Online medical misinformation threatens public health literacy, making format selection crucial for healthcare professionals. This study examined how presentation formats affect engagement in medical communication through two approaches. Study 1 analyzed 40,852 articles from China’s leading health platform, revealing text articles generated higher engagement overall, with format effectiveness varying by specialty: surgical content performed better as text, while psychological content excelled as video. Study 2 tested 240 participants in a 2 × 2 experiment, finding text format enhanced click intention through perceived completeness and accuracy despite increasing cognitive load, while video format boosted arousal and emotional engagement. Social support type moderated these effects. Informational support amplified text advantages while reducing cognitive load. Results advance health communication theory by identifying format-specific psychological pathways and provide evidence-based guidance.

Bilevel optimization has witnessed a resurgence of interest, driven by its critical role in trustworthy and efficient AI applications. Recent focus has been on finding efficient methods with provable convergence guarantees. However, while many prior works have established convergence to stationary points or local minima, obtaining the global optimum of bilevel optimization remains an important yet open problem. The difficulty lies in the fact that unlike many prior non-convex single-level problems, bilevel problems often do not admit a ``benign" landscape, and may indeed have multiple spurious local solutions. Nevertheless, attaining the global optimality is indispensable for ensuring reliability, safety, and cost-effectiveness, particularly in high-stakes engineering applications that rely on bilevel optimization. In this paper, we first explore the challenges of establishing a global convergence theory for bilevel optimization, and present two sufficient conditions for global convergence. We provide {\em algorithm-dependent} proofs to rigorously substantiate these sufficient conditions on two specific bilevel learning scenarios: representation learning and data hypercleaning (a.k.a. reweighting). Experiments corroborate the theoretical findings, demonstrating convergence to global minimum in both cases.

Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose goal is to optimize a pre-defined preference function, subject to the constraint that the model parameters are weakly Pareto optimal. To solve this problem, we convert the multi-objective constraints to a single-objective constraint through a merit function with an easy-to-evaluate gradient, and then, we use a penalty-based reformulation of the bilevel optimization problem. We theoretically establish the properties of the merit function, and the relations of solutions for the penalty reformulation and the constrained formulation. Then we propose algorithms to solve the reformulated single-level problem, and establish its convergence guarantees. We test the method on various synthetic and real-world problems. The results demonstrate the effectiveness of the proposed method in finding preference-guided optimal solutions to the multi-objective problem.

Diffusion models, which iteratively denoise data samples to synthesize high-quality outputs, have achieved empirical success across domains. However, optimizing these models for downstream tasks often involves nested bilevel structures, such as tuning hyperparameters for fine-tuning tasks or noise schedules in training dynamics, where traditional bilevel methods fail due to the infinite-dimensional probability space and prohibitive sampling costs. We formalize this challenge as a generative bilevel optimization problem and address two key scenarios: (1) fine-tuning pre-trained models via an inference-only lower-level solver paired with a sample-efficient gradient estimator for the upper level, and (2) training diffusion model from scratch with noise schedule optimization by reparameterizing the lower-level problem and designing a computationally tractable gradient estimator. Our first-order bilevel framework overcomes the incompatibility of conventional bilevel methods with diffusion processes, offering theoretical grounding and computational practicality. Experiments demonstrate that our method outperforms existing fine-tuning and hyperparameter search baselines.

Bilevel optimization, a hierarchical optimization paradigm, has gained significant attention in a wide range of practical applications, notably in the fine-tuning of generative models. However, due to the nested problem structure, most existing algorithms require either the Hessian vector calculation or the nested loop updates, which are computationally inefficient in large language model (LLM) fine-tuning. In this paper, building upon the fully first-order penalty-based approach, we propose an efficient value function-free (\textsf{PBGD-Free}) algorithm that eliminates the loop of solving the lower-level problem and admits fully single-loop updates. Inspired by the landscape analysis of representation learning-based LLM fine-tuning problem, we propose a relaxed flatness condition for the upper-level function and prove the convergence of the proposed value-function-free algorithm. We test the performance of the proposed algorithm in various applications and demonstrate its superior computational efficiency over the state-of-the-art bilevel methods.

As the economic and environmental costs of training and deploying large vision or language models increase dramatically, analog in-memory computing (AIMC) emerges as a promising energy-efficient solution. However, the training perspective, especially its training dynamic, is underexplored. In AIMC hardware, the trainable weights are represented by the conductance of resistive elements and updated using consecutive electrical pulses. While the conductance changes by a constant in response to each pulse, in reality, the change is scaled by asymmetric and non-linear response functions, leading to a non-ideal training dynamic. This paper provides a theoretical foundation for gradient-based training on AIMC hardware with non-ideal response functions. We demonstrate that asymmetric response functions negatively impact Analog SGD by imposing an implicit penalty on the objective. To overcome the issue, we propose residual learning algorithm, which provably converges exactly to a critical point by solving a bilevel optimization problem. We show that the proposed method can be extended to deal with other hardware imperfections like limited response granularity. As far as we know, it is the first paper to investigate the impact of a class of generic non-ideal response functions. The conclusion is supported by simulations validating our theoretical insights.

Estimating the confidence of large language model (LLM) outputs is essential for real-world applications requiring high user trust. Black-box uncertainty quantification (UQ) methods, relying solely on model API access, have gained popularity due to their practical benefits. In this paper, we examine the implicit assumption behind several UQ methods, which use generation consistency as a proxy for confidence-an idea we formalize as the consistency hypothesis. We introduce three mathematical statements with corresponding statistical tests to capture variations of this hypothesis and metrics to evaluate LLM output conformity across tasks. Our empirical investigation, spanning 8 benchmark datasets and 3 tasks (question answering, text summarization, and text-to-SQL), highlights the prevalence of the hypothesis under different settings. Among the statements, we highlight the ‘Sim-Any’ hypothesis as the most actionable, and demonstrate how it can be leveraged by proposing data-free black-box UQ methods that aggregate similarities between generations for confidence estimation. These approaches can outperform the closest baselines, showcasing the practical value of the empirically observed consistency hypothesis.

Interest in bilevel optimization has grown in recent years, partially due to its relevance for challenging machine-learning problems. Several exciting recent works have been centered around developing efficient gradient-based algorithms that can solve bilevel optimization problems with provable guarantees. However, the existing literature mainly focuses on bilevel problems either without constraints, or featuring only simple constraints that do not couple variables across the upper and lower levels, excluding a range of complex applications. Our paper studies this challenging but less explored scenario and develops a (fully) first-order algorithm, which we term BLOCC, to tackle BiLevel Optimization problems with Coupled Constraints. We establish rigorous convergence theory for the proposed algorithm and demonstrate its effectiveness on two well-known real-world applications - support vector machine (SVM) - based model training and infrastructure planning in transportation networks.

Specialisation, by seeking theoretically deeper explanations or more accurate predictions, is common in the sciences. It typically involves splitting, where one model is further divided into several or even hundreds of narrow-scope models. The Information Systems (IS) literature does not discuss such splitting. On the contrary, many seminal IS studies report that a narrow scope is less strong, less interesting, or less useful than a wider scope. In this commentary, we want to raise the awareness of the IS community that in modern scientific progress, specialisation – an activity that generally narrows the scope and decreases the generalisability of a hypothesis – is important. The philosophy of science discusses such positive developments as splitting and trading off a wide scope in favour of accuracy. Narrowing the scope may increase value, especially in sciences where practical applicability is valued. If the IS community generally prefers a wider scope, then we run the risk of not having the information necessary to understand IS phenomena in detail. IS research must understand splitting, how it results in narrowing the scope, and why it is performed for exploratory or predictive reasons in variance, process, and stage models.

Bilevel optimization, which captures the inherent nested structure of machine learning problems, is gaining popularity in many recent applications. Existing works on bilevel optimization mostly consider either the unconstrained problems or the constrained upper-level problems. In this context, this paper considers the stochastic bilevel optimization problems with equality constraints in both upper and lower levels. By leveraging the special structure of the equality constraints problem, the paper first presents an alternating projected SGD approach to tackle this problem and establishes the $\tilde{\cal O}(\epsilon^{-2})$ sample and iteration complexity that matches the state-of-the-art complexity of ALSET Chen et al. (2021) for stochastic unconstrained bilevel problems. To further save the cost of projection, the paper presents an alternating projected SGD approach with lazy projection and establishes the $\tilde{\cal O}(\epsilon^{-2}/T)$ upper-level and $\tilde{\cal O}(\epsilon^{-1.5}/T^{\frac{3}{4}})$ lower-level projection complexity of this new algorithm, where $T$ is the upper-level projection interval. Application to federated bilevel optimization has been presented to showcase the performance of our algorithms. Our results demonstrate that equality-constrained bilevel optimization with strongly-convex lower-level problems can be solved as efficiently as stochastic single-level optimization problems.

Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for the considered bilevel problems, which generalizes the existing metric, for a nonconvex lower-level objective that satisfies the Polyak-Łojasiewicz (PL) condition. We then propose a Generalized ALternating mEthod for bilevel opTimization (GALET) tailored to BLO with convex PL LL problem and establish that GALET achieves an $\epsilon$-stationary point for the considered problem within $\tilde{\cal O}(\epsilon^{-1})$ iterations, which matches the iteration complexity of GD for single-level smooth nonconvex problems.

Abstract Social question‐and‐answer (Q&A) communities are becoming increasingly important for knowledge acquisition. However, some users withhold knowledge, which can hinder the effectiveness of these platforms. Based on social exchange theory, the study investigates how different types of questions influence knowledge withholding, with question difficulty and user anonymity as boundary conditions. Two experiments were conducted to test hypotheses. Results indicate that informational questions are more likely to lead to knowledge withholding than conversational ones, as they elicit more fear of negative evaluation and fear of exploitation. The study also examines the interplay of question difficulty and user anonymity with question type. Overall, this study significantly extends the existing literature on counterproductive knowledge behavior by exploring the antecedents of knowledge withholding in social Q&A communities.

Stochastic bilevel optimization generalizes the classic stochastic optimization from the minimization of a single objective to the minimization of an objective function that depends on the solution of another optimization problem. Recently, bilevel optimization is regaining popularity in emerging machine learning applications such as hyper-parameter optimization and model-agnostic meta learning. To solve this class of optimization problems, existing methods require either double-loop or two-timescale updates, which are sometimes less efficient. This paper develops a new optimization method for a class of stochastic bilevel problems that we term Single-Timescale stochAstic BiLevEl optimization (STABLE) method. STABLE runs in a single loop fashion, and uses a single-timescale update with a fixed batch size. To achieve an $\epsilon$-stationary point of the bilevel problem, STABLE requires ${\cal O}(\epsilon^{-2})$ samples in total; and to achieve an $\epsilon$-optimal solution in the strongly convex case, STABLE requires ${\cal O}(\epsilon^{-1})$ samples. To the best of our knowledge, when STABLE was proposed, it is the first bilevel optimization algorithm achieving the same order of sample complexity as SGD for single-level stochastic optimization.

A wide range of multi-agent decision-making problems can be abstracted as a federated multi-armed bandit (FMAB) problem. A key challenge of the FMAB problem is that the exploration-exploitation dichotomy inherited from the multi-armed bandit aspect is compounded with data heterogeneity in federated learning. This renders the exploration and exploitation of different agents inherently entangled. This paper focuses on overcoming the difficulty of exploration in FMAB problems, and it proposes a novel federated upper confidence bound (UCB) algorithm that requires uncoordinated exploration (UE) decisions by the agents. The major distinction of this algorithm, referred to as FedUCB-UE, with the existing FMAB algorithms is that it allows the agents to explore the non-optimal arms and make personalized arm-selection decisions without coordination. While such uncoordinated exploration makes the regret analysis non-trivial, it comes with both the theoretical and empirical benefit of diversity in explorations. Under certain mild assumptions, this paper establishes that FedUCB-UE has a $\mathcal{O}(\log T)$ regret bound. Furthermore, experiments performed on synthetic datasets show that FedUCB-UE outperforms the state-of-the-art algorithms.

Model-agnostic meta learning (MAML) is currently one of the dominating approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML can be challenging due to the innate bilevel problem structure. Specifically, the loss landscape of MAML is much more complex with possibly more saddle points and local minimizers than its empirical risk minimization counterpart. To address this challenge, we leverage the recently invented sharpness-aware minimization and develop a sharpness-aware MAML approach that we term Sharp-MAML. We empirically demonstrate that Sharp-MAML and its computation-efficient variant can outperform the plain-vanilla MAML baseline (e.g., +3% accuracy on Mini-Imagenet). We complement the empirical study with the convergence rate analysis and the generalization bound of Sharp-MAML. To the best of our knowledge, this is the first empirical and theoretical study on sharpness-aware minimization in the context of bilevel learning.

K-SVD algorithm has been successfully applied to image denoising tasks dozens of years but the big bottleneck in speed and accuracy still needs attention to break. For the sparse coding stage in K-SVD, which involves ℓ0constraint, prevailing methods usually seek approximate solutions greedily but are less effective once the noise level is high. The alternative ℓ1optimization is proved to be powerful than ℓ0, however, the time consumption prevents it from the implementation. In this paper, we propose a new K-SVD framework called K-SVDPby applying the Primal-dual active set (PDAS) algorithm to it. Different from the greedy algorithms based K-SVD, the K-SVDPalgorithm develops a selection strategy motivated by KKT (Karush-Kuhn-Tucker) condition and yields to an efficient update in the sparse coding stage. Since the K-SVDPalgorithm seeks for an equivalent solution to the dual problem iteratively with simple explicit expression in this denoising problem, speed and quality of denoising can be reached simultaneously. Experiments are carried out and demonstrate the comparable denoising performance of our K-SVDPwith state-of-the-art methods.

MOTIVATION: Imaging genetics is mainly used to reveal the pathogenesis of neuropsychiatric risk genes and understand the relationship between human brain structure, functional and individual differences. Increasingly, the brain-wide imaging phenotypes in voxels are available to test the association with genetic markers. A challenge with analyzing such data is their high dimensionality and complex relationships. RESULTS: To tackle this challenge, we introduce a weighed distance correlation (wdCor) that can assess the association between genetic markers and voxel-based imaging data. Importantly, the wdCor test takes the voxel-based data as a whole multivariate phenotype, which preserves the spatial continuity and might enhance the power. Besides, an adaptive permutation procedure is introduced to determine the P-values of the wdCor test and also alleviate the computational burden in GWAS. In extensive simulation studies, wdCor achieves much better performances compared to the original distance correlation. We also successfully apply wdCor to conduct a large-scale analysis on data from the Alzheimer's disease neuroimaging project (ADNI). AVAILABILITY AND IMPLEMENTATION: Our wdCor method provides new research directions and ideas for multivariate analysis of high-dimensional data, it can also be used as a tool for scientific analysis of imaging genetics research in practical applications. The R package wdcor, and the code for reproducing all results in this article is available in Github: https://github.com/yangyuhui0129/wdcor. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Since a human face can be represented by a few feature points (FPs) with less redundant information, and calculated by a linear combination of a small number of prototypical faces, we propose a two-step 3D face reconstruction approach including FP depth estimation and shape deformation. The proposed approach can reconstruct a realistic 3D face from a 2D frontal face image. In the first step, a coupled dictionary learning method based on sparse representation is employed to explore the underlying mappings between 2D and 3D training FPs, and then the depth of the FPs is estimated. In the second step, a novel shape deformation method is proposed to reconstruct the 3D face by combining a small number of most relevant deformed faces by the estimated FPs. The proposed approach can explore the distributions of 2D and 3D faces and the underlying mappings between them well, because human faces are represented by low-dimensional FPs, and their distributions are described by sparse representations. Moreover, it is much more flexible since we can make any change in any step. Extensive experiments are conducted on BJUT_3D database, and the results validate the effectiveness of the proposed approach.

Visual object tracking is a challenging task because designing an effective and efficient appearance model is difficult. Current online tracking algorithms treat tracking as a classification task and use labeled samples to update appearance model. However, it is not clear to evaluate instance confidence belong to the object. In this paper, we propose a simple and efficient tracking algorithm with a deformable structure appearance. In our method, model updates with continuous labeled samples which are dense sampling. In order to improve the accuracy, we introduce a couple-layer regression model which prevents negative background from impacting on the model learning rather than traditional classification. The proposed DSR tracker runs in real-time and performs favorably against state-of-the-art trackers on various challenging sequences.