Goto

Collaborating Authors

 Europe


Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors

arXiv.org Machine Learning

We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic information to justify committed exploitation of the averaging distribution? We answer this question in closed form for Bayesian decision trees (BDTs) with Dirichlet-Multinomial leaf models and a Catalan-exponential tree-size prior (Schetinin&Jakaite, 2025), establishing a complete non-asymptotic theory of rational commitment thresholds.


The best new popular science books of June 2026

New Scientist

This is a month to look out for some powerful new books, with authors taking on challenges of all sorts and imagining whole new worlds. There are fresh ways to think about a cancer diagnosis, a book tackling the real inner world of hormones, in which we are all hormonal all the time, plus a major re-envisioning of the natural world where we abandon the shallows of competition for the depth and intricacies of connection and togetherness. It's quite hard going to get an up-to-date grip on human evolution, even for the best-briefed adult, so a book with sophisticated text and excellent illustrations and diagrams can only be a good thing. Especially if it is curated and edited by Alice Roberts, biological anthropologist, palaeopathologist, broadcaster - and professor of public engagement in science at the University of Birmingham, UK. She worked with a generous-sized international team of experts in many fields of human evolution, including archaeology, palaeontology, anthropology and cognitive science.


How just a spoonful a day of the German-favourite sauerkraut can boost gut health and lower cholesterol

Daily Mail - Science & tech

Quivering Karmelo Anthony is convicted of murdering Austin Metcalf, 17... but now prosecutors have granted him Hail Mary that could see him jailed for as little as TWO YEARS Trump's $70B immigration crackdown passes the House as sneaky loophole allows $1.8B weaponization'slush fund' to survive I watched footage of the race crime that split America. She's always by Trump's side, trusted with the White House's biggest secrets... and she influences millions Trump ERUPTS behind closed doors as top Republican pleads with him to axe Tulsi Gabbard's spy-chief replacement Leaked transcript of UNAIRED 60 Minutes interview exposes REAL reason'callous' CBS star Scott Pelley'deserved to be fired' Epstein's massage fixer looks PETRIFIED as she's dragged into explosive congressional grilling - and reveals jaw-dropping'blackmail' theory Caitlyn Jenner biographer and Robin Riker's ex William Hasley found dead on hiking trail at 78 Eva Longoria reunites with ex Tony Parker 15 years after cheating scandal split... as shocked fans react Shamed ex mayor Misty Roberts is sentenced to 90 DAYS as she's branded a'predator with hair extensions' by enraged mother of 17-year-old sex assault victim My compulsive bathroom habit that so many are guilty of left me in excruciating pain. DR STUART reveals early signs... cures that work in days... and when to worry Inside Travis Kelce's plan to become'the Shaq of the NFL' after wedding Taylor Swift Moment Real Housewives star Lenny Hochstein's sexual assault accuser'dances' as she leaves Star Island mansion - before filing $100k civil lawsuit Madonna's wild sex claim about JFK Jr now draws surprising response from his outspoken nephew Jack Schlossberg Zodiac killer case takes bombshell turn as unsolved cipher is CRACKED... and America's top codebreakers say evidence is all pointing to one man Kennedy heir Jack Schlossberg concedes Trump is a'genius' as aspiring congressman reveals what he'deeply respects' about president'Great' mom, 32, tried to gas herself and her three young kids to death after inviting them to'popcorn sleepover' in car, prosecutors allege Want to lose up to a stone in six weeks, plus boost your mood and energy levels? Fermented foods from kefir to kombucha are having a moment, hailed for their gut health benefits. But experts say we could be overlooking one of the healthiest ferments out there: sauerkraut.


Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach

arXiv.org Machine Learning

We study quantile regression in an extrapolation regime where the covariate takes unusually large values. Under regular variation assumptions, extreme observations can be effectively characterized through their angular components, enabling learning strategies that focus on the angle of the most extreme observations. This approach is formalized through the minimization of an asymptotic conditional risk that localizes learning in the tail of the covariate distribution. We propose a novel Support Vector Machine (SVM) framework for extreme quantile regression, leveraging reproducing kernel Hilbert spaces to handle high-dimensional and nonlinear settings. Our method also accommodates unbounded response variables and avoids restrictive transformations. We establish finite-sample learning guarantees under mild regularity assumptions. The proposed framework unifies ideas from statistical learning and multivariate extremes, providing a tractable and theoretically grounded approach to extrapolation. We complement our theoretical findings with an empirical study on river flow data from the Danube, demonstrating the practical relevance of our methods.


How human error became a weapon against large language models

New Scientist

Alan Turing proposed a test for machine intelligence: could a computer convince a human it was human? Recently, a friend told me over coffee about some disheartening feedback she had received. "They said it was good," she said, "but that it read like it was written by AI." Knowing her, I understood immediately what had happened. Her credibility was being questioned not because her work was poor, but because it was too good - too clear, too fluent, too polished. The rapid acceleration of artificial intelligence tools is changing how we think about good writing.


This model is not a real person: how AI is shaking up fashion – video

The Guardian

From digital twins to models'sculpted' by programmers, generative AI has been popping up all over the fashion industry. When an Australian e-commerce retailer started using AI-generated models to sell products, lifestyle editor Alyx Gorman had to see if the garments were more than mere pixels. The Iconic, which sells the dress worn in this video, said in a statement: 'Where AI-generated imagery is used to advertise products for sale on our platform, our expectation is that it is clearly labelled and that the product itself is represented as accurately as possible for customers.' Meanwhile, Atoir, the designer, said: 'The Australian fashion industry is highly competitive, particularly for independent brands. We believe that when used responsibly, tools like this can help smaller businesses to operate with greater agility while still maintaining the creative standards and product integrity that matter to both the brand and the customer.'


Ukrainian drone attacks hit multiple Russian targets, including refinery

Al Jazeera

Ukrainian drones have struck energy and industrial targets across several Russian regions, Russian authorities say, in an escalating campaign of strikes against infrastructure. In Saratov, a region on the Volga River with several oil refineries that has come under regular Ukrainian attack in recent years, Governor Roman Busargin said on Sunday on Telegram that "civil infrastructure" had been damaged in the overnight strikes. In the Kirov region, northeast of Moscow and about 1,300km (800 miles) from Ukraine, Governor Alexander Sokolov said drones had hit a facility in the Urzhumsky district. The Ukrainian army confirmed the attack, saying it had also hit the Lazarevo oil-pumping station in the region. Governors in the Rostov, Voronezh and Belgorod regions, all of which border Ukraine, also reported strikes, and three civilians were injured in Belgorod.


Drone hits nuclear facility as Kyiv and Moscow trade strikes

The Japan Times

Rescuers work at the site of an apartment building hit by a Russian drone strike in Zaporizhzhia, Ukraine, on Saturday. Ukraine and Russia traded aerial attacks on Saturday as President Volodymyr Zelenskyy held what he called a special meeting on next steps with top aides. A Ukrainian drone struck the machine room building of one of power units at the Russian-occupied Zaporizhzhia nuclear power plant in southeastern Ukraine on Saturday afternoon, causing unspecified damage, Interfax reported, citing Rosatom Chief Executive Officer Alexey Likhachev. Core equipment wasn't damaged, he said. Ukraine's southern military command denied any strikes, saying its military personnel "act exclusively within the framework of international humanitarian law and are aware of the consequences of any actions against nuclear facilities." In a post on Facebook late Saturday, it added, "It is the Russian Federation that has illegally kept the Zaporizhzhia Nuclear Power Plant under military control since March 2022, turning a civilian nuclear facility into an element of military infrastructure."


SoftBank plans up to 75 billion investment in French AI centers

The Japan Times

SoftBank Group plans to invest as much as €75 billion ($87 billion) to build 5 gigawatts of artificial intelligence data center capacity in France, saying the country is poised to become a top European hub for AI infrastructure. The first phase comprises an initial €45 billion investment to deliver 3.1 gigawatts of AI data center capacity in the Hauts-de-France region by 2031, SoftBank said Saturday in a statement. The commitment, which SoftBank called its biggest AI infrastructure investment in Europe, reflects personal diplomacy between Emmanuel Macron and SoftBank founder Masayoshi Son, who met during the French president's visit to Japan this year. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right. With your current subscription plan you can comment on stories.


How Putin became master of the image

BBC News

Throughout his time as Russian President, Vladimir Putin has been alert to the power of visual imagery. The first time I interviewed him in 2001, an aide swooped in just before the cameras went live and snatched away the small water glasses on the table in front of us. Why did you do that? We wouldn't want anyone to think they were for vodka, came the reply. And anyway, we can't risk a glass spilling live on TV.