Bayesian optimization is a powerful technique for optimizing expensive-to-evaluate black-box functions, consisting of two main components: a surrogate model and an acquisition function. In recent years, myopic acquisition functions have been widely adopted for their simplicity and effectiveness. However, their lack of look-ahead capability limits their performance. To address this limitation, we propose FigBO, a generalized acquisition function that incorporates the future impact of candidate points on global information gain. FigBO is a plug-and-play method that can integrate seamlessly with most existing myopic acquisition functions. Theoretically, we analyze the regret bound and convergence rate of FigBO when combined with the myopic base acquisition function expected improvement (EI), comparing them to those of standard EI. Empirically, extensive experimental results across diverse tasks demonstrate that FigBO achieves state-of-the-art performance and significantly faster convergence compared to existing methods.

Traditional k-means clustering underperforms on non-convex shapes and requires the number of clusters k to be specified in advance. We propose a simple geometric enhancement: after standard k-means, each cluster center is assigned a radius (the distance to its farthest assigned point), and clusters whose radii overlap are merged. This post-processing step loosens the requirement for exact k: as long as k is overestimated (but not excessively), the method can often reconstruct non-convex shapes through meaningful merges. We also show that this approach supports recursive partitioning: clustering can be performed independently on tiled regions of the feature space, then globally merged, making the method scalable and suitable for distributed systems. Implemented as a lightweight post-processing step atop scikit-learn's k-means, the algorithm performs well on benchmark datasets, achieving high accuracy with minimal additional computation.

Language models can behave in unexpected and unsafe ways, and so it is valuable to monitor their outputs. Internal activations of language models encode additional information that could be useful for this. The baseline approach for activation monitoring is some variation of linear probing on a particular layer: starting from a labeled dataset, train a logistic regression classifier on that layer's activations. Recent work has proposed several approaches which may improve on naive linear probing, by leveraging additional computation. One class of techniques, which we call "prompted probing," leverages test time computation to improve monitoring by (1) prompting the model with a description of the monitoring task, and (2) applying a learned linear probe to resulting activations. Another class of techniques uses computation at train time: training sparse autoencoders offline to identify an interpretable basis for the activations, and e.g. max-pooling activations across tokens using that basis before applying a linear probe. However, one can also prompt the model with a description of the monitoring task and use its output directly. We develop and test novel refinements of these methods and compare them against each other. We find asking the model zero-shot is a reasonable baseline when inference-time compute is not limited; however, activation probing methods can substantially outperform this baseline given sufficient training data. Specifically, we recommend prompted probing when inference-time compute is available, due to its superior data efficiency and good generalization performance. Alternatively, if inference-time compute is limited, we find SAE-based probing methods outperform raw activation probing.

Many model selection algorithms rely on sparse dictionary learning to provide interpretable and physics-based governing equations. The optimization algorithms typically use a hard thresholding process to enforce sparse activations in the model coefficients by removing library elements from consideration. By introducing an annealing scheme that reactivates a fraction of the removed terms with a cooling schedule, we are able to improve the performance of these sparse learning algorithms. We concentrate on two approaches to the optimization, SINDy, and an alternative using hard thresholding pursuit. We see in both cases that annealing can improve model accuracy. The effectiveness of annealing is demonstrated through comparisons on several nonlinear systems pulled from convective flows, excitable systems, and population dynamics. Finally we apply these algorithms to experimental data for projectile motion.

This paper presents ProFi-Net, a novel few-shot learning framework for WiFi-based gesture recognition that overcomes the challenges of limited training data and sparse feature representations. ProFi-Net employs a prototype-based metric learning architecture enhanced with a feature-level attention mechanism, which dynamically refines the Euclidean distance by emphasizing the most discriminative feature dimensions. Additionally, our approach introduces a curriculum-inspired data augmentation strategy exclusively on the query set. By progressively incorporating Gaussian noise of increasing magnitude, the model is exposed to a broader range of challenging variations, thereby improving its generalization and robustness to overfitting. Extensive experiments conducted across diverse real-world environments demonstrate that ProFi-Net significantly outperforms conventional prototype networks and other state-of-the-art few-shot learning methods in terms of classification accuracy and training efficiency.

Tool-using agents that act in the world need to be both useful and safe. Well-calibrated model confidences can be used to weigh the risk versus reward of potential actions, but prior work shows that many models are poorly calibrated. Inspired by interpretability literature exploring the internals of models, we propose a novel class of model-internal confidence estimators (MICE) to better assess confidence when calling tools. MICE first decodes from each intermediate layer of the language model using logitLens and then computes similarity scores between each layer's generation and the final output. These features are fed into a learned probabilistic classifier to assess confidence in the decoded output. On the simulated trial and error (STE) tool-calling dataset using Llama3 models, we find that MICE beats or matches the baselines on smoothed expected calibration error. Using MICE confidences to determine whether to call a tool significantly improves over strong baselines on a new metric, expected tool-calling utility. Further experiments show that MICE is sample-efficient, can generalize zero-shot to unseen APIs, and results in higher tool-calling utility in scenarios with varying risk levels. Our code is open source, available at https://github.com/microsoft/mice_for_cats.

Early detection of asthma in children is crucial to prevent long-term respiratory complications and reduce emergency interventions. This work presents an AI-powered diagnostic pipeline that leverages Googles Health Acoustic Representations (HeAR) model to detect early signs of asthma from pediatric respiratory sounds. The SPRSound dataset, the first open-access collection of annotated respiratory sounds in children aged 1 month to 18 years, is used to extract 2-second audio segments labeled as wheeze, crackle, rhonchi, stridor, or normal. Each segment is embedded into a 512-dimensional representation using HeAR, a foundation model pretrained on 300 million health-related audio clips, including 100 million cough sounds. Multiple classifiers, including SVM, Random Forest, and MLP, are trained on these embeddings to distinguish between asthma-indicative and normal sounds. The system achieves over 91\% accuracy, with strong performance on precision-recall metrics for positive cases. In addition to classification, learned embeddings are visualized using PCA, misclassifications are analyzed through waveform playback, and ROC and confusion matrix insights are provided. This method demonstrates that short, low-resource pediatric recordings, when powered by foundation audio models, can enable fast, noninvasive asthma screening. The approach is especially promising for digital diagnostics in remote or underserved healthcare settings.

Transferability scores aim to quantify how well a model trained on one domain generalizes to a target domain. Despite numerous methods proposed for measuring transferability, their reliability and practical usefulness remain inconclusive, often due to differing experimental setups, datasets, and assumptions. In this paper, we introduce a comprehensive benchmarking framework designed to systematically evaluate transferability scores across diverse settings. Through extensive experiments, we observe variations in how different metrics perform under various scenarios, suggesting that current evaluation practices may not fully capture each method's strengths and limitations. Our findings underscore the value of standardized assessment protocols, paving the way for more reliable transferability measures and better-informed model selection in cross-domain applications. Additionally, we achieved a 3.5% improvement using our proposed metric for the head-training fine-tuning experimental setup. Our code is available in this repository: https://github.com/alizkzm/

Exponential growth in scientific literature has heightened the demand for efficient evidence-based synthesis, driving the rise of the field of Automated Meta-analysis (AMA) powered by natural language processing and machine learning. This PRISMA systematic review introduces a structured framework for assessing the current state of AMA, based on screening 978 papers from 2006 to 2024, and analyzing 54 studies across diverse domains. Findings reveal a predominant focus on automating data processing (57%), such as extraction and statistical modeling, while only 17% address advanced synthesis stages. Just one study (2%) explored preliminary full-process automation, highlighting a critical gap that limits AMA's capacity for comprehensive synthesis. Despite recent breakthroughs in large language models (LLMs) and advanced AI, their integration into statistical modeling and higher-order synthesis, such as heterogeneity assessment and bias evaluation, remains underdeveloped. This has constrained AMA's potential for fully autonomous meta-analysis. From our dataset spanning medical (67%) and non-medical (33%) applications, we found that AMA has exhibited distinct implementation patterns and varying degrees of effectiveness in actually improving efficiency, scalability, and reproducibility. While automation has enhanced specific meta-analytic tasks, achieving seamless, end-to-end automation remains an open challenge. As AI systems advance in reasoning and contextual understanding, addressing these gaps is now imperative. Future efforts must focus on bridging automation across all meta-analysis stages, refining interpretability, and ensuring methodological robustness to fully realize AMA's potential for scalable, domain-agnostic synthesis.

First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal matrix. Despite the widespread adoption of first-order methods, second-order optimization algorithms often exhibit superior convergence compared to methods like Adam and SGD. However, their practicality in training DNNs is still limited by a significantly higher per-iteration computational cost compared to first-order methods. In this thesis, we present AdaFisher, a novel adaptive second-order optimizer that leverages a diagonal block-Kronecker approximation of the Fisher information matrix to adaptively precondition gradients. AdaFisher aims to bridge the gap between the improved convergence and generalization of second-order methods and the computational efficiency needed for training DNNs. Despite the traditionally slower speed of second-order optimizers, AdaFisher is effective for tasks such as image classification and language modeling, exhibiting remarkable stability and robustness during hyperparameter tuning. We demonstrate that AdaFisher outperforms state-of-the-art optimizers in both accuracy and convergence speed. The code is available from https://github.com/AtlasAnalyticsLab/AdaFisher.