arXiv subjects

D. B. Emerson

Publications and source records attributed to D. B. Emerson.

15 recordsLinked to original sources

arXiv2026

Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment

Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to reproduce, compare, and extend. Existing evaluations are often tied to custom infrastructure, released as incomplete research code, and conducted primarily in simulation, which limits portability and practical relevance. We present Flower Hub, a platform for publishing, discovering, and executing decentralized and federated applications. We show how it enables reproducible benchmarking by packaging benchmarks as executable, versioned applications with standardized metadata, pinned dependencies, and explicit evaluation workflows. We instantiate this approach with a multi-domain benchmark suite spanning cross-silo and cross-device settings, and including tasks in medical imaging, financial tabular learning, legal instruction tuning, phishing URL detection, and audio tagging. We further demonstrate that the same benchmarking application can run across both simulation and deployment runtimes without changing the application code, enabling unified evaluation across varying learning environments. Beyond model quality, our benchmark design supports system-aware reporting, including runtime and communication metrics. This work advances benchmarking in FL settings from ad hoc code artifacts towards portable, executable, and reusable benchmark applications.

cs.LG↗

arXiv2026

On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics

Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is a rising interest in generating high-quality synthetic proxies for real tabular data as a means of reducing privacy risk and proprietary data exposure. With tabular diffusion models (TDMs) demonstrating leading performance in synthesizing such data, understanding and measuring the privacy risks associated with these models is imperative. Leveraging state-of-the-art membership inference attacks for TDMs in both black- and white-box settings, this work quantifies the impact of training setup, synthesis choices, and attacker knowledge on privacy leakage. Moreover, the results demonstrate that adversaries need not have perfect knowledge of the training setup, identical data distributions, or massive compute resources to construct successful attacks. Finally, the pitfalls associated with applying heuristic privacy metrics, such as distance-to-closest record, are revealed.

cs.LG↗

arXiv2026

An A Posteriori Error Estimator for Electrically Coupled Liquid Crystal Equilibrium Configurations

This paper derives an a posteriori error estimator for the nonlinear first-order optimality conditions associated with the electrically and flexoelectrically coupled Frank-Oseen model of liquid crystals, building on previous results for elastic systems. The estimator is proposed for a penalty approach to imposing the unit-length constraint required by the model. Moreover, theory is proven establishing that the estimator provides a reliable estimate of global approximation error and an efficient measure of local error, suitable for use in adaptive refinement. Numerical experiments demonstrate significant improvements in efficiency with adaptive refinement guided by the proposed estimator in a multilevel, nested-iteration framework and superior physical properties for challenging electrically coupled systems.

math.NA↗

arXiv2026

CAPID: Context-Aware PII Detection for Question-Answering Systems

Detecting personally identifiable information (PII) in user queries is critical for ensuring privacy in question-answering systems. Current approaches mainly redact all PII, disregarding the fact that some of them may be contextually relevant to the user's question, resulting in a degradation of response quality. Large language models (LLMs) might be able to help determine which PII are relevant, but due to their closed source nature and lack of privacy guarantees, they are unsuitable for sensitive data processing. To achieve privacy-preserving PII detection, we propose CAPID, a practical approach that fine-tunes a locally owned small language model (SLM) that filters sensitive information before it is passed to LLMs for QA. However, existing datasets do not capture the context-dependent relevance of PII needed to train such a model effectively. To fill this gap, we propose a synthetic data generation pipeline that leverages LLMs to produce a diverse, domain-rich dataset spanning multiple PII types and relevance levels. Using this dataset, we fine-tune an SLM to detect PII spans, classify their types, and estimate contextual relevance. Our experiments show that relevance-aware PII detection with a fine-tuned SLM substantially outperforms existing baselines in span, relevance and type accuracy while preserving significantly higher downstream utility under anonymization.

cs.CR↗

arXiv2026

Template-Based Probes Are Imperfect Lenses for Counterfactual Bias Evaluation in LLMs

Bias in large language models (LLMs) has many forms, from overt discrimination to implicit stereotypes. Counterfactual bias evaluation is a widely used approach to quantifying bias and often relies on template-based probes that explicitly state group membership. It aims to measure whether the outcome of a task performed by an LLM is invariant to a change in group membership. In this work, we find that template-based probes can introduce systematic distortions in bias measurements. Specifically, we consistently find that such probes suggest that LLMs classify text associated with White race as negative at disproportionately elevated rates. This is observed consistently across a large collection of LLMs, over several diverse template-based probes, and with different classification approaches. We hypothesize that this arises artificially due to linguistic asymmetries present in LLM pretraining data, in the form of markedness, (e.g., Black president vs. president) and templates used for bias measurement (e.g., Black president vs. White president). These findings highlight the need for more rigorous methodologies in counterfactual bias evaluation, ensuring that observed disparities reflect genuine biases rather than artifacts of linguistic conventions.

cs.CL↗

arXiv2025

Adaptive Latent-Space Constraints in Personalized Federated Learning

Federated learning (FL) is an effective and widely used approach to training deep learning models on decentralized datasets held by distinct clients. FL also strengthens both security and privacy protections for training data. Common challenges associated with statistical heterogeneity between distributed datasets have spurred significant interest in personalized FL (pFL) methods, where models combine aspects of global learning with local modeling specific to each client's unique characteristics. This work investigates the efficacy of theoretically supported, adaptive MMD measures in pFL, primarily focusing on the Ditto framework, a state-of-the-art technique for distributed data heterogeneity. The use of such measures significantly improves model performance across a variety of tasks, especially those with pronounced feature heterogeneity. Additional experiments demonstrate that such measures are directly applicable to other pFL techniques and yield similar improvements across a number of datasets. Finally, the results motivate the use of constraints tailored to the various kinds of heterogeneity expected in FL systems.

cs.LG↗

arXiv2025

MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction

Large language models (LLMs) have shown promising performance on tasks that require reasoning, such as text-to-SQL, code generation, and debugging. However, regulatory frameworks with strict privacy requirements constrain their integration into sensitive systems. State-of-the-art LLMs are also proprietary, costly, and resource-intensive, making local deployment impractical. Consequently, utilizing such LLMs often requires sharing data with third-party providers, raising privacy concerns and risking noncompliance with regulations. Although fine-tuned small language models (SLMs) can outperform LLMs on certain tasks and be deployed locally to mitigate privacy concerns, they underperform on more complex tasks such as text-to-SQL translation. In this work, we introduce MaskSQL, a text-to-SQL framework that utilizes abstraction as a privacy protection mechanism to mask sensitive information in LLM prompts. Unlike redaction, which removes content entirely, or generalization, which broadens tokens, abstraction retains essential information while discarding unnecessary details, striking an effective privacy-utility balance for the text-to-SQL task. Moreover, by providing mechanisms to control the privacy-utility tradeoff, MaskSQL facilitates adoption across a broader range of use cases. Our experimental results show that MaskSQL outperforms leading SLM-based text-to-SQL models and achieves performance approaching state-of-the-art LLM-based models, while preserving privacy.

cs.CR↗

arXiv2024

On The Role of Reasoning in the Identification of Subtle Stereotypes in Natural Language

Large language models (LLMs) are trained on vast, uncurated datasets that contain various forms of biases and language reinforcing harmful stereotypes that may be subsequently inherited by the models themselves. Therefore, it is essential to examine and address biases in language models, integrating fairness into their development to ensure that these models do not perpetuate social biases. In this work, we demonstrate the importance of reasoning in zero-shot stereotype identification across several open-source LLMs. Accurate identification of stereotypical language is a complex task requiring a nuanced understanding of social structures, biases, and existing unfair generalizations about particular groups. While improved accuracy is observed through model scaling, the use of reasoning, especially multi-step reasoning, is crucial to consistent performance. Additionally, through a qualitative analysis of select reasoning traces, we highlight how reasoning improves not just accuracy, but also the interpretability of model decisions. This work firmly establishes reasoning as a critical component in automatic stereotype detection and is a first step towards stronger stereotype mitigation pipelines for LLMs.

cs.CL↗

arXiv2024

A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical Datasets

Federated learning (FL) is increasingly being recognized as a key approach to overcoming the data silos that so frequently obstruct the training and deployment of machine-learning models in clinical settings. This work contributes to a growing body of FL research specifically focused on clinical applications along three important directions. First, we expand the FLamby benchmark (du Terrail et al., 2022a) to include a comprehensive evaluation of personalized FL methods and demonstrate substantive performance improvements over the original results. Next, we advocate for a comprehensive checkpointing and evaluation framework for FL to reflect practical settings and provide multiple comparison baselines. To this end, an open-source library aimed at making FL experimentation simpler and more reproducible is released. Finally, we propose an important ablation of PerFCL (Zhang et al., 2022). This ablation results in a natural extension of FENDA (Kim et al., 2016) to the FL setting. Experiments conducted on the FLamby benchmark and GEMINI datasets (Verma et al., 2017) show that the proposed approach is robust to heterogeneous clinical data and often outperforms existing global and personalized FL techniques, including PerFCL.

cs.LG↗

arXiv2018

Error Estimators and Marking Strategies for Electrically Coupled Liquid Crystal Systems

This paper derives a posteriori error estimators for the nonlinear first-order optimality conditions associated with the electrically and flexoelectrically coupled Frank-Oseen model of liquid crystals, building on the results of [14] for elastic systems. Estimators are proposed for both Lagrangian and penalty approaches to imposing the unit-length constraint required by the model. Moreover, theory is proven establishing the penalty method estimator as a reliable estimate of global approximation error and an efficient measure of local error, suitable for use in adaptive refinement. Numerical experiments conducted herein demonstrate significant improvements in both accuracy and efficiency with adaptive refinement guided by the proposed estimators for both constraint formulations. The numerical results also extend the simulations of [14] to include systems with known analytical solutions, confirming the theoretical results and enabling performance comparisons for a selection of established marking strategies. In each case, the adapted grids successfully yield substantial reductions in computational work, comparable or better physical properties, and deliver more uniformly distributed error.

math.NA↗

arXiv2017

A Posteriori Error Estimators for the Frank-Oseen Model of Liquid Crystals

This paper derives a posteriori error estimators for the nonlinear first-order optimality conditions associated with the Frank-Oseen elastic free-energy model of nematic and cholesteric liquid crystals, where the required unit-length constraint is imposed via either a Lagrange multiplier or penalty method. Furthermore, theory establishing the reliability of the proposed error estimator for the penalty method is presented, yielding a concrete upper bound on the approximation error of discrete solutions. The error estimators herein are composed of readily computable quantities on each element of a finite-element mesh, allowing the formulation of an efficient adaptive mesh refinement strategy. Four elastic equilibrium problems are considered to examine the performance of the error estimators and corresponding adaptive mesh refinements against that of a simple uniform refinement scheme. The adapted grids successfully provide significant reductions in computational work while producing solutions that are highly competitive with those of uniform mesh in terms of constraint conformance and computed free energies.

math.NA↗

arXiv2016

A Deflation Technique for Detecting Multiple Liquid Crystal Equilibrium States

Multiple equilibrium states arise in many physical systems, including various types of liquid crystal structures. Having the ability to reliably compute such states enables more accurate physical analysis and understanding of experimental behavior. This paper adapts and extends a deflation technique for the computation of multiple distinct solutions arising in the context of modeling equilibrium configurations of nematic and cholesteric liquid crystals. The deflation method is applied as part of an overall free-energy variational approach and is modified to fit the framework of optimization of a functional with pointwise constraints. It is shown that multigrid methods designed for the undeflated systems may be applied to efficiently solve the linear systems arising in the application of deflation. For the numerical algorithm, the deflation approach is interwoven with nested iteration, creating a dynamic and efficient method that further enables the discovery of distinct solutions. Finally, four numerical experiments are performed demonstrating the efficacy and accuracy of the algorithm in detecting important physical phenomena, including bifurcation and disclination behaviors. The final numerical experiment expands the algorithm to model cholesteric liquid crystals and illustrates the full discovery power of the deflation process.

math.NA↗

arXiv2014

Constrained Optimization for Liquid Crystal Equilibria: Extended Results

This paper investigates energy-minimization finite-element approaches for the computation of nematic liquid crystal equilibrium configurations. We compare the performance of these methods when the necessary unit-length constraint is enforced by either continuous Lagrange multipliers or a penalty functional. Building on previous work in [1,2], the penalty method is derived and the linearizations within the nonlinear iteration are shown to be well-posed under certain assumptions. In addition, the paper discusses the effects of tailored trust-region methods and nested iteration for both formulations. Such methods are aimed at increasing the efficiency and robustness of each algorithms' nonlinear iterations. Three representative, free-elastic, equilibrium problems are considered to examine each method's performance. The first two configurations have analytical solutions and, therefore, convergence to the true solution is considered. The third problem considers more complicated boundary conditions, relevant in ongoing research, simulating surface nano-patterning. A multigrid approach is introduced and tested for a flexoelectrically coupled model to establish scalability for highly complicated applications. The Lagrange multiplier method is found to outperform the penalty method in a number of measures, trust regions are shown to improve robustness, and nested iteration proves highly effective at reducing computational costs.

math.NA↗

arXiv2014

Energy Minimization for Liquid Crystal Equilibrium with Electric and Flexoelectric Effects

This paper outlines an energy-minimization finite-element approach to the modeling of equilibrium configurations for nematic liquid crystals in the presence of internal and external electric fields. The method targets minimization of system free energy based on the electrically and flexoelectrically augmented Frank-Oseen free energy models. The Hessian, resulting from the linearization of the first-order optimality conditions, is shown to be invertible for both models when discretized by a mixed finite-element method under certain assumptions. This implies that the intermediate discrete linearizations are well-posed. A coupled multigrid solver with Vanka-type relaxation is proposed and numerically vetted for approximation of the solution to the linear systems arising in the linearizations. Two electric model numerical experiments are performed with the proposed iterative solver. The first compares the algorithm's solution of a classical Freedericksz transition problem to the known analytical solution and demonstrates the convergence of the algorithm to the true solution. The second experiment targets a problem with more complicated boundary conditions, simulating a nano-patterned surface. In addition, numerical simulations incorporating these nano-patterned boundaries for a flexoelectric model are run with the iterative solver. These simulations verify expected physical behavior predicted by a perturbation model. The algorithm accurately handles heterogeneous coefficients and efficiently resolves configurations resulting from classical and complicated boundary conditions relevant in ongoing research.

physics.comp-ph↗

arXiv2014

An Energy-Minimization Finite-Element Approach for the Frank-Oseen Model of Nematic Liquid Crystals: Continuum and Discrete Analysis

This paper outlines an energy-minimization finite-element approach to the computational modeling of equilibrium configurations for nematic liquid crystals under free elastic effects. The method targets minimization of the system free energy based on the Frank-Oseen free-energy model. Solutions to the intermediate discretized free elastic linearizations are shown to exist generally and are unique under certain assumptions. This requires proving continuity, coercivity, and weak coercivity for the accompanying appropriate bilinear forms within a mixed finite-element framework. Error analysis demonstrates that the method constitutes a convergent scheme. Numerical experiments are performed for problems with a range of physical parameters as well as simple and patterned boundary conditions. The resulting algorithm accurately handles heterogeneous constant coefficients and effectively resolves configurations resulting from complicated boundary conditions relevant in ongoing research.

math.NA↗