This study explores the application of supervised machine learning algorithms to predict coffee ratings based on a combination of influential textual and numerical attributes extracted from user reviews. Through careful data preprocessing including text cleaning, feature extraction using TF-IDF, and selection with SelectKBest, the study identifies key factors contributing to coffee quality assessments. Six models (Decision Tree, KNearest Neighbors, Multi-layer Perceptron, Random Forest, Extra Trees, and XGBoost) were trained and evaluated using optimized hyperparameters. Model performance was assessed primarily using F1-score, Gmean, and AUC metrics. Results demonstrate that ensemble methods (Extra Trees, Random Forest, and XGBoost), as well as Multi-layer Perceptron, consistently outperform simpler classifiers (Decision Trees and K-Nearest Neighbors) in terms of evaluation metrics such as F1 scores, G-mean and AUC. The findings highlight the essence of rigorous feature selection and hyperparameter tuning in building robust predictive systems for sensory product evaluation, offering a data driven approach to complement traditional coffee cupping by expertise of trained professionals.

Modern IoT devices increasingly rely on machine learning solutions to process data locally. However, the lack of graphics processing units (GPUs) or dedicated accelerators on most platforms makes on-device training largely infeasible, often requiring cloud-based services to perform this task. This procedure often raises privacy-related concerns, and creates dependency on reliable and always-on connectivity. Federated Learning (FL) is a new trend that addresses these issues by enabling decentralized and collaborative training directly on devices, but it requires highly efficient optimization algorithms. L-SGD, a lightweight variant of stochastic gradient descent, has enabled neural network training on Arm Cortex-M Microcontroller Units (MCUs). This work extends L-SGD to RISC-V-based MCUs, an open and emerging architecture that still lacks robust support for on-device training. L-SGD was evaluated on both Arm and RISC-V platforms using 32-bit floating-point arithmetic, highlighting the performance impact of the absence of Floating-Point Units (FPUs) in RISC-V MCUs. To mitigate these limitations, we introduce an 8-bit quantized version of L-SGD for RISC-V, which achieves nearly 4x reduction in memory usage and a 2.2x speedup in training time, with negligible accuracy degradation.

Accurate recognition of vessel types from Automatic Identification System (AIS) tracks is essential for safety oversight and combating illegal, unreported, and unregulated (IUU) activity. This paper presents a strait-scale, machine-learning pipeline that classifies moving vessels using only AIS data. We analyze eight days of historical AIS from the Danish Maritime Authority covering the Bornholm Strait in the Baltic Sea (January 22-30, 2025). After forward/backward filling voyage records, removing kinematic and geospatial outliers, and segmenting per-MMSI tracks while excluding stationary periods ($\ge 1$ h), we derive 31 trajectory-level features spanning kinematics (e.g., SOG statistics), temporal, geospatial (Haversine distances, spans), and ship-shape attributes computed from AIS A/B/C/D reference points (length, width, aspect ratio, bridge-position ratio). To avoid leakage, we perform grouped train/test splits by MMSI and use stratified 5-fold cross-validation. Across five classes (cargo, tanker, passenger, high-speed craft, fishing; N=1{,}910 trajectories; test=382), tree-based models dominate: a Random Forest with SMOTE attains 92.15% accuracy (macro-precision 94.11%, macro-recall 92.51%, macro-F1 93.27%) on the held-out test set, while a tuned RF reaches one-vs-rest ROC-AUC up to 0.9897. Feature-importance analysis highlights the bridge-position ratio and maximum SOG as the most discriminative signals; principal errors occur between cargo and tanker, reflecting similar transit behavior. We demonstrate operational value by backfilling missing ship types on unseen data and discuss improvements such as DBSCAN based trip segmentation and gradient-boosted ensembles to handle frequent-stop ferries and further lift performance. The results show that lightweight features over AIS trajectories enable real-time vessel type classification in straits.

The sliced Wasserstein distance (SW) reduces optimal transport on $\mathbb{R}^d$ to a sum of one-dimensional projections, and thanks to this efficiency, it is widely used in geometry, generative modeling, and registration tasks. Recent work shows that quasi-Monte Carlo constructions for computing SW (QSW) yield direction sets with excellent approximation error. This paper presents an alternate, novel approach: learning directions with Bayesian optimization (BO), particularly in settings where SW appears inside an optimization loop (e.g., gradient flows). We introduce a family of drop-in selectors for projection directions: BOSW, a one-shot BO scheme on the unit sphere; RBOSW, a periodic-refresh variant; ABOSW, an adaptive hybrid that seeds from competitive QSW sets and performs a few lightweight BO refinements; and ARBOSW, a restarted hybrid that periodically relearns directions during optimization. Our BO approaches can be composed with QSW and its variants (demonstrated by ABOSW/ARBOSW) and require no changes to downstream losses or gradients. We provide numerical experiments where our methods achieve state-of-the-art performance, and on the experimental suite of the original QSW paper, we find that ABOSW and ARBOSW can achieve convergence comparable to the best QSW variants with modest runtime overhead.

Performative prediction (PP) is an algorithmic framework for optimizing machine learning (ML) models where the model's deployment affects the distribution of the data it is trained on. Compared to traditional ML with fixed data, designing algorithms in PP converging to a stable point -- known as a stationary performative stable (SPS) solution -- is more challenging than the counterpart in conventional ML tasks due to the model-induced distribution shifts. While considerable efforts have been made to find SPS solutions using methods such as repeated gradient descent (RGD) and greedy stochastic gradient descent (SGD-GD), most prior studies assumed a strongly convex loss until a recent work established $O(1/\sqrt{T})$ convergence of SGD-GD to SPS solutions under smooth, non-convex losses. However, this latest progress is still based on the restricted bounded variance assumption in stochastic gradient estimates and yields convergence bounds with a non-vanishing error neighborhood that scales with the variance. This limitation motivates us to improve convergence rates and reduce error in stochastic optimization for PP, particularly in non-convex settings. Thus, we propose a new algorithm called stochastic performative prediction with variance reduction (SPRINT) and establish its convergence to an SPS solution at a rate of $O(1/T)$. Notably, the resulting error neighborhood is independent of the variance of the stochastic gradients. Experiments on multiple real datasets with non-convex models demonstrate that SPRINT outperforms SGD-GD in both convergence rate and stability.

Adapting machine learning models to medical time series across different domains remains a challenge due to complex temporal dependencies and dynamic distribution shifts. Current approaches often focus on isolated feature representations, limiting their ability to fully capture the intricate temporal dynamics necessary for robust domain adaptation. In this work, we propose a novel framework leveraging multi-view contrastive learning to integrate temporal patterns, derivative-based dynamics, and frequency-domain features. Our method employs independent encoders and a hierarchical fusion mechanism to learn feature-invariant representations that are transferable across domains while preserving temporal coherence. Extensive experiments on diverse medical datasets, including electroencephalogram (EEG), electrocardiogram (ECG), and electromyography (EMG) demonstrate that our approach significantly outperforms state-of-the-art methods in transfer learning tasks. By advancing the robustness and generalizability of machine learning models, our framework offers a practical pathway for deploying reliable AI systems in diverse healthcare settings. Data and Code Availability This study uses publicly available datasets in medical and healthcare domains, including SleepEEG (Kemp et al., 2000) and ECG (Clifford et al., 2017) for pre-training, and Epilepsy (Andrzejak et al., 2001), FD (Less-meier et al., 2016), Gesture (Liu et al., 2009), and EMG (Goldberger et al., 2000) for fine-tuning. The datasets used in this study are publicly accessible via their respective repositories, with detailed documentation included in the supplementary material.

Language models obtain extensive capabilities through pre-training. However, the pre-training process remains a black box. In this work, we track linear interpretable feature evolution across pre-training snapshots using a sparse dictionary learning method called crosscoders. We find that most features begin to form around a specific point, while more complex patterns emerge in later training stages. Feature attribution analyses reveal causal connections between feature evolution and downstream performance. Our feature-level observations are highly consistent with previous findings on Transformer's two-stage learning process, which we term a statistical learning phase and a feature learning phase. Our work opens up the possibility to track fine-grained representation progress during language model learning dynamics.

In this paper, we present a general specification for Functional Effects Models, which use Machine Learning (ML) methodologies to learn individual-specific preference parameters from socio-demographic characteristics, therefore accounting for inter-individual heterogeneity in panel choice data. We identify three specific advantages of the Functional Effects Model over traditional fixed, and random/mixed effects models: (i) by mapping individual-specific effects as a function of socio-demographic variables, we can account for these effects when forecasting choices of previously unobserved individuals (ii) the (approximate) maximum-likelihood estimation of functional effects avoids the incidental parameters problem of the fixed effects model, even when the number of observed choices per individual is small; and (iii) we do not rely on the strong distributional assumptions of the random effects model, which may not match reality. We learn functional intercept and functional slopes with powerful non-linear machine learning regressors for tabular data, namely gradient boosting decision trees and deep neural networks. We validate our proposed methodology on a synthetic experiment and three real-world panel case studies, demonstrating that the Functional Effects Model: (i) can identify the true values of individual-specific effects when the data generation process is known; (ii) outperforms both state-of-the-art ML choice modelling techniques that omit individual heterogeneity in terms of predictive performance, as well as traditional static panel choice models in terms of learning inter-individual heterogeneity. The results indicate that the FI-RUMBoost model, which combines the individual-specific constants of the Functional Effects Model with the complex, non-linear utilities of RUMBoost, performs marginally best on large-scale revealed preference panel data.

We consider the problem of clustering a sample of probability distributions from a random distribution on $\mathbb R^p$. Our proposed partitioning method makes use of a symmetric, positive-definite kernel $k$ and its associated reproducing kernel Hilbert space (RKHS) $\mathcal H$. By mapping each distribution to its corresponding kernel mean embedding in $\mathcal H$, we obtain a sample in this RKHS where we carry out the $K$-means clustering procedure, which provides an unsupervised classification of the original sample. The procedure is simple and computationally feasible even for dimension $p>1$. The simulation studies provide insight into the choice of the kernel and its tuning parameter. The performance of the proposed clustering procedure is illustrated on a collection of Synthetic Aperture Radar (SAR) images.

In this paper, we propose a novel element-wise subset selection method for the alternating least squares (ALS) algorithm, focusing on low-rank matrix factorization involving matrices with missing values, as commonly encountered in recommender systems. While ALS is widely used for providing personalized recommendations based on user-item interaction data, its high computational cost, stemming from repeated regression operations, poses significant challenges for large-scale datasets. To enhance the efficiency of ALS, we propose a core-elements subsampling method that selects a representative subset of data and leverages sparse matrix operations to approximate ALS estimations efficiently. We establish theoretical guarantees for the approximation and convergence of the proposed approach, showing that it achieves similar accuracy with significantly reduced computational time compared to full-data ALS. Extensive simulations and real-world applications demonstrate the effectiveness of our method in various scenarios, emphasizing its potential in large-scale recommendation systems.