In this work, we investigate the existence and effect of percolation in training deep Neural Networks (NNs) with dropout. Dropout methods are regularisation techniques for training NNs, first introduced by G. Hinton et al. (2012). These methods temporarily remove connections in the NN, randomly at each stage of training, and update the remaining subnetwork with Stochastic Gradient Descent (SGD). The process of removing connections from a network at random is similar to percolation, a paradigm model of statistical physics. If dropout were to remove enough connections such that there is no path between the input and output of the NN, then the NN could not make predictions informed by the data. We study new percolation models that mimic dropout in NNs and characterise the relationship between network topology and this path problem. The theory shows the existence of a percolative effect in dropout. We also show that this percolative effect can cause a breakdown when training NNs without biases with dropout; and we argue heuristically that this breakdown extends to NNs with biases.

Satellite data of atmospheric pollutants are often available only at coarse spatial resolution, limiting their applicability in local-scale environmental analysis and decision-making. Spatial downscaling methods aim to transform the coarse satellite data into high-resolution fields. In this work, two widely used deep learning architectures, the super-resolution deep residual network (SRDRN) and the encoder-decoder-based UNet, are considered for spatial downscaling of tropospheric ozone. Both methods are extended with a lightweight temporal module, which encodes observation time using either sinusoidal or radial basis function (RBF) encoding, and fuses the temporal features with the spatial representations in the networks. The proposed time-aware extensions are evaluated against their baseline counterparts in a case study on ozone downscaling over Italy. The results suggest that, while only slightly increasing computational complexity, the temporal modules significantly improve downscaling performance and convergence speed.

Kernel density estimation is a key component of a wide variety of algorithms in machine learning, Bayesian inference, stochastic dynamics and signal processing. However, the unsupervised density estimation technique requires tuning a crucial hyperparameter: the kernel bandwidth. The choice of bandwidth is critical as it controls the bias-variance trade-off by over- or under-smoothing the topological features. Topological data analysis provides methods to mathematically quantify topological characteristics, such as connected components, loops, voids et cetera, even in high dimensions where visualization of density estimates is impossible. In this paper, we propose an unsupervised learning approach using a topology-based loss function for the automated and unsupervised selection of the optimal bandwidth and benchmark it against classical techniques -- demonstrating its potential across different dimensions.

Machine learning on graphs has recently achieved impressive progress in various domains, including molecular property prediction and chip design. However, benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent evaluation protocols, which hampers reproducibility and broader progress. To address this, we introduce GraphBench, a comprehensive benchmarking suite that spans diverse domains and prediction tasks, including node-level, edge-level, graph-level, and generative settings. GraphBench provides standardized evaluation protocols -- with consistent dataset splits and performance metrics that account for out-of-distribution generalization -- as well as a unified hyperparameter tuning framework. Additionally, we benchmark GraphBench using message-passing neural networks and graph transformer models, providing principled baselines and establishing a reference performance. See www.graphbench.io for further details.

Model combination is a powerful approach to achieve superior performance with a set of models than by just selecting any single one. We study both theoretically and empirically the effectiveness of ensembles of Multi-Frequency Echo State Networks (MFESNs), which have been shown to achieve state-of-the-art macroeconomic time series forecasting results (Ballarin et al., 2024a). Hedge and Follow-the-Leader schemes are discussed, and their online learning guarantees are extended to the case of dependent data. In applications, our proposed Ensemble Echo State Networks show significantly improved predictive performance compared to individual MFESN models.

Covariate adjustment is an approach to improve the precision of trial analyses by adjusting for baseline variables that are prognostic of the primary endpoint. Motivated by the SEARCH Universal HIV Test-and-Treat Trial (2013-2017), we tell our story of developing, evaluating, and implementing a machine learning-based approach for covariate adjustment. We provide the rationale for as well as the practical concerns with such an approach for estimating marginal effects. Using schematics, we illustrate our procedure: targeted machine learning estimation (TMLE) with Adaptive Pre-specification. Briefly, sample-splitting is used to data-adaptively select the combination of estimators of the outcome regression (i.e., the conditional expectation of the outcome given the trial arm and covariates) and known propensity score (i.e., the conditional probability of being randomized to the intervention given the covariates) that minimizes the cross-validated variance estimate and, thereby, maximizes empirical efficiency. We discuss our approach for evaluating finite sample performance with parametric and plasmode simulations, pre-specifying the Statistical Analysis Plan, and unblinding in real-time on video conference with our colleagues from around the world. We present the results from applying our approach in the primary, pre-specified analysis of 8 recently published trials (2022-2024). We conclude with practical recommendations and an invitation to implement our approach in the primary analysis of your next trial.

In this paper, we develop a novel accelerated fixed-point-based framework using delayed inexact oracles to approximate a fixed point of a nonexpansive operator (or equivalently, a root of a co-coercive operator), a central problem in scientific computing. Our approach leverages both Nesterov's acceleration technique and the Krasnosel'skii-Mann (KM) iteration, while accounting for delayed inexact oracles, a key mechanism in asynchronous algorithms. We also introduce a unified approximate error condition for delayed inexact oracles, which can cover various practical scenarios. Under mild conditions and appropriate parameter updates, we establish both $\mathcal{O}(1/k^2)$ non-asymptotic and $o(1/k^2)$ asymptotic convergence rates in expectation for the squared norm of residual. Our rate significantly improves the $\mathcal{O}(1/k)$ rates in classical KM-type methods, including their asynchronous variants. We also establish $o(1/k^2)$ almost sure convergence rates and the almost sure convergence of iterates to a solution of the problem. Within our framework, we instantiate three settings for the underlying operator: (i) a deterministic universal delayed oracle; (ii) a stochastic delayed oracle; and (iii) a finite-sum structure with asynchronous updates. For each case, we instantiate our framework to obtain a concrete algorithmic variant for which our convergence results still apply, and whose iteration complexity depends linearly on the maximum delay. Finally, we verify our algorithms and theoretical results through two numerical examples on both matrix game and shallow neural network training problems.

Statistical learning under distributional drift remains insufficiently characterized: when each observation alters the data-generating law, classical generalization bounds can collapse. We introduce a new statistical primitive, the reproducibility budget $C_T$, which quantifies a system's finite capacity for statistical reproducibility - the extent to which its sampling process can remain governed by a consistent underlying distribution in the presence of both exogenous change and endogenous feedback. Formally, $C_T$ is defined as the cumulative Fisher-Rao path length of the coupled learner-environment evolution, measuring the total distributional motion accumulated during learning. From this construct we derive a drift-feedback generalization bound of order $O(T^{-1/2} + C_T/T)$, and we prove a matching minimax lower bound showing that this rate is minimax-optimal. Consequently, the results establish a reproducibility speed limit: no algorithm can achieve smaller worst-case generalization error than that imposed by the average Fisher-Rao drift rate $C_T/T$ of the data-generating process. The framework situates exogenous drift, adaptive data analysis, and performative prediction within a common geometric structure, with $C_T$ emerging as the intrinsic quantity measuring distributional motion across these settings.

While large margin classifiers are originally an outcome of an optimization framework, support vectors (SVs) can be obtained from geometric approaches. This article presents advances in the use of Gabriel graphs (GGs) in binary and multiclass classification problems. For Chipclass, a hyperparameter-less and optimization-less GG-based binary classifier, we discuss how activation functions and support edge (SE)-centered neurons affect the classification, proposing smoother functions and structural SV (SSV)-centered neurons to achieve margins with low probabilities and smoother classification contours. We extend the neural network architecture, which can be trained with backpropagation with a softmax function and a cross-entropy loss, or by solving a system of linear equations. A new subgraph-/distance-based membership function for graph regularization is also proposed, along with a new GG recomputation algorithm that is less computationally expensive than the standard approach. Experimental results with the Friedman test show that our method was better than previous GG-based classifiers and statistically equivalent to tree-based models.

Firms often develop targeting policies to personalize marketing actions and improve incremental profits. Effective targeting depends on accurately separating customers with positive versus negative treatment effects. We propose an approach to estimate the conditional average treatment effects (CATEs) of marketing actions that aligns their estimation with the firm's profit objective. The method recognizes that, for many customers, treatment effects are so extreme that additional accuracy is unlikely to change the recommended actions. However, accuracy matters near the decision boundary, as small errors can alter targeting decisions. By modifying the firm's objective function in the standard profit maximization problem, our method yields a near-optimal targeting policy while simultaneously estimating CATEs. This introduces a new perspective on CATE estimation, reframing it as a problem of profit optimization rather than prediction accuracy. We establish the theoretical properties of the proposed method and demonstrate its performance and trade-offs using synthetic data.