Neural network surrogate models have emerged as a promising approach to model solution fields for a wide variety of boundary value problems encountered in physical modeling. Stochastic problems represent an area of particularly high interest because of the potential to significantly reduce the repeated evaluation of expensive forward models via traditional numerical solvers when conducting parametric analysis. However, many studies found in the literature primarily focus on the ability of neural network surrogate models to represent deterministic samples or mean field solutions and largely overlook surrogate model performance at the tails of the distribution. The present study examines in detail the ability of neural network surrogate models to capture the full distribution of solution fields over the entire probability space, while emphasis is placed at the tails of the distribution. Serving as a canonical problem is the heat conduction equation with a highly stochastic source term, inducing extremely large variation in the thermal solution field. Comparisons are made between a classic feed-forward fully connected network and a Deep Operator Network architecture, using both data-driven and physics-informed loss functions. Results show that the worst-case prediction errors are an order of magnitude larger than the mean field error, highlighting the importance of the outlier samples. The large errors associated with extreme samples result from the networks having to extrapolate beyond the bounds of the training data. A method for identifying these samples is presented along with a discussion of potential approaches to account of their errors. Among the models considered, the fully connected neural network trained using a weak form residual loss performs best in handling these extrapolated inputs, achieving the highest prediction accuracy for the numerically produced datasets.

We develop a skew-adaptive extension of split conformal prediction for regression. The method starts from an asymmetric interval family centered at a point prediction and uses the gauge approach to deduce the conformity score induced by this family. The inverse hyperbolic sine transform of signed scaled residuals provides the training target for an additional predictive model, whose role is to learn how predictive uncertainty should tilt across the feature space. The resulting procedure preserves the finite-sample marginal validity of split conformal prediction under exchangeability, while producing intervals that adapt to both local scale and local skewness. We also develop a calibration-sample-based estimator for comparing the expected relative future width of the skew-adaptive and classical scaled-score intervals. Experiments on a variety of datasets indicate gains in prediction interval efficiency over the scaled-score construction and conformalized quantile regression, and show that the proposed estimator closely matches the corresponding average width ratio observed on the test sample.

Flexible continuous-time survival modeling is critical for capturing complex time-varying hazard dynamics in high-dimensional data; however, training such models remains challenging due to the intractable integral required for likelihood estimation. We introduce QSurv, a scalable deep learning framework that enables nonparametric continuous-time modeling without relying on time discretization or restrictive distributional assumptions. We propose a training objective based on Gauss-Legendre numerical quadrature, which approximates the cumulative hazard with high-order accuracy while facilitating efficient end-to-end training via standard backpropagation. Furthermore, to effectively capture non-stationary hazard dynamics in complex architectures, we introduce time-conditioned low-rank adaptation, a mechanism that conditions general neural backbones on time by dynamically modulating weights via low-rank updates. We provide theoretical analysis establishing approximation error bounds for cumulative-hazard evaluation. Comprehensive experiments across synthetic benchmarks, large-scale real-world tabular datasets, and high-dimensional medical imaging tasks demonstrate that QSurv achieves competitive predictive performance with advantages in instantaneous hazard function estimation, enabling more interpretable characterization of time-varying risk patterns.

Differential privacy changes the effective sample size governing CVaR learning. For tail mass $τ$, the privacy-relevant sample size is not $n$, but $nτ$; equivalently, the effective private tail sample size is $εnτ$. Private CVaR excess risk decomposes into ordinary tail-risk statistical error and a privacy price. This decomposition is complete for scalar estimation and finite classes: scalar estimation has rate $Θ(B \min\{1,(nτ)^{-1/2}+(εnτ)^{-1}\})$, and finite classes of size $M$ have rate $Θ(B \min\{1,\sqrt{\log(2M)/(nτ)}+\log(2M)/(εnτ)\})$. These complete rates hold under pure DP, and their lower bounds extend to approximate DP in the stated small-$δ$ regimes. For convex Lipschitz learning, modular upper and lower reductions show that the CVaR-specific privacy term necessarily scales as $1/(εnτ)$, with dimension dependence inherited from private stochastic convex optimization. Together, these results identify ordinary private learning on $Θ(nτ)$ informative tail records as the canonical hard subproblem inside private CVaR learning.

Dependence among marginally constrained observations can break a finite-sample barrier. To formalize this phenomenon, we introduce the \emph{minimum list entropy coupling} $H(P\|Q_1,\dots,Q_m)$, the minimum conditional entropy $H(X|Y_1,\dots,Y_m)$ over all joint distributions with prescribed discrete marginals $X\sim P$ and $Y_i\sim Q_i$. Unlike classical formulations based on independent observations, our model allows $Y_1,\dots,Y_m$ to be arbitrarily dependent while keeping each marginal fixed. This enlarged coupling space reveals a sharp dichotomy: independent observations reduce residual uncertainty exponentially, whereas dependent observations can eliminate it exactly after finitely many samples. We characterize this zero-entropy regime through necessary and sufficient conditions and give concrete structural criteria under which it occurs. In particular, under mild support assumptions, zero entropy is achieved with $O(\log(1/P_{\min}))$ observations, where $P_{\min}$ is the minimum nonzero mass of $P$. We also develop a greedy algorithm with monotone approximation guarantees for computing $H(P\|Q_1,\dots,Q_m)$. Finally, we show that the same framework formalizes finite-sample limits in distribution-matching representation learning and randomness extraction, where zero entropy corresponds to exact recovery and exact extraction.

Why does Amazon have no Western rivals? Vitamins, repair tape and a jar of mango chutney - just some of what my household bought last month via Amazon's sprawling online shopping platform. We also shopped at the company's supermarket chain Whole Foods, streamed its TV shows, read books on Kindle e-readers, and browsed countless websites no doubt powered by Amazon Web Services (AWS), its highly profitable cloud-computing business. And that isn't half of the interconnected products and services offered by the global behemoth, which earlier this year overtook US superstore giant Walmart to become the world's largest company by annual sales. But why does Amazon, launched by Jeff Bezos in 1995 as an online bookstore out of a rented garage, have so few serious rivals in the West when it comes to e-commerce?

What would make the UK a better place to live? People across the UK are being urged to share their vision for how their community and country's future should look, as part of a major new research project. The National Conversation is being launched with voice notes submitted by high-profile figures, including former footballer Gary Lineker, Chief Rabbi Sir Ephraim Mirvis, and broadcaster Mariella Frostrup. Participants will be asked to complete a survey carried out by researchers from the University of Oxford and leave a 60-second voice note. AI models will then be used to analyse thousands of responses to map what could bring us together.

Inside the'kill-zone' on Ukraine's front line, where new weapons have transformed war After 225 days stuck in a front-line foxhole, the Ukrainian infantryman's muscles were so weak he could barely walk. His commanders had tried five times to swap him with another soldier - but they could never reach him. Rotating soldiers on the front line in eastern Ukraine is extremely difficult because of the constant threat of drones. This area near Kostyantynivka is currently one of the most dangerous hotspots and the Ukrainian military admits that Russian forces have reached its outskirts. Known as Kenya, the infantryman took two days to walk 11km (6.8 miles) to get back to his brigade, avoiding mines and hiding from drones to get out.

ISIS shadow commander Abu-Bilal al-Minuki was killed in a precision strike in Nigeria after human intelligence penetrated defenses that had shielded him for years, analyst says.

Bulgarian pop star Dara was met by a crowd of fans in Sofia airport on Sunday, celebrating her historic Eurovision win. The 27-year-old's tune Bangaranga won Bulgaria its first ever title in the song contest. Thank you for being here, she told fans as she arrived in the Bulgarian capital, Sofia, before adding I cannot wait to dip my toes in this atmosphere. Russia launched one of the biggest air strikes on Kyiv since the start of the war with several apartment blocks hit. Why is the Princess of Wales in Italy this week?