Alzheimer's disease (AD) is a neurodegenerative disorder marked by memory loss and cognitive decline, making early detection vital for timely intervention. However, early diagnosis is challenging due to the heterogeneous presentation of symptoms. Resting-state fMRI (rs-fMRI) captures spontaneous brain activity and functional connectivity, which are known to be disrupted in AD and mild cognitive impairment (MCI). Traditional methods, such as Pearson's correlation, have been used to calculate association matrices, but these approaches often overlook the dynamic and non-stationary nature of brain activity. In this study, we introduce a novel method that integrates discrete wavelet transform (DWT) and graph theory to model the dynamic behavior of brain networks. By decomposing rs-fMRI signals using DWT, our approach captures the time-frequency representation of brain activity, allowing for a more nuanced analysis of the underlying network dynamics. Graph theory provides a robust mathematical framework to analyze these complex networks, while machine learning is employed to automate the discrimination of different stages of AD based on learned patterns from different frequency bands. We applied our method to a dataset of rs-fMRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, demonstrating its potential as an early diagnostic tool for AD and for monitoring disease progression. Our statistical analysis identifies specific brain regions and connections that are affected in AD and MCI, at different frequency bands, offering deeper insights into the disease's impact on brain function.

Automated feature engineering (AutoFE) is the process of automatically building and selecting new features that help improve downstream predictive performance. While traditional feature engineering requires significant domain expertise and time-consuming iterative testing, AutoFE strives to make feature engineering easy and accessible to all data science practitioners. We introduce a new AutoFE algorithm, IIFE, based on determining which feature pairs synergize well through an information-theoretic perspective called interaction information. We demonstrate the superior performance of IIFE over existing algorithms. We also show how interaction information can be used to improve existing AutoFE algorithms. Finally, we highlight several critical experimental setup issues in the existing AutoFE literature and their effects on performance.

In the early stages of drug discovery, decisions regarding which experiments to pursue can be influenced by computational models. These decisions are critical due to the time-consuming and expensive nature of the experiments. Therefore, it is becoming essential to accurately quantify the uncertainty in machine learning predictions, such that resources can be used optimally and trust in the models improves. While computational methods for drug discovery often suffer from limited data and sparse experimental observations, additional information can exist in the form of censored labels that provide thresholds rather than precise values of observations. However, the standard approaches that quantify uncertainty in machine learning cannot fully utilize censored labels. In this work, we adapt ensemble-based, Bayesian, and Gaussian models with tools to learn from censored labels by using the Tobit model from survival analysis. Our results demonstrate that despite the partial information available in censored labels, they are essential to accurately and reliably model the real pharmaceutical setting.

Proteins are essential to numerous biological functions, with their sequences determining their roles within organisms. Traditional methods for determining protein function are time-consuming and labor-intensive. This study addresses the increasing demand for precise, effective, and automated protein sequence classification methods by employing natural language processing (NLP) techniques on a dataset comprising 75 target protein classes. We explored various machine learning and deep learning models, including K-Nearest Neighbors (KNN), Multinomial Na\"ive Bayes, Logistic Regression, Multi-Layer Perceptron (MLP), Decision Tree, Random Forest, XGBoost, Voting and Stacking classifiers, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and transformer models (BertForSequenceClassification, DistilBERT, and ProtBert). Experiments were conducted using amino acid ranges of 1-4 grams for machine learning models and different sequence lengths for CNN and LSTM models. The KNN algorithm performed best on tri-gram data with 70.0% accuracy and a macro F1 score of 63.0%. The Voting classifier achieved best performance with 74.0% accuracy and an F1 score of 65.0%, while the Stacking classifier reached 75.0% accuracy and an F1 score of 64.0%. ProtBert demonstrated the highest performance among transformer models, with a accuracy 76.0% and F1 score 61.0% which is same for all three transformer models. Advanced NLP techniques, particularly ensemble methods and transformer models, show great potential in protein classification. Our results demonstrate that ensemble methods, particularly Voting Soft classifiers, achieved superior results, highlighting the importance of sufficient training data and addressing sequence similarity across different classes.

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between keys and queries. Recent work has explored alternatives to softmax attention in transformers, such as ReLU and sigmoid activations. In this work, we revisit sigmoid attention and conduct an in-depth theoretical and empirical analysis. Theoretically, we prove that transformers with sigmoid attention are universal function approximators and benefit from improved regularity compared to softmax attention. Through detailed empirical analysis, we identify stabilization of large initial attention norms during the early stages of training as a crucial factor for the successful training of models with sigmoid attention, outperforming prior attempts. We also introduce FLASHSIGMOID, a hardware-aware and memory-efficient implementation of sigmoid attention yielding a 17% inference kernel speed-up over FLASHATTENTION2 on H100 GPUs. Experiments across language, vision, and speech show that properly normalized sigmoid attention matches the strong performance of softmax attention on a wide range of domains and scales, which previous attempts at sigmoid attention were unable to fully achieve. Our work unifies prior art and establishes best practices for sigmoid attention as a drop-in softmax replacement in transformers.

Metric magnitude is a measure of the "size" of point clouds with many desirable geometric properties. It has been adapted to various mathematical contexts and recent work suggests that it can enhance machine learning and optimization algorithms. But its usability is limited due to the computational cost when the dataset is large or when the computation must be carried out repeatedly (e.g. in model training). In this paper, we study the magnitude computation problem, and show efficient ways of approximating it. We show that it can be cast as a convex optimization problem, but not as a submodular optimization. The paper describes two new algorithms - an iterative approximation algorithm that converges fast and is accurate, and a subset selection method that makes the computation even faster. It has been previously proposed that magnitude of model sequences generated during stochastic gradient descent is correlated to generalization gap. Extension of this result using our more scalable algorithms shows that longer sequences in fact bear higher correlations. We also describe new applications of magnitude in machine learning - as an effective regularizer for neural network training, and as a novel clustering criterion.

Imbalanced data are frequently encountered in real-world classification tasks. Previous works on imbalanced learning mostly focused on learning with a minority class of few samples. However, the notion of imbalance also applies to cases where the minority class contains abundant samples, which is usually the case for industrial applications like fraud detection in the area of financial risk management. In this paper, we take a population-level approach to imbalanced learning by proposing a new formulation called \emph{ultra-imbalanced classification} (UIC). Under UIC, loss functions behave differently even if infinite amount of training samples are available. To understand the intrinsic difficulty of UIC problems, we borrow ideas from information theory and establish a framework to compare different loss functions through the lens of statistical information. A novel learning objective termed Tunable Boosting Loss is developed which is provably resistant against data imbalance under UIC, as well as being empirically efficient verified by extensive experimental studies on both public and industrial datasets.

Although fundamental to the advancement of Machine Learning, the classic evaluation metrics extracted from the confusion matrix, such as precision and F1, are limited. Such metrics only offer a quantitative view of the models' performance, without considering the complexity of the data or the quality of the hit. To overcome these limitations, recent research has introduced the use of psychometric metrics such as Item Response Theory (IRT), which allows an assessment at the level of latent characteristics of instances. This work investigates how IRT concepts can enrich a confusion matrix in order to identify which model is the most appropriate among options with similar performance. In the study carried out, IRT does not replace, but complements classical metrics by offering a new layer of evaluation and observation of the fine behavior of models in specific instances. It was also observed that there is 97% confidence that the score from the IRT has different contributions from 66% of the classical metrics analyzed.

Since the entry of kernel theory in the field of quantum machine learning, quantum kernel methods (QKMs) have gained increasing attention with regard to both probing promising applications and delivering intriguing research insights. Two common approaches for computing the underlying Gram matrix have emerged: fidelity quantum kernels (FQKs) and projected quantum kernels (PQKs). Benchmarking these methods is crucial to gain robust insights and to understand their practical utility. In this work, we present a comprehensive large-scale study examining QKMs based on FQKs and PQKs across a manifold of design choices. Our investigation encompasses both classification and regression tasks for five dataset families and 64 datasets, systematically comparing the use of FQKs and PQKs quantum support vector machines and kernel ridge regression. This resulted in over 20,000 models that were trained and optimized using a state-of-the-art hyperparameter search to ensure robust and comprehensive insights. We delve into the importance of hyperparameters on model performance scores and support our findings through rigorous correlation analyses. In this, we also closely inspect two data encoding strategies. Moreover, we provide an in-depth analysis addressing the design freedom of PQKs and explore the underlying principles responsible for learning. Our goal is not to identify the best-performing model for a specific task but to uncover the mechanisms that lead to effective QKMs and reveal universal patterns.

Gaussian process (GP) models that combine both categorical and continuous input variables have found use in longitudinal data analysis of and computer experiments. However, standard inference for these models has the typical cubic scaling, and common scalable approximation schemes for GPs cannot be applied since the covariance function is non-continuous. In this work, we derive a basis function approximation scheme for mixed-domain covariance functions, which scales linearly with respect to the number of observations and total number of basis functions. The proposed approach is naturally applicable to also Bayesian GP regression with discrete observation models. We demonstrate the scalability of the approach and compare model reduction techniques for additive GP models in a longitudinal data context. We confirm that we can approximate the exact GP model accurately in a fraction of the runtime compared to fitting the corresponding exact model. In addition, we demonstrate a scalable model reduction workflow for obtaining smaller and more interpretable models when dealing with a large number of candidate predictors.