The field of numerical optimization has recently seen a surge in the development of "novel" metaheuristic algorithms, inspired by metaphors derived from natural or human-made processes, which have been widely criticized for obscuring meaningful innovations and failing to distinguish themselves from existing approaches. Aiming to address these concerns, we investigate the applicability of statistical tests for comparing algorithms based on their search behavior. We utilize the cross-match statistical test to compare multivariate distributions and assess the solutions produced by 114 algorithms from the MEALPY library. These findings are incorporated into an empirical analysis aiming to identify algorithms with similar search behaviors.

Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make it challenging to establish the rule of thumb for designing the golden model architecture. In this study, we argue that refining existing advanced models through a universal calibrating strategy can deliver substantial benefits with minimal resource costs, as opposed to elaborating and training a new model from scratch. We first identify a multi-target learning conflict in the calibrating process, which arises when optimizing variables across time steps, leading to the underutilization of the model's learning capabilities. To address this issue, we propose an innovative calibrating strategy called Socket+Plug (SoP). This approach retains an exclusive optimizer and early-stopping monitor for each predicted target within each Plug while keeping the fully trained Socket backbone frozen. The model-agnostic nature of SoP allows it to directly calibrate the performance of any trained deep forecasting models, regardless of their specific architectures. Extensive experiments on various time series benchmarks and a spatio-temporal meteorological ERA5 dataset demonstrate the effectiveness of SoP, achieving up to a 22% improvement even when employing a simple MLP as the Plug (highlighted in Figure 1). Code is available at https://github.com/hanyuki23/SoP.

Extremile regression, as a least squares analog of quantile regression, is potentially useful tool for modeling and understanding the extreme tails of a distribution. However, existing extremile regression methods, as nonparametric approaches, may face challenges in high-dimensional settings due to data sparsity, computational inefficiency, and the risk of overfitting. While linear regression serves as the foundation for many other statistical and machine learning models due to its simplicity, interpretability, and relatively easy implementation, particularly in high-dimensional settings, this paper introduces a novel definition of linear extremile regression along with an accompanying estimation methodology. The regression coefficient estimators of this method achieve $\sqrt{n}$-consistency, which nonparametric extremile regression may not provide. In particular, while semi-supervised learning can leverage unlabeled data to make more accurate predictions and avoid overfitting to small labeled datasets in high-dimensional spaces, we propose a semi-supervised learning approach to enhance estimation efficiency, even when the specified linear extremile regression model may be misspecified. Both simulation studies and real data analyses demonstrate the finite-sample performance of our proposed methods.

We present a novel tuning procedure for random forests (RFs) that improves the accuracy of estimated quantiles and produces valid, relatively narrow prediction intervals. While RFs are typically used to estimate mean responses (conditional on covariates), they can also be used to estimate quantiles by estimating the full distribution of the response. However, standard approaches for building RFs often result in excessively biased quantile estimates. To reduce this bias, our proposed tuning procedure minimizes "quantile coverage loss" (QCL), which we define as the estimated bias of the marginal quantile coverage probability estimate based on the out-of-bag sample. We adapt QCL tuning to handle censored data and demonstrate its use with random survival forests. We show that QCL tuning results in quantile estimates with more accurate coverage probabilities than those achieved using default parameter values or traditional tuning (using MSPE for uncensored data and C-index for censored data), while also reducing the estimated MSE of these coverage probabilities. We discuss how the superior performance of QCL tuning is linked to its alignment with the estimation goal. Finally, we explore the validity and width of prediction intervals created using this method.

Graphical models have been popularly used for capturing conditional independence structure in multivariate data, which are often built upon independent and identically distributed observations, limiting their applicability to complex datasets such as network-linked data. This paper proposes a nonparametric graphical model that addresses these limitations by accommodating heterogeneous graph structures without imposing any specific distributional assumptions. The proposed estimation method effectively integrates network embedding with nonparametric graphical model estimation. It further transforms the graph learning task into solving a finite-dimensional linear equation system by leveraging the properties of vector-valued reproducing kernel Hilbert space. Moreover, theoretical guarantees are established for the proposed method in terms of the estimation consistency and exact recovery of the heterogeneous graph structures. Its effectiveness is also demonstrated through a variety of simulated examples and a real application to the statistician coauthorship dataset.

Inferring protein production kinetics for dividing cells is complicated due to protein inheritance from the mother cell. For instance, fluorescence measurements -- commonly used to assess gene activation -- may reflect not only newly produced proteins but also those inherited through successive cell divisions. In such cases, observed protein levels in any given cell are shaped by its division history. As a case study, we examine activation of the glc3 gene in yeast involved in glycogen synthesis and expressed under nutrient-limiting conditions. We monitor this activity using snapshot fluorescence measurements via flow cytometry, where GFP expression reflects glc3 promoter activity. A naïve analysis of flow cytometry data ignoring cell division suggests many cells are active with low expression. Explicitly accounting for the (non-Markovian) effects of cell division and protein inheritance makes it impossible to write down a tractable likelihood -- a key ingredient in physics-inspired inference, defining the probability of observing data given a model. The dependence on a cell's division history breaks the assumptions of standard (Markovian) master equations, rendering traditional likelihood-based approaches inapplicable. Instead, we adapt conditional normalizing flows (a class of neural network models designed to learn probability distributions) to approximate otherwise intractable likelihoods from simulated data. In doing so, we find that glc3 is mostly inactive under stress, showing that while cells occasionally activate the gene, expression is brief and transient.

Although generative models have made remarkable progress in recent years, their use in critical applications has been hindered by their incapacity to reliably evaluate sample quality. Quality refers to at least two complementary concepts: fidelity and coverage. Current quality metrics often lack reliable, interpretable values due to an absence of calibration or insufficient robustness to outliers. To address these shortcomings, we introduce two novel metrics, Clipped Density and Clipped Coverage. By clipping individual sample contributions and, for fidelity, the radii of nearest neighbor balls, our metrics prevent out-of-distribution samples from biasing the aggregated values. Through analytical and empirical calibration, these metrics exhibit linear score degradation as the proportion of poor samples increases. Thus, they can be straightforwardly interpreted as equivalent proportions of good samples. Extensive experiments on synthetic and real-world datasets demonstrate that Clipped Density and Clipped Coverage outperform existing methods in terms of robustness, sensitivity, and interpretability for evaluating generative models.

Hybrid quantum-classical algorithms like the variational quantum eigensolver (VQE) show promise for quantum simulations on near-term quantum devices, but are often limited by complex objective functions and expensive optimization procedures. Here, we propose Flow-VQE, a generative framework leveraging conditional normalizing flows with parameterized quantum circuits to efficiently generate high-quality variational parameters. By embedding a generative model into the VQE optimization loop through preference-based training, Flow-VQE enables quantum gradient-free optimization and offers a systematic approach for parameter transfer, accelerating convergence across related problems through warm-started optimization. We compare Flow-VQE to a number of standard benchmarks through numerical simulations on molecular systems, including hydrogen chains, water, ammonia, and benzene. We find that Flow-VQE outperforms baseline optimization algorithms, achieving computational accuracy with fewer circuit evaluations (improvements range from modest to more than two orders of magnitude) and, when used to warm-start the optimization of new systems, accelerates subsequent fine-tuning by up to 50-fold compared with Hartree--Fock initialization. Therefore, we believe Flow-VQE can become a pragmatic and versatile paradigm for leveraging generative modeling to reduce the costs of variational quantum algorithms.

Gaussian mixture models (GMMs) are ubiquitous in statistical learning, particularly for unsupervised problems. While full GMMs suffer from the overparameterization of their covariance matrices in high-dimensional spaces, spherical GMMs (with isotropic covariance matrices) certainly lack flexibility to fit certain anisotropic distributions. Connecting these two extremes, we introduce a new family of parsimonious GMMs with piecewise-constant covariance eigenvalue profiles. These extend several low-rank models like the celebrated mixtures of probabilistic principal component analyzers (MPPCA), by enabling any possible sequence of eigenvalue multiplicities. If the latter are prespecified, then we can naturally derive an expectation-maximization (EM) algorithm to learn the mixture parameters. Otherwise, to address the notoriously-challenging issue of jointly learning the mixture parameters and hyperparameters, we propose a componentwise penalized EM algorithm, whose monotonicity is proven. We show the superior likelihood-parsimony tradeoffs achieved by our models on a variety of unsupervised experiments: density fitting, clustering and single-image denoising.

We introduce a new family of toy problems that combine features of linear-regression-style continuous in-context learning (ICL) with discrete associative recall. We pretrain transformer models on sample traces from this toy, specifically symbolically-labeled interleaved state observations from randomly drawn linear deterministic dynamical systems. We study if the transformer models can recall the state of a sequence previously seen in its context when prompted to do so with the corresponding in-context label. Taking a closer look at this task, it becomes clear that the model must perform two functions: (1) identify which system's state should be recalled and apply that system to its last seen state, and (2) continuing to apply the correct system to predict the subsequent states. Training dynamics reveal that the first capability emerges well into a model's training. Surprisingly, the second capability, of continuing the prediction of a resumed sequence, develops much earlier. Via out-of-distribution experiments, and a mechanistic analysis on model weights via edge pruning, we find that next-token prediction for this toy problem involves at least two separate mechanisms. One mechanism uses the discrete symbolic labels to do the associative recall required to predict the start of a resumption of a previously seen sequence. The second mechanism, which is largely agnostic to the discrete symbolic labels, performs a "Bayesian-style" prediction based on the previous token and the context. These two mechanisms have different learning dynamics. To confirm that this multi-mechanism (manifesting as separate phase transitions) phenomenon is not just an artifact of our toy setting, we used OLMo training checkpoints on an ICL translation task to see a similar phenomenon: a decisive gap in the emergence of first-task-token performance vs second-task-token performance.