arXiv subjects

Howard Bondell

Publications and source records attributed to Howard Bondell.

At least 19 recordsLinked to original sources

arXiv2026

TimeLAVA: Learning-Agnostic Valuation for Time Series Data

Data valuation quantifies the intrinsic quality of individual samples to enable principled data curation, quality control, and robust learning. For time series in critical domains such as healthcare, finance, and industrial monitoring, effective valuation methods are essential yet fundamentally lacking. Existing approaches are either model-dependent, limiting their generalizability, or designed for i.i.d. data and thus fail to capture temporal dependencies, multi-scale patterns, and non-stationary dynamics inherent to sequential data. We introduce TimeLAVA, a learning-agnostic framework that values temporal segments by their marginal contribution to minimizing distributional discrepancy between evaluated and reference data. At its core is a novel Selective Wavelet-based Wasserstein discrepancy combining multi-scale wavelet transforms for temporal localization with unbalanced optimal transport for robustness to distributional shifts. Segment values are efficiently computed via sensitivity analysis without requiring model training and aggregated into point-wise scores. We provide theoretical guarantees linking valuation to model-agnostic generalization and prove bounded sensitivity to outlier contamination. Extensive experiments across anomaly detection, data pruning, and label noise detection demonstrate that TimeLAVA produces significantly more informative value scores than existing methods on diverse real-world datasets.

stat.ML↗

arXiv2026

Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting

Causal discovery aims to uncover causal structures from observational data, which is crucial for real-world decision-making. However, different causal discovery algorithms can produce divergent results that conflict with each other, complicating the identification of accurate causal graphs. Traditional approaches rely on numerical values and statistical assumptions, often ignoring rich domain-specific information, such as feature descriptions, which could also help structure learning. While recent works explore using Large Language Models (LLMs) to infer causal relations via direct queries, such methods can be unreliable due to a lack of alignment with the actual data. To address these limitations, we propose Causal Ensemble Agent (CEA), a novel framework that aggregates structural insights from statistical discovery experts across different graph levels via linear opinion pooling, and uses an LLM as a meta-referee to dynamically reweight experts when the aggregated confidence is close to the decision boundary, thereby composing an improved and more complete causal graph. Extensive experiments on both synthetic and real-world datasets demonstrate that CEA achieves the strongest overall performance across a wide range of causal discovery methods, highlighting the effectiveness of using LLMs for meta-analysis in causal discovery.

cs.LG↗

arXiv2026

Bayesian Inference of Contextual Bandit Policies via Empirical Likelihood

Policy inference plays an essential role in the contextual bandit problem. In this paper, we use empirical likelihood to develop a Bayesian inference method for the joint analysis of multiple contextual bandit policies in finite sample regimes. The proposed inference method is robust to small sample sizes and is able to provide accurate uncertainty measurements for policy value evaluation. In addition, it allows for flexible inferences on policy comparison with full uncertainty quantification. We demonstrate the effectiveness of the proposed inference method using Monte Carlo simulations and its application to an adolescent body mass index data set.

stat.ML↗

arXiv2025

Power-divergence copulas: A new class of Archimedean copulas, with an insurance application

This paper demonstrates that, under a particular convention, the convex functions that characterise the phi divergences also generate Archimedean copulas in at least two dimensions. As a special case, we develop the family of Archimedean copulas associated with the important family of power divergences, which we call the power-divergence copulas. The properties of the family are extensively studied, including the subfamilies that are absolutely continuous or have a singular component, the ordering of the family, limiting cases (i.e., the Frechet-Hoeffding lower bound and Frechet-Hoeffding upper bound), the Kendall's tau and tail-dependence coefficients, and cases that extend to three or more dimensions. In an illustrative application, the power-divergence copulas are used to model a Danish fire insurance dataset. It is shown that the power-divergence copulas provide an adequate fit to the bivariate distribution of two kinds of fire-related losses claimed by businesses, while several benchmarks (a suite of well known Archimedean, extreme-value, and elliptical copulas) do not.

stat.ME↗

arXiv2025

Mathematical Modelling and Optimisation of Athletic Performance: Tapering and Periodisation

We conduct a mathematical optimization of the training impulse profile to maximize performance for two seminal athletic performance models: the Banister et al. (1975) Fitness--Fatigue Impulse Response Model and the Busso (2003) Variable Dose--Response Model. We discuss discrepancies in both the quantitative and qualitative aspects of the optimized training impulse profiles compared to what is physically plausible and relative to common training practices recommended in the empirical sports science literature, such as periodization and tapering. We analytically prove that, under the Banister formulation, the optimal training strategy always consists of sustained maximal training, followed by the complete cessation of training prior to the prioritized performance date, and therefore does not yield periodization, or tapering beyond this trivial form. This highlights a gap between theoretical prediction and empirically supported practice, underscoring the need for models that incorporate additional physiological effects. We then propose a set of illustrative and interpretable nonlinear modifications in the magnitude and time response to training in the Fitness--Fatigue Impulse Response model such that the optimized training impulse profile demonstrates these qualities.

q-bio.QM↗

arXiv2025

Generalized Power Priors for Improved Bayesian Inference with Historical Data

The power prior is a class of informative priors designed to incorporate historical data alongside current data in a Bayesian framework. It includes a power parameter that controls the influence of historical data, providing flexibility and adaptability. A key property of the power prior is that the resulting posterior minimizes a linear combination of KL divergences between two pseudo-posterior distributions: one ignoring historical data and the other fully incorporating it. We extend this framework by identifying the posterior distribution as the minimizer of a linear combination of Amari's $\alpha$-divergence, a generalization of KL divergence. We show that this generalization can lead to improved performance by allowing for the data to adapt to appropriate choices of the $\alpha$ parameter. Theoretical properties of this generalized power posterior are established, including behavior as a generalized geodesic on the Riemannian manifold of probability distributions, offering novel insights into its geometric interpretation.

stat.ML↗

arXiv2025

Theoretical and Practical Analysis of Fr\'echet Regression via Comparison Geometry

Fr\'echet regression extends classical regression methods to non-Euclidean metric spaces, enabling the analysis of data relationships on complex structures such as manifolds and graphs. This work establishes a rigorous theoretical analysis for Fr\'echet regression through the lens of comparison geometry which leads to important considerations for its use in practice. The analysis provides key results on the existence, uniqueness, and stability of the Fr\'echet mean, along with statistical guarantees for nonparametric regression, including exponential concentration bounds and convergence rates. Additionally, insights into angle stability reveal the interplay between curvature of the manifold and the behavior of the regression estimator in these non-Euclidean contexts. Empirical experiments validate the theoretical findings, demonstrating the effectiveness of proposed hyperbolic mappings, particularly for data with heteroscedasticity, and highlighting the practical usefulness of these results.

stat.ML↗

arXiv2024

Preserving Angles Improves Feature Distillation

Knowledge distillation methods compress models by training a student network using the classification outputs of a high quality teacher model, but can fail to effectively transfer the properties of computer vision foundation models from the teacher to the student. While it has been recently shown that feature distillation$\unicode{x2013}$where a teacher model's output features are replicated instead$\unicode{x2013}$can reproduce performance for foundation models across numerous downstream tasks, they fall short in matching critical properties such as robustness and out-of-distribution (OOD) detection performance. This paper overcomes this shortcoming by introducing Cosine-similarity Preserving Compression (CosPress), a feature distillation technique that learns a mapping to compress the latent space of the teacher model into the smaller latent space of the student, by preserving the cosine similarities between image embeddings. This enables direct optimisation of the student network and produces a more faithful reproduction of the teacher's properties. It is shown that distillation with CosPress on a variety of datasets, including ImageNet, produces more accurate models with greater performance on generalisability, robustness and OOD detection benchmarks, and that this technique provides a competitive pathway for training highly performant lightweight models on small datasets. Code is available at github.com/emannix/cospress.

cs.CV↗

arXiv2024

Test-Time Augmentation Meets Variational Bayes

Data augmentation is known to contribute significantly to the robustness of machine learning models. In most instances, data augmentation is utilized during the training phase. Test-Time Augmentation (TTA) is a technique that instead leverages these data augmentations during the testing phase to achieve robust predictions. More precisely, TTA averages the predictions of multiple data augmentations of an instance to produce a final prediction. Although the effectiveness of TTA has been empirically reported, it can be expected that the predictive performance achieved will depend on the set of data augmentation methods used during testing. In particular, the data augmentation methods applied should make different contributions to performance. That is, it is anticipated that there may be differing degrees of contribution in the set of data augmentation methods used for TTA, and these could have a negative impact on prediction performance. In this study, we consider a weighted version of the TTA based on the contribution of each data augmentation. Some variants of TTA can be regarded as considering the problem of determining the appropriate weighting. We demonstrate that the determination of the coefficients of this weighted TTA can be formalized in a variational Bayesian framework. We also show that optimizing the weights to maximize the marginal log-likelihood suppresses candidates of unwanted data augmentations at the test phase.

stat.ML↗

arXiv2024

Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds

The density ratio of two probability distributions is one of the fundamental tools in mathematical and computational statistics and machine learning, and it has a variety of known applications. Therefore, density ratio estimation from finite samples is a very important task, but it is known to be unstable when the distributions are distant from each other. One approach to address this problem is density ratio estimation using incremental mixtures of the two distributions. We geometrically reinterpret existing methods for density ratio estimation based on incremental mixtures. We show that these methods can be regarded as iterating on the Riemannian manifold along a particular curve between the two probability distributions. Making use of the geometry of the manifold, we propose to consider incremental density ratio estimation along generalized geodesics on this manifold. To achieve such a method requires Monte Carlo sampling along geodesics via transformations of the two distributions. We show how to implement an iterative algorithm to sample along these geodesics and show how changing the distances along the geodesic affect the variance and accuracy of the estimation of the density ratio. Our experiments demonstrate that the proposed approach outperforms the existing approaches using incremental mixtures that do not take the geometry of the

stat.ML↗

arXiv2024

ComFe: An Interpretable Head for Vision Transformers

Interpretable computer vision models explain their classifications through comparing the distances between the local embeddings of an image and a set of prototypes that represent the training data. However, these approaches introduce additional hyper-parameters that need to be tuned to apply to new datasets, scale poorly, and are more computationally intensive to train in comparison to black-box approaches. In this work, we introduce Component Features (ComFe), a highly scalable interpretable-by-design image classification head for pretrained Vision Transformers (ViTs) that can obtain competitive performance in comparison to comparable non-interpretable methods. To our knowledge, ComFe is the first interpretable head and unlike other interpretable approaches can be readily applied to large-scale datasets such as ImageNet-1K. Additionally, ComFe provides improved robustness and outperforms previous interpretable approaches on key benchmark datasets while using a consistent set of hyperparameters and without finetuning the pretrained ViT backbone. With only global image labels and no segmentation or part annotations, ComFe can identify consistent component features within an image and determine which of these features are informative in making a prediction. Code is available at github.com/emannix/comfe-component-features.

cs.CV↗

arXiv2023

A Mixture of Exemplars Approach for Efficient Out-of-Distribution Detection with Foundation Models

One of the early weaknesses identified in deep neural networks trained for image classification tasks was their inability to provide low confidence predictions on out-of-distribution (OOD) data that was significantly different from the in-distribution (ID) data used to train them. Representation learning, where neural networks are trained in specific ways that improve their ability to detect OOD examples, has emerged as a promising solution. However, these approaches require long training times and can add additional overhead to detect OOD examples. Recent developments in Vision Transformer (ViT) foundation models$\unicode{x2013}$large networks trained on large and diverse datasets with self-supervised approaches$\unicode{x2013}$also show strong performance in OOD detection, and could address these challenges. This paper presents Mixture of Exemplars (MoLAR), an efficient approach to tackling OOD detection challenges that is designed to maximise the benefit of training a classifier with a high quality, frozen, pretrained foundation model backbone. MoLAR provides strong OOD detection performance when only comparing the similarity of OOD examples to the exemplars, a small set of images chosen to be representative of the dataset, leading to significantly reduced overhead for OOD detection inference over other methods that provide best performance when the full ID dataset is used. Extensive experiments demonstrate the improved OOD detection performance of MoLAR in comparison to comparable approaches in both supervised and semi-supervised settings, and code is available at github.com/emannix/molar-mixture-of-exemplars.

cs.CV↗

arXiv2023

Adaptive sampling method to monitor low-risk pathways with limited surveillance resources

The rise of globalisation has led to a sharp increase in international trade, with high volumes of containers, goods and items moving across the world. Unfortunately, these trade pathways also facilitate the movement of unwanted pests, weeds, diseases, and pathogens. Each item could contain biosecurity risk material, but it is impractical to inspect every item. Instead, inspection efforts typically focus on high risk items. However, low risk does not imply no risk. It is crucial to monitor the low risk pathways to ensure that they are and remain low risk. To do so, many approaches would seek to estimate the risk to some precision, but the lower the risk, the more samples needed to estimate the risk. On a low-risk pathway that can be afforded more limited inspection resources, it makes more sense to assign fewer samples to the lower risk activities. We approach the problem by introducing two thresholds. Our method focuses on letting us know whether the risk is below certain thresholds, rather than estimating the risk precisely. This method also allows us to detect a significant change in risk. Our approach typically requires less sampling than previous methods, while still providing evidence to regulators to help them efficiently and effectively allocate inspection effort.

stat.AP↗

arXiv2023

FedDAG: Federated DAG Structure Learning

To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server. However, due to the consideration of privacy protection, data owners gradually refuse to share their personalized raw data to avoid private information leakage, making this task more troublesome by cutting off the first step. Thus, a puzzle arises: \textit{how do we discover the underlying DAG structure from decentralized data?} In this paper, focusing on the additive noise models (ANMs) assumption of data generation, we take the first step in developing a gradient-based learning framework named FedDAG, which can learn the DAG structure without directly touching the local data and also can naturally handle the data heterogeneity. Our method benefits from a two-level structure of each local model. The first level structure learns the edges and directions of the graph and communicates with the server to get the model information from other clients during the learning procedure, while the second level structure approximates the mechanisms among variables and personally updates on its own data to accommodate the data heterogeneity. Moreover, FedDAG formulates the overall learning task as a continuous optimization problem by taking advantage of an equality acyclicity constraint, which can be solved by gradient descent methods to boost the searching efficiency. Extensive experiments on both synthetic and real-world datasets verify the efficacy of the proposed method.

cs.LG↗

arXiv2023

MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models

State-of-the-art causal discovery methods usually assume that the observational data is complete. However, the missing data problem is pervasive in many practical scenarios such as clinical trials, economics, and biology. One straightforward way to address the missing data problem is first to impute the data using off-the-shelf imputation methods and then apply existing causal discovery methods. However, such a two-step method may suffer from suboptimality, as the imputation algorithm may introduce bias for modeling the underlying data distribution. In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations. Focusing mainly on the assumptions of ignorable missingness and the identifiable additive noise models (ANMs), MissDAG maximizes the expected likelihood of the visible part of observations under the expectation-maximization (EM) framework. In the E-step, in cases where computing the posterior distributions of parameters in closed-form is not feasible, Monte Carlo EM is leveraged to approximate the likelihood. In the M-step, MissDAG leverages the density transformation to model the noise distributions with simpler and specific formulations by virtue of the ANMs and uses a likelihood-based causal discovery algorithm with directed acyclic graph constraint. We demonstrate the flexibility of MissDAG for incorporating various causal discovery algorithms and its efficacy through extensive simulations and real data experiments.

cs.LG↗

arXiv2022

GLM for partially pooled categorical predictors with a case study in biosecurity

National governments use border information to efficiently manage the biosecurity risk presented by travel and commerce. In the Australian border biosecurity system, data about cargo consignments are collected from records of directions: that is, the records of actions taken by the biosecurity regulator. This data collection is complicated by the way directions for a given entry are recorded. An entry is a collection of import lines where each line is a single type of item or commodity. Analysis is simple when the data are recorded in line mode: the directions are recorded individually for each line. The challenge comes when data are recorded in container mode, because the same direction is recorded against each line in the entry. In other words, if at least one line in an entry has a non-compliant inspection result, then all lines in that entry are recorded as non-compliant. Therefore, container mode data creates a challenge for estimating the probability that certain items are non-compliant, because matching the records of non-compliance to the line information is impossible. We develop a statistical model to use container mode data to help inform biosecurity risk of items. We use asymptotic analysis to estimate the value of container mode data compared to line mode data, do a simulation study to verify that we can accurately estimate parameters in a large dataset, and we apply our methods to a real dataset, for which important information about the risk of non-compliance is recovered using the new model.

stat.AP↗

arXiv2022

Sparse high-dimensional linear regression with a partitioned empirical Bayes ECM algorithm

Bayesian variable selection methods are powerful techniques for fitting and inferring on sparse high-dimensional linear regression models. However, many are computationally intensive or require restrictive prior distributions on model parameters. In this paper, we proposed a computationally efficient and powerful Bayesian approach for sparse high-dimensional linear regression. Minimal prior assumptions on the parameters are required through the use of plug-in empirical Bayes estimates of hyperparameters. Efficient maximum a posteriori (MAP) estimation is completed through a Parameter-Expanded Expectation-Conditional-Maximization (PX-ECM) algorithm. The PX-ECM results in a robust computationally efficient coordinate-wise optimization which -- when updating the coefficient for a particular predictor -- adjusts for the impact of other predictor variables. The completion of the E-step uses an approach motivated by the popular two-group approach to multiple testing. The result is a PaRtitiOned empirical Bayes Ecm (PROBE) algorithm applied to sparse high-dimensional linear regression, which can be completed using one-at-a-time or all-at-once type optimization. We compare the empirical properties of PROBE to comparable approaches with numerous simulation studies and analyses of cancer cell drug responses. The proposed approach is implemented in the R package probe.

stat.ME↗

arXiv2022

Temporal and spectral governing dynamics of Australian hydrological streamflow time series

We use new and established methodologies in multivariate time series analysis to study the dynamics of 414 Australian hydrological stations' streamflow. First, we analyze our collection of time series in the temporal domain, and compare the similarity in hydrological stations' candidate trajectories. Then, we introduce a Whittle Likelihood-based optimization framework to study the collective similarity in periodic phenomena among our collection of stations. Having identified noteworthy similarity in the temporal and spectral domains, we introduce an algorithmic procedure to estimate a governing hydrological streamflow process across Australia. To determine the stability of such behaviours over time, we then study the evolution of the governing dynamics and underlying time series with time-varying applications of principal components analysis (PCA) and spectral analysis.

stat.AP↗