We present GO-CBED, a goal-oriented Bayesian framework for sequential causal experimental design. Unlike conventional approaches that select interventions aimed at inferring the full causal model, GO-CBED directly maximizes the expected information gain (EIG) on user-specified causal quantities of interest, enabling more targeted and efficient experimentation. The framework is both non-myopic, optimizing over entire intervention sequences, and goal-oriented, targeting only model aspects relevant to the causal query. To address the intractability of exact EIG computation, we introduce a variational lower bound estimator, optimized jointly through a transformer-based policy network and normalizing flow-based variational posteriors. The resulting policy enables real-time decision-making via an amortized network. We demonstrate that GO-CBED consistently outperforms existing baselines across various causal reasoning and discovery tasks-including synthetic structural causal models and semi-synthetic gene regulatory networks-particularly in settings with limited experimental budgets and complex causal mechanisms. Our results highlight the benefits of aligning experimental design objectives with specific research goals and of forward-looking sequential planning.
Mechanistic mathematical models of biological systems usually contain a number of unknown parameters whose values need to be estimated from available experimental data in order for the models to be validated and used to make quantitative predictions. This requires that the models are practically identifiable, that is, the values of the parameters can be confidently determined, given available data. A well-designed experiment can produce data that are much more informative for the purpose of inferring parameter values than a poorly designed experiment. It is, therefore, of great interest to optimally design experiments such that the resulting data maximise the practical identifiability of a chosen model. Experimental design is also useful for model discrimination, where we seek to distinguish between multiple distinct, competing models of the same biological system in order to determine which model better reveals insight into the underlying biological mechanisms. In many cases, an external stimulus can be used as a control input to probe the behaviour of the system. In this paper, we will explore techniques for optimally designing such a control for a given experiment, in order to maximise parameter identifiability and model discrimination, and demonstrate these techniques in the context of commonly applied ordinary differential equation models. We use a profile likelihood-based approach to assess parameter identifiability. We then show how the problem of optimal experimental design for model discrimination can be formulated as an optimal control problem, which can be solved efficiently by applying Pontryagin's Maximum Principle.
Accurate parameter estimation in electrochemical battery models is essential for monitoring and assessing the performance of lithium-ion batteries (LiBs). This paper presents a novel approach that combines deep reinforcement learning (DRL) with an optimal experimental design (OED) framework to identify key electrochemical parameters of LiB cell models. The proposed method utilizes the twin delayed deep deterministic policy gradient (TD3) algorithm to optimize input excitation, thereby increasing the sensitivity of the system response to electrochemical parameters. The performance of this DRL-based approach is evaluated against a nonlinear model predictive control (NMPC) method and conventional tests. Results indicate that the DRL-based method provides superior information content, reflected in higher Fisher information (FI) values and lower parameter estimation errors compared to the NMPC design and conventional test practices. Additionally, the DRL approach offers a substantial reduction in experimental time and computational resources.
We study finite-armed semiparametric bandits, where each arm's reward combines a linear component with an unknown, potentially adversarial shift. This model strictly generalizes classical linear bandits and reflects complexities common in practice. We propose the first experimental-design approach that simultaneously offers a sharp regret bound, a PAC bound, and a best-arm identification guarantee. Our method attains the minimax regret $\tilde{O}(\sqrt{dT})$, matching the known lower bound for finite-armed linear bandits, and further achieves logarithmic regret under a positive suboptimality gap condition. These guarantees follow from our refined non-asymptotic analysis of orthogonalized regression that attains the optimal $\sqrt{d}$ rate, paving the way for robust and efficient learning across a broad class of semiparametric bandit problems.
Shojaee et al. (2025) report that Large Reasoning Models (LRMs) exhibit "accuracy collapse" on planning puzzles beyond certain complexity thresholds. We demonstrate that their findings primarily reflect experimental design limitations rather than fundamental reasoning failures. Our analysis reveals three critical issues: (1) Tower of Hanoi experiments risk exceeding model output token limits, with models explicitly acknowledging these constraints in their outputs; (2) The authors' automated evaluation framework fails to distinguish between reasoning failures and practical constraints, leading to misclassification of model capabilities; (3) Most concerningly, their River Crossing benchmarks include mathematically impossible instances for N > 5 due to insufficient boat capacity, yet models are scored as failures for not solving these unsolvable problems. When we control for these experimental artifacts, by requesting generating functions instead of exhaustive move lists, preliminary experiments across multiple models indicate high accuracy on Tower of Hanoi instances previously reported as complete failures. These findings highlight the importance of careful experimental design when evaluating AI reasoning capabilities.
Computational inverse problems for biomedical simulators suffer from limited data and relatively high parameter dimensionality. This often requires sensitivity analysis, where parameters of the model are ranked based on their influence on the specific quantities of interest. This is especially important for simulators used to build medical digital twins, as the amount of data is typically limited. For expensive models, such as blood flow models, emulation is employed to expedite the simulation time. Parameter ranking and fixing using sensitivity analysis are often heuristic, though, and vary with the specific application or simulator used. The present study provides an innovative solution to this problem by leveraging polynomial chaos expansions (PCEs) for both multioutput global sensitivity analysis and formal parameter identifiability. For the former, we use dimension reduction to efficiently quantify time-series sensitivity of a one-dimensional pulmonary hemodynamics model. We consider both Windkessel and structured tree boundary conditions. We then use PCEs to construct profile-likelihood confidence intervals to formally assess parameter identifiability, and show how changes in experimental design improve identifiability. Our work presents a novel approach to determining parameter identifiability and leverages a common emulation strategy for enabling profile-likelihood analysis in problems governed by partial differential equations.
A combinatorial intervention, consisting of multiple treatments applied to a single unit with potentially interactive effects, has substantial applications in fields such as biomedicine, engineering, and beyond. Given $p$ possible treatments, conducting all possible $2^p$ combinatorial interventions can be laborious and quickly becomes infeasible as $p$ increases. Here we introduce probabilistic factorial experimental design, formalized from how scientists perform lab experiments. In this framework, the experimenter selects a dosage for each possible treatment and applies it to a group of units. Each unit independently receives a random combination of treatments, sampled from a product Bernoulli distribution determined by the dosages. Additionally, the experimenter can carry out such experiments over multiple rounds, adapting the design in an active manner. We address the optimal experimental design problem within an intervention model that imposes bounded-degree interactions between treatments. In the passive setting, we provide a closed-form solution for the near-optimal design. Our results prove that a dosage of $\tfrac{1}{2}$ for each treatment is optimal up to a factor of $1+O(\tfrac{\ln(n)}{n})$ for estimating any $k$-way interaction model, regardless of $k$, and imply that $O\big(kp^{3k}\ln(p)\big)$ observations are required to accurately estimate this model. For the multi-round setting, we provide a near-optimal acquisition function that can be numerically optimized. We also explore several extensions of the design problem and finally validate our findings through simulations.
We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative preference queries to identify the underlying reward while ensuring theoretical guarantees. We propose a meta-algorithm based on randomized exploration, which avoids the computational challenges associated with optimistic approaches and remains tractable. We establish both regret and last-iterate guarantees under mild reinforcement learning oracle assumptions. To improve query complexity, we introduce and analyze an improved algorithm that collects batches of trajectory pairs and applies optimal experimental design to select informative comparison queries. The batch structure also enables parallelization of preference queries, which is relevant in practical deployment as feedback can be gathered concurrently. Empirical evaluation confirms that the proposed method is competitive with reward-based reinforcement learning while requiring a small number of preference queries.
Many critical applications, from autonomous scientific discovery to personalized medicine, demand systems that can both strategically acquire the most informative data and instantaneously perform inference based upon it. While amortized methods for Bayesian inference and experimental design offer part of the solution, neither approach is optimal in the most general and challenging task, where new data needs to be collected for instant inference. To tackle this issue, we introduce the Amortized Active Learning and Inference Engine (ALINE), a unified framework for amortized Bayesian inference and active data acquisition. ALINE leverages a transformer architecture trained via reinforcement learning with a reward based on self-estimated information gain provided by its own integrated inference component. This allows it to strategically query informative data points while simultaneously refining its predictions. Moreover, ALINE can selectively direct its querying strategy towards specific subsets of model parameters or designated predictive tasks, optimizing for posterior estimation, data prediction, or a mixture thereof. Empirical results on regression-based active learning, classical Bayesian experimental design benchmarks, and a psychometric model with selectively targeted parameters demonstrate that ALINE delivers both instant and accurate inference along with efficient selection of informative points.
In many settings in science and industry, such as drug discovery and clinical trials, a central challenge is designing experiments under time and budget constraints. Bayesian Optimal Experimental Design (BOED) is a paradigm to pick maximally informative designs that has been increasingly applied to such problems. During training, BOED selects inputs according to a pre-determined acquisition criterion. During testing, the model learned during training encounters a naturally occurring distribution of test samples. This leads to an instance of covariate shift, where the train and test samples are drawn from different distributions. Prior work has shown that in the presence of model misspecification, covariate shift amplifies generalization error. Our first contribution is to provide a mathematical decomposition of generalization error that reveals key contributors to generalization error in the presence of model misspecification. We show that generalization error under misspecification is the result of, in addition to covariate shift, a phenomenon we term error (de-)amplification which has not been identified or studied in prior work. Our second contribution is to provide a detailed empirical analysis to show that methods that result in representative and de-amplifying training data increase generalization performance. Our third contribution is to develop a novel acquisition function that mitigates the effects of model misspecification by including a term for representativeness and implicitly inducing de-amplification. Our experimental results demonstrate that our method outperforms traditional BOED in the presence of misspecification.
We study stochastic linear bandits with heavy-tailed rewards, where the rewards have a finite $(1+\epsilon)$-absolute central moment bounded by $\upsilon$ for some $\epsilon \in (0,1]$. We improve both upper and lower bounds on the minimax regret compared to prior work. When $\upsilon = \mathcal{O}(1)$, the best prior known regret upper bound is $\tilde{\mathcal{O}}(d T^{\frac{1}{1+\epsilon}})$. While a lower with the same scaling has been given, it relies on a construction using $\upsilon = \mathcal{O}(d)$, and adapting the construction to the bounded-moment regime with $\upsilon = \mathcal{O}(1)$ yields only a $\Omega(d^{\frac{\epsilon}{1+\epsilon}} T^{\frac{1}{1+\epsilon}})$ lower bound. This matches the known rate for multi-armed bandits and is generally loose for linear bandits, in particular being $\sqrt{d}$ below the optimal rate in the finite-variance case ($\epsilon = 1$). We propose a new elimination-based algorithm guided by experimental design, which achieves regret $\tilde{\mathcal{O}}(d^{\frac{1+3\epsilon}{2(1+\epsilon)}} T^{\frac{1}{1+\epsilon}})$, thus improving the dependence on $d$ for all $\epsilon \in (0,1)$ and recovering a known optimal result for $\epsilon = 1$. We also establish a lower bound of $\Omega(d^{\frac{2\epsilon}{1+\epsilon}} T^{\frac{1}{1+\epsilon}})$, which strictly improves upon the multi-armed bandit rate and highlights the hardness of heavy-tailed linear bandit problems. For finite action sets, we derive similarly improved upper and lower bounds for regret. Finally, we provide action set dependent regret upper bounds showing that for some geometries, such as $l_p$-norm balls for $p \le 1 + \epsilon$, we can further reduce the dependence on $d$, and we can handle infinite-dimensional settings via the kernel trick, in particular establishing new regret bounds for the Mat\'ern kernel that are the first to be sublinear for all $\epsilon \in (0, 1]$.
In recent years, the rapid advancement and democratization of generative AI models have sparked significant debate over safety, ethical risks, and dual-use concerns, particularly in the context of cybersecurity. While anecdotally known, this paper provides empirical evidence regarding generative AI's association with malicious internet-related activities and cybercrime by examining the phenomenon through psychological frameworks of technological amplification and affordance theory. Using a quasi-experimental design with interrupted time series analysis, we analyze two datasets, one general and one cryptocurrency-focused, to empirically assess generative AI's role in cybercrime. The findings contribute to ongoing discussions about AI governance by balancing control and fostering innovation, underscoring the need for strategies to guide policymakers, inform AI developers and cybersecurity professionals, and educate the public to maximize AI's benefits while mitigating its risks.
How should researchers analyze randomized experiments in which the main outcome is measured in multiple ways but each measure contains some degree of error? We describe modeling approaches that enable researchers to identify causal parameters of interest, suggest ways that experimental designs can be augmented so as to make linear latent variable models more credible, and discuss empirical tests of key modeling assumptions. We show that when experimental researchers invest appropriately in multiple outcome measures, an optimally weighted index of the outcome measures enables researchers to obtain efficient and interpretable estimates of causal parameters by applying standard regression methods, and that weights may be obtained using instrumental variables regression. Maximum likelihood and generalized method of moments estimators can be used to obtain estimates and standard errors in a single step. An empirical application illustrates the gains in precision and robustness that multiple outcome measures can provide.
In industrial X-ray Computed Tomography (CT), the need for rapid in-line inspection is critical. Sparse-angle tomography plays a significant role in this by reducing the required number of projections, thereby accelerating processing and conserving resources. Most existing methods aim to balance reconstruction quality and scanning time, typically relying on fixed scan durations. Adaptive adjustment of the number of angles is essential; for instance, more angles may be required for objects with complex geometries or noisier projections. The concept of optimal stopping, which dynamically adjusts this balance according to varying industrial needs, remains overlooked. Building on our previous work, we integrate optimal stopping into sequential Optimal Experimental Design (sOED) and Reinforcement Learning (RL). We propose a novel method for computing the policy gradient within the Actor-Critic framework, enabling the development of adaptive policies for informative angle selection and scan termination. Additionally, we investigate the gap between simulation and real-world applications in the context of the developed learning-based method. Our trained model, developed using synthetic data, demonstrates reliable performance when applied to experimental X-ray CT data. This approach enhances the flexibility of CT operations and expands the applicability of sparse-angle tomography in industrial settings.
With recent Nobel Prizes recognising AI contributions to science, Large Language Models (LLMs) are transforming scientific research by enhancing productivity and reshaping the scientific method. LLMs are now involved in experimental design, data analysis, and workflows, particularly in chemistry and biology. However, challenges such as hallucinations and reliability persist. In this contribution, we review how Large Language Models (LLMs) are redefining the scientific method and explore their potential applications across different stages of the scientific cycle, from hypothesis testing to discovery. We conclude that, for LLMs to serve as relevant and effective creative engines and productivity enhancers, their deep integration into all steps of the scientific process should be pursued in collaboration and alignment with human scientific goals, with clear evaluation metrics. The transition to AI-driven science raises ethical questions about creativity, oversight, and responsibility. With careful guidance, LLMs could evolve into creative engines, driving transformative breakthroughs across scientific disciplines responsibly and effectively. However, the scientific community must also decide how much it leaves to LLMs to drive science, even when associations with 'reasoning', mostly currently undeserved, are made in exchange for the potential to explore hypothesis and solution regions that might otherwise remain unexplored by human exploration alone.
Recent claims suggest that large language models (LMs) underperform humans in comprehending minimally complex English statements (Dentella et al., 2024). Here, we revisit those findings and argue that human performance was overestimated, while LLM abilities were underestimated. Using the same stimuli, we report a preregistered study comparing human responses in two conditions: one allowed rereading (replicating the original study), and one that restricted rereading (a more naturalistic comprehension test). Human accuracy dropped significantly when rereading was restricted (73%), falling below that of Falcon-180B-Chat (76%) and GPT-4 (81%). The newer GPT-o1 model achieves perfect accuracy. Results further show that both humans and models are disproportionately challenged by queries involving potentially reciprocal actions (e.g., kissing), suggesting shared pragmatic sensitivities rather than model-specific deficits. Additional analyses using Llama-2-70B log probabilities, a recoding of open-ended model responses, and grammaticality ratings of other sentences reveal systematic underestimation of model performance. We find that GPT-4o can align with either naive or expert grammaticality judgments, depending on prompt framing. These findings underscore the need for more careful experimental design and coding practices in LLM evaluation, and they challenge the assumption that current models are inherently weaker than humans at language comprehension.
Scientific imaging often involves long acquisition times to obtain high-quality data, especially when probing complex, heterogeneous systems. However, reducing acquisition time to increase throughput inevitably introduces significant noise into the measurements. We present a machine learning approach that not only denoises low-quality measurements with calibrated uncertainty bounds, but also reveals emergent structure in the latent space. By using ensembles of lightweight, randomly structured neural networks trained via conformal quantile regression, our method performs reliable denoising while uncovering interpretable spatial and chemical features -- without requiring labels or segmentation. Unlike conventional approaches focused solely on image restoration, our framework leverages the denoising process itself to drive the emergence of meaningful representations. We validate the approach on real-world geobiochemical imaging data, showing how it supports confident interpretation and guides experimental design under resource constraints.
Contextual online decision-making problems with constraints appear in various real-world applications, such as personalized recommendation with resource limits and dynamic pricing with fairness constraints. In this paper, we investigate a general formulation of sequential decision-making with stage-wise feasibility constraints, where at each round, the learner must select an action based on observed context while ensuring a problem-specific feasibility criterion. We propose a unified algorithmic framework that captures many existing constrained learning problems, including constrained bandits, stream active learning, online hypothesis testing, and model calibration. Central to our approach is the concept of upper counterfactual confidence bound, which enables the design of practically efficient online algorithms using any offline conditional density estimation oracle. Technically, to handle feasibility constraints, we introduce a generalized notion of the eluder dimension, extending it from the classical setting based on square loss to a broader class of metric-like probability divergences, which could capture the complexity of various density function classes and characterize the loss incurred due to feasibility constraint uncertainty. Our result offers a principled foundation for constrained sequential decision-making in both theory and practice.
Motivation: High-throughput omics technologies generate complex datasets with thousands of features that are quantified across multiple experimental conditions, but often suffer from incomplete measurements, missing values and individually fluctuating variances. This requires sophisticated analytical methods for accurate, deep and insightful biological interpretations, capable of dealing with a large variety of data properties and different amounts of completeness. Software to handle such data complexity is rare and mostly relies on programming-based environments, limiting accessibility for researchers without computational expertise. Results: We present OmicsQ, an interactive, web-based platform designed to streamline quantitative omics data analysis. OmicsQ integrates established statistical processing tools with an intuitive, browser-based visualization interface. It provides robust batch correction, automated experimental design annotation, and missing-data handling without imputation, which ensures data integrity and avoids artifacts from a priori assumptions. OmicsQ seamlessly interacts with external applications for statistical testing, clustering, analysis of protein complex behavior, and pathway enrichment, offering a comprehensive and flexible workflow from data import to biological interpretation that is broadly applicable tov data from different domains. Availability and Implementation: OmicsQ is implemented in R and R Shiny and is available at https://computproteomics.bmb.sdu.dk/app_direct/OmicsQ. Source code and installation instructions can be found at https://github.com/computproteomics/OmicsQ
Quantitative Systems Pharmacology (QSP) promises to accelerate drug development, enable personalized medicine, and improve the predictability of clinical outcomes. Realizing this potential requires effectively managing the complexity of mathematical models representing biological systems. Here, we present and validate a novel QSP workflow--CRISP (Contextualized Reduction for Identifiability and Scientific Precision)--that addresses a central challenge in QSP: the problem of complexity and over-parameterization, in which models contain irrelevant parameters that obscure interpretation and hinder predictive reliability. The CRISP workflow begins with a literature-derived model, constructed to be comprehensive and unbiased by integrating prior mechanistic insights. At the core of the workflow is the Manifold Boundary Approximation Method (MBAM), a reduction technique that simplifies models while preserving mechanistic structure and predictive fidelity. By applying MBAM in a context-specific manner, CRISP links parsimonious models directly to predictions of interest, clarifying causal structure and enhancing interpretability. The resulting models are computationally efficient and well-suited to key QSP tasks, including virtual population generation, experimental design, toxicology, and target discovery. We demonstrate the utility of CRISP on case studies involving the coagulation cascade and SHIV infection, and identify promising directions for improving the efficacy of bNAb therapies for HIV. Together, these results establish CRISP as a general-purpose QSP workflow for turning complex mechanistic models into tools for precise scientific reasoning to guide pharmacological and regulatory decision-making.