Pathology Foundation Models (FMs) hold great promise for healthcare. Before they can be used in clinical practice, it is essential to ensure they are robust to variations between medical centers. We measure whether pathology FMs focus on biological features like tissue and cancer type, or on the well known confounding medical center signatures introduced by staining procedure and other differences. We introduce the Robustness Index. This novel robustness metric reflects to what degree biological features dominate confounding features. Ten current publicly available pathology FMs are evaluated. We find that all current pathology foundation models evaluated represent the medical center to a strong degree. Significant differences in the robustness index are observed. Only one model so far has a robustness index greater than one, meaning biological features dominate confounding features, but only slightly. A quantitative approach to measure the influence of medical center differences on FM-based prediction performance is described. We analyze the impact of unrobustness on classification performance of downstream models, and find that cancer-type classification errors are not random, but specifically attributable to same-center confounders: images of other classes from the same medical center. We visualize FM embedding spaces, and find these are more strongly organized by medical centers than by biological factors. As a consequence, the medical center of origin is predicted more accurately than the tissue source and cancer type. The robustness index introduced here is provided with the aim of advancing progress towards clinical adoption of robust and reliable pathology FMs.

An AI assessor is an external, ideally indepen-dent system that predicts an indicator, e.g., a loss value, of another AI system. Assessors can lever-age information from the test results of many other AI systems and have the flexibility of be-ing trained on any loss function or scoring rule: from squared error to toxicity metrics. Here we address the question: is it always optimal to train the assessor for the target metric? Or could it be better to train for a different metric and then map predictions back to the target metric? Us-ing twenty regression and classification problems with tabular data, we experimentally explore this question for, respectively, regression losses and classification scores with monotonic and non-monotonic mappings and find that, contrary to intuition, optimising for more informative met-rics is not generally better. Surprisingly, some monotonic transformations are promising. For example, the logistic loss is useful for minimis-ing absolute or quadratic errors in regression, and the logarithmic score helps maximise quadratic or spherical scores in classification.

As a specialized branch of deep learning, Learning to Optimize (L2O) tackles optimization problems by training DNN-based solvers. Despite achieving significant success in various scenarios, such as faster convergence in solving convex optimizations and improved optimality in addressing non-convex cases, there remains a deficiency in theoretical support. Current research heavily relies on stringent assumptions that do not align with the intricacies of the training process. To address this gap, our study aims to establish L2O's convergence through its training methodology. We demonstrate that learning an algorithm's hyperparameters significantly enhances its convergence. Focusing on the gradient descent (GD) algorithm for quadratic programming, we prove the convergence of L2O's training using the neural tangent kernel theory. Moreover, we conduct empirical evaluations using synthetic datasets. Our findings indicate exceeding 50\% outperformance over the GD methods.

Spatially embedded networks (SENs) represent a special type of complex graph, whose topologies are constrained by the networks' embedded spatial environments. The graph representation of such networks is thereby influenced by the embedded spatial features of both nodes and edges. Accurate network representation of the graph structure and graph features is a fundamental task for various graph-related tasks. In this study, a Generic Multimodal Spatially Graph Convolutional Network (GMu-SGCN) is developed for efficient representation of spatially embedded networks. The developed GMu-SGCN model has the ability to learn the node connection pattern via multimodal node and edge features. In order to evaluate the developed model, a river network dataset and a power network dataset have been used as test beds. The river network represents the naturally developed SENs, whereas the power network represents a man-made network. Both types of networks are heavily constrained by the spatial environments and uncertainties from nature. Comprehensive evaluation analysis shows the developed GMu-SGCN can improve accuracy of the edge existence prediction task by 37.1\% compared to a GraphSAGE model which only considers the node's position feature in a power network test bed. Our model demonstrates the importance of considering the multidimensional spatial feature for spatially embedded network representation.

Gaussian smoothing combined with a probabilistic framework for denoising via the empirical Bayes formalism, i.e., the Tweedie-Miyasawa formula (TMF), are the two key ingredients in the success of score-based generative models in Euclidean spaces. Smoothing holds the key for easing the problem of learning and sampling in high dimensions, denoising is needed for recovering the original signal, and TMF ties these together via the score function of noisy data. In this work, we extend this paradigm to the problem of learning and sampling the distribution of binary data on the Boolean hypercube by adopting Bernoulli noise, instead of Gaussian noise, as a smoothing device. We first derive a TMF-like expression for the optimal denoiser for the Hamming loss, where a score function naturally appears. Sampling noisy binary data is then achieved using a Langevin-like sampler which we theoretically analyze for different noise levels. At high Bernoulli noise levels sampling becomes easy, akin to log-concave sampling in Euclidean spaces. In addition, we extend the sequential multi-measurement sampling of Saremi et al. (2024) to the binary setting where we can bring the "effective noise" down by sampling multiple noisy measurements at a fixed noise level, without the need for continuous-time stochastic processes. We validate our formalism and theoretical findings by experiments on synthetic data and binarized images.

We show that a gradient-descent with a simple, universal rule for step-size selection provably finds $k$-SVD, i.e., the $k\geq 1$ largest singular values and corresponding vectors, of any matrix, despite nonconvexity. There has been substantial progress towards this in the past few years where existing results are able to establish such guarantees for the \emph{exact-parameterized} and \emph{over-parameterized} settings, with choice of oracle-provided step size. But guarantees for generic setting with a step size selection that does not require oracle-provided information has remained a challenge. We overcome this challenge and establish that gradient descent with an appealingly simple adaptive step size (akin to preconditioning) and random initialization enjoys global linear convergence for generic setting. Our convergence analysis reveals that the gradient method has an attracting region, and within this attracting region, the method behaves like Heron's method (a.k.a. the Babylonian method). Empirically, we validate the theoretical results. The emergence of modern compute infrastructure for iterative optimization coupled with this work is likely to provide means to solve $k$-SVD for very large matrices.

Ensuring the reliability and safety of automated decision-making is crucial. This paper proposes a new approach for measuring the reliability of predictions in machine learning models. We analyze how the outputs of a trained neural network change using clustering to measure distances between outputs and class centroids. We propose this distance as a metric to evaluate the confidence of predictions. We assign each prediction to a cluster with centroid representing the mean softmax output for all correct predictions of a given class. We then define a safety threshold for a class as the smallest distance from an incorrect prediction to the given class centroid. We evaluate the approach on the MNIST and CIFAR-10 datasets using a Convolutional Neural Network and a Vision Transformer, respectively. The results show that our approach is consistent across these data sets and network models, and indicate that the proposed metric can offer an efficient way of determining when automated predictions are acceptable and when they should be deferred to human operators.

The aging sewer infrastructure in the U.S., covering 2.1 million kilometers, encounters increasing structural issues, resulting in around 75,000 yearly sanitary sewer overflows that present serious economic, environmental, and public health hazards. Conventional inspection techniques and deterministic models do not account for the unpredictable nature of sewer decline, whereas probabilistic methods depend on extensive historical data, which is frequently lacking or incomplete. This research intends to enhance predictive accuracy for the condition of sewer pipelines through machine learning models artificial neural networks (ANNs) and multiple linear regression (MLR) by integrating factors such as pipe age, material, diameter, environmental influences, and PACP ratings. ANNs utilized ReLU activation functions and Adam optimization, whereas MLR applied regularization to address multicollinearity, with both models assessed through metrics like RMSE, MAE, and R2. The findings indicated that ANNs surpassed MLR, attaining an R2 of 0.9066 compared to MLRs 0.8474, successfully modeling nonlinear relationships while preserving generalization. MLR, on the other hand, offered enhanced interpretability by pinpointing significant predictors such as residual buildup. As a result, pipeline degradation is driven by pipe length, age, and pipe diameter as key predictors, while depth, soil type, and segment show minimal influence in this analysis. Future studies ought to prioritize hybrid models that merge the accuracy of ANNs with the interpretability of MLR, incorporating advanced methods such as SHAP analysis and transfer learning to improve scalability in managing infrastructure and promoting environmental sustainability.

This work introduces the Query/Hit (Q/H) learning model. The setup consists of two agents. One agent, Alice, has access to a streaming source, while the other, Bob, does not have direct access to the source. Communication occurs through sequential Q/H pairs: Bob sends a sequence of source symbols (queries), and Alice responds with the waiting time until each query appears in the source stream (hits). This model is motivated by scenarios with communication, computation, and privacy constraints that limit real-time access to the source. The error exponent for sequential hypothesis testing under the Q/H model is characterized, and a querying strategy, the Dynamic Scout-Sentinel Algorithm (DSSA), is proposed. The strategy employs a mutual information neural estimator to compute the error exponent associated with each query and to select the query with the highest efficiency. Extensive empirical evaluations on both synthetic and real-world datasets -- including mouse movement trajectories, typesetting patterns, and touch-based user interactions -- are provided to evaluate the performance of the proposed strategy in comparison with baselines, in terms of probability of error, query choice, and time-to-detection.

We challenge the prevailing view that oscillations in Quantization Aware Training (QAT) are merely undesirable artifacts caused by the Straight-Through Estimator (STE). Through theoretical analysis of QAT in linear models, we demonstrate that the gradient of the loss function can be decomposed into two terms: the original full-precision loss and a term that causes quantization oscillations. Based on these insights, we propose a novel regularization method that induces oscillations to improve quantization robustness. Contrary to traditional methods that focuses on minimizing the effects of oscillations, our approach leverages the beneficial aspects of weight oscillations to preserve model performance under quantization. Our empirical results on ResNet-18 and Tiny ViT demonstrate that this counter-intuitive strategy matches QAT accuracy at >= 3-bit weight quantization, while maintaining close to full precision accuracy at bits greater than the target bit. Our work therefore provides a new perspective on model preparation for quantization, particularly for finding weights that are robust to changes in the bit of the quantizer -- an area where current methods struggle to match the accuracy of QAT at specific bits.