Search Papers

AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competitions to solve real-world machine learning problems. We formalize AI research agents as search policies that navigate a space of candidate solutions, iteratively modifying them using operators. By designing and systematically varying different operator sets and search policies (Greedy, MCTS, Evolutionary), we show that their interplay is critical for achieving high performance. Our best pairing of search strategy and operator set achieves a state-of-the-art result on MLE-bench lite, increasing the success rate of achieving a Kaggle medal from 39.6% to 47.7%. Our investigation underscores the importance of jointly considering the search strategy, operator design, and evaluation methodology in advancing automated machine learning.

Quantum computing promises to revolutionize our understanding of the limits of computation, and its implications in cryptography have long been evident. Today, cryptographers are actively devising post-quantum solutions to counter the threats posed by quantum-enabled adversaries. Meanwhile, quantum scientists are innovating quantum protocols to empower defenders. However, the broader impact of quantum computing and quantum machine learning (QML) on other cybersecurity domains still needs to be explored. In this work, we investigate the potential impact of QML on cybersecurity applications of traditional ML. First, we explore the potential advantages of quantum computing in machine learning problems specifically related to cybersecurity. Then, we describe a methodology to quantify the future impact of fault-tolerant QML algorithms on real-world problems. As a case study, we apply our approach to standard methods and datasets in network intrusion detection, one of the most studied applications of machine learning in cybersecurity. Our results provide insight into the conditions for obtaining a quantum advantage and the need for future quantum hardware and software advancements.

The increasing reliance on Global Navigation Satellite Systems (GNSS), particularly the Global Positioning System (GPS), underscores the urgent need to safeguard these technologies against malicious threats such as spoofing and jamming. As the backbone for positioning, navigation, and timing (PNT) across various applications including transportation, telecommunications, and emergency services GNSS is vulnerable to deliberate interference that poses significant risks. Spoofing attacks, which involve transmitting counterfeit GNSS signals to mislead receivers into calculating incorrect positions, can result in serious consequences, from navigational errors in civilian aviation to security breaches in military operations. Furthermore, the lack of inherent security measures within GNSS systems makes them attractive targets for adversaries. While GNSS/GPS jamming and spoofing systems consist of numerous components, the ability to distinguish authentic signals from malicious ones is essential for maintaining system integrity. Recent advancements in machine learning and deep learning provide promising avenues for enhancing detection and mitigation strategies against these threats. This paper addresses both spoofing and jamming by tackling real-world challenges through machine learning, deep learning, and computer vision techniques. Through extensive experiments on two real-world datasets related to spoofing and jamming detection using advanced algorithms, we achieved state of the art results. In the GNSS/GPS jamming detection task, we attained approximately 99% accuracy, improving performance by around 5% compared to previous studies. Additionally, we addressed a challenging tasks related to spoofing detection, yielding results that underscore the potential of machine learning and deep learning in this domain.

Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However, the optimal integration of retrieval augmentation into molecular machine learning remains unclear. Graph neural networks stand to benefit from clever matching to understand the structural alignment of retrieved molecules to a query molecule. Neural graph matching offers a compelling solution by explicitly modeling node and edge affinities between two structural graphs while employing a noise-robust, end-to-end neural network to learn affinity metrics. We apply this approach to mass spectrum simulation and introduce MARASON, a novel model that incorporates neural graph matching to enhance a fragmentation-based neural network. Experimental results highlight the effectiveness of our design, with MARASON achieving 28% top-1 accuracy, a substantial improvement over the non-retrieval state-of-the-art accuracy of 19%. Moreover, MARASON outperforms both naive retrieval-augmented generation methods and traditional graph matching approaches. Code is publicly available at https://github.com/coleygroup/ms-pred

Machine Learning models are being extensively used in safety critical applications where errors from these models could cause harm to the user. Such risks are amplified when multiple machine learning models, which are deployed concurrently, interact and make errors simultaneously. This paper explores three scenarios where error correlations between multiple models arise, resulting in such aggregated risks. Using real-world data, we simulate these scenarios and quantify the correlations in errors of different models. Our findings indicate that aggregated risks are substantial, particularly when models share similar algorithms, training datasets, or foundational models. Overall, we observe that correlations across models are pervasive and likely to intensify with increased reliance on foundational models and widely used public datasets, highlighting the need for effective mitigation strategies to address these challenges.

Machine learning (ML) models rely heavily on consistent and accurate performance metrics to evaluate and compare their effectiveness. However, existing libraries often suffer from fragmentation, inconsistent implementations, and insufficient data validation protocols, leading to unreliable results. Existing libraries have often been developed independently and without adherence to a unified standard, particularly concerning the specific tasks they aim to support. As a result, each library tends to adopt its conventions for metric computation, input/output formatting, error handling, and data validation protocols. This lack of standardization leads to both implementation differences (ID) and reporting differences (RD), making it difficult to compare results across frameworks or ensure reliable evaluations. To address these issues, we introduce AllMetrics, an open-source unified Python library designed to standardize metric evaluation across diverse ML tasks, including regression, classification, clustering, segmentation, and image-to-image translation. The library implements class-specific reporting for multi-class tasks through configurable parameters to cover all use cases, while incorporating task-specific parameters to resolve metric computation discrepancies across implementations. Various datasets from domains like healthcare, finance, and real estate were applied to our library and compared with Python, Matlab, and R components to identify which yield similar results. AllMetrics combines a modular Application Programming Interface (API) with robust input validation mechanisms to ensure reproducibility and reliability in model evaluation. This paper presents the design principles, architectural components, and empirical analyses demonstrating the ability to mitigate evaluation errors and to enhance the trustworthiness of ML workflows.

Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs). AIDE frames machine learning engineering as a code optimization problem, and formulates trial-and-error as a tree search in the space of potential solutions. By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench.

Machine learning models are increasingly used to produce predictions that serve as input data in subsequent statistical analyses. For example, computer vision predictions of economic and environmental indicators based on satellite imagery are used in downstream regressions; similarly, language models are widely used to approximate human ratings and opinions in social science research. However, failure to properly account for errors in the machine learning predictions renders standard statistical procedures invalid. Prior work uses what we call the Predict-Then-Debias estimator to give valid confidence intervals when machine learning algorithms impute missing variables, assuming a small complete sample from the population of interest. We expand the scope by introducing bootstrap confidence intervals that apply when the complete data is a nonuniform (i.e., weighted, stratified, or clustered) sample and to settings where an arbitrary subset of features is imputed. Importantly, the method can be applied to many settings without requiring additional calculations. We prove that these confidence intervals are valid under no assumptions on the quality of the machine learning model and are no wider than the intervals obtained by methods that do not use machine learning predictions.

Privacy and regulatory barriers often hinder centralized machine learning solutions, particularly in sectors like healthcare where data cannot be freely shared. Federated learning has emerged as a powerful paradigm to address these concerns; however, existing frameworks primarily support gradientbased models, leaving a gap for more interpretable, tree-based approaches. This paper introduces a federated learning framework for Random Forest classifiers that preserves data privacy and provides robust performance in distributed settings. By leveraging PySyft for secure, privacy-aware computation, our method enables multiple institutions to collaboratively train Random Forest models on locally stored data without exposing sensitive information. The framework supports weighted model averaging to account for varying data distributions, incremental learning to progressively refine models, and local evaluation to assess performance across heterogeneous datasets. Experiments on two realworld healthcare benchmarks demonstrate that the federated approach maintains competitive predictive accuracy—within a maximum 9% margin of centralized methods—while satisfying stringent privacy requirements. These findings underscore the viability of tree-based federated learning for scenarios where data cannot be centralized due to regulatory, competitive, or technical constraints. The proposed solution addresses a notable gap in existing federated learning libraries, offering an adaptable tool for secure distributed machine learning tasks that demand both transparency and reliable performance. The tool is available at https://github.com/ieeta-pt/fed_rf

A large part of modern machine learning theory often involves computing the high-dimensional expected trace of a rational expression of large rectangular random matrices. To symbolically compute such quantities using free probability theory, we introduce auto-fpt, a lightweight Python and SymPy-based tool that can automatically produce a reduced system of fixed-point equations which can be solved for the quantities of interest, and effectively constitutes a theory. We overview the algorithmic ideas underlying auto-fpt and its applications to various interesting problems, such as the high-dimensional error of linearized feed-forward neural networks, recovering well-known results. We hope that auto-fpt streamlines the majority of calculations involved in high-dimensional analysis, while helping the machine learning community reproduce known and uncover new phenomena.

Solutions to the Algorithm Selection Problem (ASP) in machine learning face the challenge of high computational costs associated with evaluating various algorithms' performances on a given dataset. To mitigate this cost, the meta-learning field can leverage previously executed experiments shared in online repositories such as OpenML. OpenML provides an extensive collection of machine learning experiments. However, an analysis of OpenML's records reveals limitations. It lacks diversity in pipelines, specifically when exploring data preprocessing steps/blocks, such as scaling or imputation, resulting in limited representation. Its experiments are often focused on a few popular techniques within each pipeline block, leading to an imbalanced sample. To overcome the observed limitations of OpenML, we propose PIPES, a collection of experiments involving multiple pipelines designed to represent all combinations of the selected sets of techniques, aiming at diversity and completeness. PIPES stores the results of experiments performed applying 9,408 pipelines to 300 datasets. It includes detailed information on the pipeline blocks, training and testing times, predictions, performances, and the eventual error messages. This comprehensive collection of results allows researchers to perform analyses across diverse and representative pipelines and datasets. PIPES also offers potential for expansion, as additional data and experiments can be incorporated to support the meta-learning community further. The data, code, supplementary material, and all experiments can be found at https://github.com/cynthiamaia/PIPES.git.

The successful application of modern machine learning for time series classification is often hampered by limitations in quality and quantity of available training data. To overcome these limitations, available domain expert knowledge in the form of parametrised mechanistic dynamical models can be used whenever it is available and time series observations may be represented as an element from a given class of parametrised dynamical models. This makes the learning process interpretable and allows the modeller to deal with sparsely and irregularly sampled data in a natural way. However, the internal processes of a dynamical model are often only partially observed. This can lead to ambiguity regarding which particular model realization best explains a given time series observation. This problem is well-known in the literature, and a dynamical model with this issue is referred to as structurally unidentifiable. Training a classifier that incorporates knowledge about a structurally unidentifiable dynamical model can negatively influence classification performance. To address this issue, we employ structural identifiability analysis to explicitly relate parameter configurations that are associated with identical system outputs. Using the derived relations in classifier training, we demonstrate that this method significantly improves the classifier's ability to generalize to unseen data on a number of example models from the biomedical domain. This effect is especially pronounced when the number of training instances is limited. Our results demonstrate the importance of accounting for structural identifiability, a topic that has received relatively little attention from the machine learning community.

• A causal discovery method is introduced based on machine learning and explainability techniques. • Complex relationships in the data are captured and approximated by ML models, echoing their structural causal model. • Shapley values are used to help measuring how each feature contributes to data’s causal structure. • Results comparable to state-of-the-art methods in synthetic data and Sachs protein network support the approach. • A repository with open-source code is provided to foster wide adoption and further development. Explainable Artificial Intelligence (XAI) techniques hold significant potential for enhancing the causal discovery process, which is crucial for understanding complex systems in areas like healthcare, economics, and artificial intelligence. However, no causal discovery methods currently incorporate explainability into their models to derive the causal graphs. Thus, in this paper we explore this innovative approach, as it offers substantial potential and represents a promising new direction worth investigating. Specifically, we introduce R e X, a causal discovery method that leverages machine learning (ML) models coupled with explainability techniques, specifically Shapley values, to identify and interpret significant causal relationships among variables. Comparative evaluations on synthetic datasets comprising continuous tabular data reveal that R e X outperforms state-of-the-art causal discovery methods across diverse data generation processes, including non-linear and additive noise models. Moreover, R e X was tested on the Sachs single-cell protein-signaling dataset, achieving a precision of 0.952 and recovering key causal relationships with no incorrect edges. Taking together, these results showcase R e X’s effectiveness in accurately recovering true causal structures while minimizing false positive predictions, its robustness across diverse datasets, and its applicability to real-world problems. By combining ML and explainability techniques with causal discovery, R e X bridges the gap between predictive modeling and causal inference, offering an effective tool for understanding complex causal structures. R e X is publicly available at https://github.com/renero/causalgraph .

Existing biomedical benchmarks do not provide end-to-end infrastructure for training, evaluation, and inference of models that integrate multimodal biological data and a broad range of machine learning tasks in therapeutics. We present PyTDC, an open-source machine-learning platform providing streamlined training, evaluation, and inference software for multimodal biological AI models. PyTDC unifies distributed, heterogeneous, continuously updated data sources and model weights and standardizes benchmarking and inference endpoints. This paper discusses the components of PyTDC's architecture and, to our knowledge, the first-of-its-kind case study on the introduced single-cell drug-target nomination ML task. We find state-of-the-art methods in graph representation learning and domain-specific methods from graph theory perform poorly on this task. Though we find a context-aware geometric deep learning method that outperforms the evaluated SoTA and domain-specific baseline methods, the model is unable to generalize to unseen cell types or incorporate additional modalities, highlighting PyTDC's capacity to facilitate an exciting avenue of research developing multimodal, context-aware, foundation models for open problems in biomedical AI.

Introduction: Supervised machine learning classifiers sometimes face challenges related to the performance, accuracy, or overfitting. Methods: This paper introduces the Artificial Liver Classifier (ALC), a novel supervised learning model inspired by the human liver's detoxification function. The ALC is characterized by its simplicity, speed, capability to reduce overfitting, and effectiveness in addressing multi-class classification problems through straightforward mathematical operations. To optimize the ALC's parameters, an improved FOX optimization algorithm (IFOX) is employed during training. Results: We evaluate the proposed ALC on five benchmark datasets: Iris Flower, Breast Cancer Wisconsin, Wine, Voice Gender, and MNIST. The results demonstrate competitive performance, with ALC achieving up to 100% accuracy on the Iris dataset-surpassing logistic regression, multilayer perceptron, and support vector machine-and 99.12% accuracy on the Breast Cancer dataset, outperforming XGBoost and logistic regression. Across all datasets, ALC consistently shows smaller generalization gaps and lower loss values compared to conventional classifiers. Discussion: These findings highlight the potential of biologically inspired models to develop efficient machine learning classifiers and open new avenues for innovation in the field.

We present \texttt{MathOptAI.jl}, an open-source Julia library for embedding trained machine learning predictors into a JuMP model. \texttt{MathOptAI.jl} can embed a wide variety of neural networks, decision trees, and Gaussian Processes into a larger mathematical optimization model. In addition to interfacing a range of Julia-based machine learning libraries such as \texttt{Lux.jl} and \texttt{Flux.jl}, \texttt{MathOptAI.jl} uses Julia's Python interface to provide support for PyTorch models. When the PyTorch support is combined with \texttt{MathOptAI.jl}'s gray-box formulation, the function, Jacobian, and Hessian evaluations associated with the PyTorch model are offloaded to the GPU in Python, while the rest of the nonlinear oracles are evaluated on the CPU in Julia. \MathOptAI is available at https://github.com/lanl-ansi/MathOptAI.jl under a BSD-3 license.

We introduce TimeSeriesGym, a scalable benchmarking framework for evaluating Artificial Intelligence (AI) agents on time series machine learning engineering challenges. Existing benchmarks lack scalability, focus narrowly on model building in well-defined settings, and evaluate only a limited set of research artifacts (e.g., CSV submission files). To make AI agent benchmarking more relevant to the practice of machine learning engineering, our framework scales along two critical dimensions. First, recognizing that effective ML engineering requires a range of diverse skills, TimeSeriesGym incorporates challenges from diverse sources spanning multiple domains and tasks. We design challenges to evaluate both isolated capabilities (including data handling, understanding research repositories, and code translation) and their combinations, and rather than addressing each challenge independently, we develop tools that support designing multiple challenges at scale. Second, we implement evaluation mechanisms for multiple research artifacts, including submission files, code, and models, using both precise numeric measures and more flexible LLM-based evaluation approaches. This dual strategy balances objective assessment with contextual judgment. Although our initial focus is on time series applications, our framework can be readily extended to other data modalities, broadly enhancing the comprehensiveness and practical utility of agentic AI evaluation. We open-source our benchmarking framework to facilitate future research on the ML engineering capabilities of AI agents.

QML-HCS is a research-grade framework for constructing and analyzing quantum-inspired machine learning models operating under hypercausal feedback dynamics. Hypercausal refers to AI systems that leverage extended, deep, or nonlinear causal relationships (expanded causality) to reason, predict, and infer states beyond the capabilities of traditional causal models. Current machine learning and quantum-inspired systems struggle in non-stationary environments, where data distributions drift and models lack mechanisms for continuous adaptation, causal stability, and coherent state updating. QML-HCS addresses this limitation through a unified computational architecture that integrates quantum-inspired superposition principles, dynamic causal feedback, and deterministic-stochastic hybrid execution to enable adaptive behavior in changing environments. The framework implements a hypercausal processing core capable of reversible transformations, multipath causal propagation, and evaluation of alternative states under drift. Its architecture incorporates continuous feedback to preserve causal consistency and adjust model behavior without requiring full retraining. QML-HCS provides a reproducible and extensible Python interface backed by efficient computational routines, enabling experimentation in quantum-inspired learning, causal reasoning, and hybrid computation without the need for specialized hardware. A minimal simulation demonstrates how a hypercausal model adapts to a sudden shift in the input distribution while preserving internal coherence. This initial release establishes the foundational architecture for future theoretical extensions, benchmarking studies, and integration with classical and quantum simulation platforms.

Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics). This sole focus on efficacy has steered development of large-scale models that require massive resources, and results in considerable carbon footprint across the model life-cycle. In this work, we explore how physics inductive biases can offer useful trade-offs between model efficacy and model efficiency (compute, energy, and carbon). We study a variety of models for spatio-temporal forecasting, a task governed by physical laws and well-suited for exploring different levels of physics inductive bias. We show that embedding physics inductive biases into the model design can yield substantial efficiency gains while retaining or even improving efficacy for the tasks under consideration. In addition to using standard physics-informed spatio-temporal models, we demonstrate the usefulness of more recent models like flow matching as a general purpose method for spatio-temporal forecasting. Our experiments show that incorporating physics inductive biases offer a principled way to improve the efficiency and reduce the carbon footprint of machine learning models. We argue that model efficiency, along with model efficacy, should become a core consideration driving machine learning model development and deployment.

Postprandial hyperglycemia, marked by the blood glucose level exceeding the normal range after consuming a meal, is a critical indicator of progression toward type 2 diabetes in people with prediabetes and in healthy individuals. A key metric for understanding blood glucose dynamics after eating is the postprandial area under the curve (AUC). Predicting postprandial AUC in advance based on a person's lifestyle factors, such as diet and physical activity level, and explaining the factors that affect postprandial blood glucose could allow an individual to adjust their lifestyle accordingly to maintain normal glucose levels. In this study, we developed an explainable machine learning solution, GlucoLens, that takes sensor-driven inputs and uses advanced data processing, large language models, and trainable machine learning models to predict postprandial AUC and hyperglycemia from diet, physical activity, and recent glucose patterns. We used data obtained from wearables in a five-week clinical trial of 10 adults who worked full-time to develop and evaluate the proposed computational model that integrates wearable sensing, multimodal data, and machine learning. Our machine learning model takes multimodal data from wearable activity and glucose monitoring sensors, along with food and work logs, and provides an interpretable prediction of the postprandial glucose pattern. Our GlucoLens system achieves a normalized root mean squared error (NRMSE) of 0.123 in its best configuration. On average, the proposed technology provides a 16% better performance level compared to the comparison models. Additionally, our technique predicts hyperglycemia with an accuracy of 73.3% and an F1 score of 0.716 and recommends different treatment options to help avoid hyperglycemia through diverse counterfactual explanations. Code available: https://github.com/ab9mamun/GlucoLens.