Abstract Quantum Machine Learning (QML) represents a transformative paradigm that leverages quantum mechanical principles to enhance computational optimization in complex systems beyond the capabilities of classical machine learning algorithms. This paper investigates the optimization advantages of QML through a comprehensive analysis of quantum neural networks, quantum support vector machines, and hybrid quantum-classical architectures applied to complex system optimization problems. Our methodology employs variational quantum circuits with optimized feature encoding strategies and compares performance against classical baselines across multiple complexity scales. Experimental results demonstrate that QML algorithms achieve superior accuracy (95.1% for hybrid approaches vs 89.5% for classical neural networks), faster convergence rates (10x improvement in optimization iterations), and exponential scalability advantages for large-scale problems (31.7x speedup for problems with 5000 + parameters). The findings reveal that quantum algorithms excel in exploring high-dimensional solution spaces through superposition and entanglement, enabling more efficient navigation of complex optimization landscapes. Key contributions include a novel hybrid quantum-classical optimization framework, systematic performance benchmarking across problem complexities, and identification of quantum advantage thresholds for practical deployment. Results indicate that QML provides significant computational benefits for complex system optimization, particularly in scenarios involving large parameter spaces, non-convex optimization landscapes, and real-time processing requirements.
Mirkan Emir Sancak, Unal Sen, Ulker Diler Keris-Sen
Accurate determination of total oxidant concentration [Ox]tot in nonthermal plasma treated aqueous systems remains a critical challenge due to the transient nature of reactive oxygen and nitrogen species and the subjectivity of conventional titration methods used for [Ox]tot determination. This study introduces a color based computer analysis method that integrates advanced image processing with machine learning to quantify colorimetric changes in potassium iodide solutions during oxidation. A custom built visual acquisition system recorded high resolution video of the color transitions occurring during plasma treatment while the change in oxidant concentration was simultaneously monitored using a standard titrimetric method. Extracted image frames were processed through a structured pipeline to obtain RGB, HSV, and Lab color features. Statistical analysis revealed strong linear relationships between selected color features and measured oxidant concentrations, particularly for HSV saturation, Lab a and b channels, and the blue component of RGB. These features were subsequently used to train and validate multiple machine learning models including linear regression, ridge regression, random forest, gradient boosting, and neural networks. Linear regression and gradient boosting demonstrated the highest predictive accuracy with R2 values exceeding 0.99. Dimensionality reduction from nine features to smaller feature subsets preserved predictive performance while improving computational efficiency. Comparison with experimental titration measurements showed that the proposed system predicts total oxidant concentration in potassium iodide solution with very high accuracy, achieving R2 values above 0.998 even under reduced feature conditions.
Personalized federated learning (PFL) offers a flexible framework for aggregating information across distributed clients with heterogeneous data. This work considers a personalized federated learning setting that simultaneously learns global and local models. While purely local training has no communication cost, collaborative learning among the clients can leverage shared knowledge to improve statistical accuracy, presenting an accuracy-communication trade-off in personalized federated learning. However, the theoretical analysis of how personalization quantitatively influences sample and algorithmic efficiency and their inherent trade-off is largely unexplored. This paper makes a contribution towards filling this gap, by providing a quantitative characterization of the personalization degree on the tradeoff. The results further offers theoretical insights for choosing the personalization degree. As a side contribution, we establish the minimax optimality in terms of statistical accuracy for a widely studied PFL formulation. The theoretical result is validated on both synthetic and real-world datasets and its generalizability is verified in a non-convex setting.
Goutham Rajendran, Simon Buchholz, Bryon Aragam
et al.
To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causal representation learning. The other approach is to build highly-performant foundation models and then invest efforts into understanding how they work. In this work, we relate these two approaches and study how to learn human-interpretable concepts from data. Weaving together ideas from both fields, we formally define a notion of concepts and show that they can be provably recovered from diverse data. Experiments on synthetic data and large language models show the utility of our unified approach.
Numerous benchmarks for Few-Shot Learning have been proposed in the last decade. However all of these benchmarks focus on performance averaged over many tasks, and the question of how to reliably evaluate and tune models trained for individual tasks in this regime has not been addressed. This paper presents the first investigation into task-level evaluation -- a fundamental step when deploying a model. We measure the accuracy of performance estimators in the few-shot setting, consider strategies for model selection, and examine the reasons for the failure of evaluators usually thought of as being robust. We conclude that cross-validation with a low number of folds is the best choice for directly estimating the performance of a model, whereas using bootstrapping or cross validation with a large number of folds is better for model selection purposes. Overall, we find that existing benchmarks for few-shot learning are not designed in such a way that one can get a reliable picture of how effectively methods can be used on individual tasks.
We suggest that deep learning can be used for pre-screening cancer by analyzing demographic and anthropometric information of patients, as well as biological markers obtained from routine blood samples and relative risks obtained from meta-analysis and international databases. We applied feature selection algorithms to a database of 116 women, including 52 healthy women and 64 women diagnosed with breast cancer, to identify the best pre-screening predictors of cancer. We utilized the best predictors to perform k-fold Monte Carlo cross-validation experiments that compare deep learning against traditional machine learning algorithms. Our results indicate that a deep learning model with an input-layer architecture that is fine-tuned using feature selection can effectively distinguish between patients with and without cancer. Additionally, compared to machine learning, deep learning has the lowest uncertainty in its predictions. These findings suggest that deep learning algorithms applied to cancer pre-screening offer a radiation-free, non-invasive, and affordable complement to screening methods based on imagery. The implementation of deep learning algorithms in cancer pre-screening offer opportunities to identify individuals who may require imaging-based screening, can encourage self-examination, and decrease the psychological externalities associated with false positives in cancer screening. The integration of deep learning algorithms for both screening and pre-screening will ultimately lead to earlier detection of malignancy, reducing the healthcare and societal burden associated to cancer treatment.
Quantum machine learning implemented by variational quantum circuits (VQCs) is considered a promising concept for the noisy intermediate-scale quantum computing era. Focusing on applications in quantum reinforcement learning, we propose a specific action decoding procedure for a quantum policy gradient approach. We introduce a novel quality measure that enables us to optimize the classical post-processing required for action selection, inspired by local and global quantum measurements. The resulting algorithm demonstrates a significant performance improvement in several benchmark environments. With this technique, we successfully execute a full training routine on a 5-qubit hardware device. Our method introduces only negligible classical overhead and has the potential to improve VQC-based algorithms beyond the field of quantum reinforcement learning.
Making statements about the performance of trained models on tasks involving new data is one of the primary goals of machine learning, i.e., to understand the generalization power of a model. Various capacity measures try to capture this ability, but usually fall short in explaining important characteristics of models that we observe in practice. In this study, we propose the local effective dimension as a capacity measure which seems to correlate well with generalization error on standard data sets. Importantly, we prove that the local effective dimension bounds the generalization error and discuss the aptness of this capacity measure for machine learning models.
This paper summarizes some challenges encountered and best practices established in several years of teaching Machine Learning for the Physical Sciences at the undergraduate and graduate level. I discuss motivations for teaching ML to physicists, desirable properties of pedagogical materials, such as accessibility, relevance, and likeness to real-world research problems, and give examples of components of teaching units.
Alice Tarzariol, Martin Gebser, Konstantin Schekotihin
Efficient omission of symmetric solution candidates is essential for combinatorial problem-solving. Most of the existing approaches are instance-specific and focus on the automatic computation of Symmetry Breaking Constraints (SBCs) for each given problem instance. However, the application of such approaches to large-scale instances or advanced problem encodings might be problematic since the computed SBCs are propositional and, therefore, can neither be meaningfully interpreted nor transferred to other instances. As a result, a time-consuming recomputation of SBCs must be done before every invocation of a solver. To overcome these limitations, we introduce a new model-oriented approach for Answer Set Programming that lifts the SBCs of small problem instances into a set of interpretable first-order constraints using the Inductive Logic Programming paradigm. Experiments demonstrate the ability of our framework to learn general constraints from instance-specific SBCs for a collection of combinatorial problems. The obtained results indicate that our approach significantly outperforms a state-of-the-art instance-specific method as well as the direct application of a solver.
Ludwig Bothmann, Sven Strickroth, Giuseppe Casalicchio
et al.
Education should not be a privilege but a common good. It should be openly accessible to everyone, with as few barriers as possible; even more so for key technologies such as Machine Learning (ML) and Data Science (DS). Open Educational Resources (OER) are a crucial factor for greater educational equity. In this paper, we describe the specific requirements for OER in ML and DS and argue that it is especially important for these fields to make source files publicly available, leading to Open Source Educational Resources (OSER). We present our view on the collaborative development of OSER, the challenges this poses, and first steps towards their solutions. We outline how OSER can be used for blended learning scenarios and share our experiences in university education. Finally, we discuss additional challenges such as credit assignment or granting certificates.
Over the past few years, providers such as Google, Microsoft, and Amazon have started to provide customers with access to software interfaces allowing them to easily embed machine learning tasks into their applications. Overall, organizations can now use Machine Learning as a Service (MLaaS) engines to outsource complex tasks, e.g., training classifiers, performing predictions, clustering, etc. They can also let others query models trained on their data. Naturally, this approach can also be used (and is often advocated) in other contexts, including government collaborations, citizen science projects, and business-to-business partnerships. However, if malicious users were able to recover data used to train these models, the resulting information leakage would create serious issues. Likewise, if the inner parameters of the model are considered proprietary information, then access to the model should not allow an adversary to learn such parameters. In this document, we set to review privacy challenges in this space, providing a systematic review of the relevant research literature, also exploring possible countermeasures. More specifically, we provide ample background information on relevant concepts around machine learning and privacy. Then, we discuss possible adversarial models and settings, cover a wide range of attacks that relate to private and/or sensitive information leakage, and review recent results attempting to defend against such attacks. Finally, we conclude with a list of open problems that require more work, including the need for better evaluations, more targeted defenses, and the study of the relation to policy and data protection efforts.
Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principled posterior updating mechanism to solve sequential tasks in continual learning. By relying on sparse inducing point approximations for scalable posteriors, we propose a novel auto-regressive variational distribution which reveals two fruitful connections to existing results in Bayesian inference, expectation propagation and orthogonal inducing points. Mean predictive entropy estimates show VAR-GPs prevent catastrophic forgetting, which is empirically supported by strong performance on modern continual learning benchmarks against competitive baselines. A thorough ablation study demonstrates the efficacy of our modeling choices.
Current methods to interpret deep learning models by generating saliency maps generally rely on two key assumptions. First, they use first-order approximations of the loss function neglecting higher-order terms such as the loss curvatures. Second, they evaluate each feature's importance in isolation, ignoring their inter-dependencies. In this work, we study the effect of relaxing these two assumptions. First, by characterizing a closed-form formula for the Hessian matrix of a deep ReLU network, we prove that, for a classification problem with a large number of classes, if an input has a high confidence classification score, the inclusion of the Hessian term has small impacts in the final solution. We prove this result by showing that in this case the Hessian matrix is approximately of rank one and its leading eigenvector is almost parallel to the gradient of the loss function. Our empirical experiments on ImageNet samples are consistent with our theory. This result can have implications in other related problems such as adversarial examples as well. Second, we compute the importance of group-features in deep learning interpretation by introducing a sparsity regularization term. We use the $L_0-L_1$ relaxation technique along with the proximal gradient descent to have an efficient computation of group feature importance scores. Our empirical results indicate that considering group features can improve deep learning interpretation significantly.