This paper compares different methods for forecasting the term structure of U.S. and European zero-coupon government bonds using both traditional econometric and Machine Learning (ML) approaches. We compare classical models (e.g., Dynamic Nelson-Siegel (DNS) and Principal Component Analysis (PCA)) with different Neural Network (NN) architectures, including those inspired by the classical models, on the U.S. Treasury market and bonds issued by the European Central Bank (ECB). To enhance predictive performance, macroeconomic variables are incorporated. The findings for both markets are separately analyzed and compared. To this end, we propose a robust model evaluation framework combining statistical accuracy metrics - such as RMSE, MAE, and directional accuracy - with the economic relevance of a quantitative bond trading strategy. Results show that NNs consistently outperform traditional models in both forecasting accuracy and portfolio performance. For the U.S., the most effective approach is a direct-forecasting NN that incorporates DNS factors to reduce the dimensionality of zero-rate data and an Autoencoder (AE) to extract macroeconomic features, while for Europe, the optimal model is a factor-based NN using PCA-derived zero-rate factors without the integration of macroeconomic variables. Overall, the paper demonstrates how combining traditional modeling approaches with modern ML techniques and evaluation can improve yield curve forecasts and support applications in fixed-income portfolio construction.

Bayesian filtering of partially and noisily observed dynamical systems seeks to infer the evolving conditional distribution of the state of a dynamical system, given observations, in an online fashion. This Bayesian filtering distribution is the natural object for uncertainty quantification, but it is rarely available as a supervised learning target. However, one can often use the forecast model to generate synthetic system trajectories, along with synthetic observations. We introduce the proper scoring ensemble filter (PSEF), an ensemble data assimilation method based on training an analysis map to approximate the filtering distribution using only synthetic state--observation trajectories. The analysis step is represented as a permutation-invariant, transformer-based map that takes as input a forecast ensemble and observations, producing an analysis ensemble. Training is based on strictly proper scoring rules -- with the energy score used in our implementation -- so that probabilistic accuracy is rewarded over the whole probability distribution. We prove that, under a realizability assumption, the population objective is minimized by the true Bayesian filtering distribution. We also derive the finite-ensemble empirical objective used in training and relate its single state--observation trajectory form to the population objective, using a mean-field consistency argument. Numerical experiments show that the learned filter accurately approximates challenging filtering distributions, including nonlinear, non-Gaussian, and multi-modal posteriors, and achieves stronger performance in data assimilation tasks than classical methods or learning-based methods with mean-squared-error objectives. For close-to-Gaussian problems, learning a correction to the EnKF is the best approach, while for highly non-Gaussian problems an end-to-end approach that discards this inductive bias is superior.

Modern machine learning systems have outgrown their origins as isolated predictive constructs, evolving into complex socio-technical architectures that actively mediate human opportunity. As algorithms increasingly determine access to economic and social opportunities, it has become widely recognized that these systems are deeply embedded with the structural inequalities and prejudices of their environments. The field of algorithmic fairness emerged in response to the growing recognition that models optimized for predictive accuracy can systematically disadvantage marginalized groups. Early mitigation strategies, however, rested on fragile simplifications that limited their effectiveness in complex sociotechnical environments. This thesis identifies and addresses two fundamental limitations of contemporary fairness paradigms: the reliance on deterministic point estimates for auditing and the treatment of individuals as isolated entities devoid of structural context. First, the diagnosis of algorithmic unfairness has traditionally depended on scalar metrics that fail to capture the nuances of real-world deployment. This deterministic approach ignores the high statistical variance inherent in small, intersectional groups, often leading to false alarms or missed detections of bias. Furthermore, standard auditing struggles with the opacity of black-box models, frequently conflating unjustifiable bias with the influence of legitimate features.

We develop a general framework for analyzing representation costs of parametric data-fitting methods through their parameter-space regularizers. From this abstract perspective, we define representation costs for arbitrary parametric models and reveal their induced (native) function spaces. This unifies recent function-space views of data-fitting methods. We also prove that many natural results hold in this abstract setting, including representer theorems for parametric methods on their native spaces. The framework also rigorously connects parametric methods with their equivalent nonparametric descriptions under sufficient overparameterization. Classical methods and their native spaces, such as kernel methods / reproducing kernel Hilbert spaces, wavelets / Besov spaces, and shallow neural networks / variation spaces emerge as special cases of our abstract framework. A byproduct of "axiomatizing" the study of representation costs is that we also immediately obtain new results for deep neural networks: For depth-$L$ feedforward ReLU networks, their induced native spaces are $p$-normable quasi-Banach spaces with $p = 2/L$. This reveals that the inductive bias of deep neural networks (as given by the representation cost) cannot be captured by norms for depths $L > 2$.

This paper presents a probabilistic framework for online test-time adaptation problems. In them, a model is trained on labeled data but must adapt to unlabeled data at test time under the assumption that training and test distributions potentially differ, that is, there might have been a distributional shift. The framework is based on a state-space modelling architecture from which parameter learning, parameter time evolution, prior tuning, and prediction can be characterized.

Smoke rises from Crimea Bridge on Monday. The Ukrainian army is pounding supply routes and striking energy facilities across Crimea. Warsaw - For Yulia, a 23-year-old resident of Crimea, nights have become sleepless due to increased Ukrainian drone attacks on the peninsula annexed by Russia in 2014. Kyiv's army is pounding supply routes and striking energy facilities across the Black Sea territory -- a campaign it sees as fair retribution for Moscow's daily barrages of Ukrainian cities, and one that it hopes will turn the tide of the four-year war in its favor. On Thursday, the Moscow-installed governor of Crimea announced power cuts across the peninsula, which despite the war had been a popular holiday destination for Russians. In a time of both misinformation and too much information, quality journalism is more crucial than ever.

Family secrets of Trump's closest White House aide: Natalie Harp's estranged socialist brother reveals ugly details of feud... and the tragedy that shattered everything Clay Aiken opens up about the'catastrophic' aftermath of grabbing Kelly Ripa's face live on air Iran's suicide drone strike on US ally threatens Trump's fragile peace in Strait of Hormuz Live, laugh, love mom charged with incestuous abuse of her two teenage adopted sons demands DIVORCE from handsome husband... as shocking custody request revealed Harry and Meghan may smugly believe the Establishment'plot' to return them is working. But they have no idea what Kate and William are thinking. My royal insiders have not held back... it's damning: RICHARD EDEN America's hottest housing market is a surprising East Coast city where 58% of homes sell above asking price Eva Longoria, 51, drops jaws in white string bikini as she displays gym-honed body during family beach day in Spain... after fleeing US Beloved Fox & Friends star says she's quitting after 22 years because of serious health condition Truth about Taylor Swift's'hookups' with ex Matty Healy... revealed by friends as his new model fiancée is accused of kinky pre-wedding stunts to humiliate Swift I lost a stone in 28 days WITHOUT weight-loss jabs: At size 32, I couldn't bear being fat anymore. This old-fashioned diet got me holiday-ready in weeks... YOU can do it too with these 6 steps Eerie'apocalyptic' sounds heard on Mount Shasta lead horseback riders to bizarre discovery Angelina Jolie war with Brad Pitt over sale of lavish French wine estate turns in Brad's favor as secretive vodka billionaire buyer forced to testify Lavish photos show Mark Zuckerberg's secretive new $170m hideout: First look behind the guarded gates of billionaire's palatial bunker Lionel Richie, 77, 'taken to hospital by ambulance' after dizzy spell onstage saw him end concert An anniversary present from Harry? Duchess of Sussex debuts new ring - and royal fans say it looks very similar to Kate's engagement band Grotesque'zombie squirrels' with oozing flesh pods spark alarm across the US BRYONY GORDON: Have you been tempted by the'Ozempic of alcohol' pill? I certainly was, but I've since faced a humbling truth.

Environment Energy Renewables 300-year-old shipwreck found near world's largest offshore wind farm The three rare ingots discovered under 131-feet of water hearken back to England's former lead industry. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. The ingots featured lettered imprints similar to other artifacts dating to the 17th century. Breakthroughs, discoveries, and DIY tips sent six days a week. By signing up, you confirm you are 16+, will receive newsletters and promotional content and agree to our Terms of Use and acknowledge the data practices in our Privacy Policy .

Is the war entering a new phase? At least five people have been killed in a Ukrainian attack on Russia and the Crimean peninsula as Kyiv steps up strikes, according to the Russian-appointed governor in the annexed region. Crimea Governor Sergey Aksyonov said two people, including a child, were killed and two others wounded following "overnight enemy attacks" into Thursday. Russia's defence ministry said 269 Ukrainian drones were downed over Russia and Crimea overnight. The head of the Krasnoarmeysk district in Krasnodar Krai said debris from a drone strike triggered an oil depot fire.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?