type: cross Abstract: We study sequential decision-making in partially observable environments against strategic, adaptive opponents, modeled as partially observable Markov games (POMGs). The central challenge is to learn latent dynamics from partial observations while facing an adversary whose behavior depends on the learner's strategy, making standard regret notions inadequate. We prove that an epoch-based opt....
|