Amortized Bayesian inference (ABI) offers fast, scalable approximations to posterior densities by training neural surrogates on data simulated from the statistical model. However, ABI methods are highly sensitive to model misspecification: when observed data fall outside the training distribution (generative scope of the statistical models), neural surrogates can behave unpredictably. This makes it a challenge in a model comparison setting, where multiple statistical models are considered, of which at least some are misspecified. Recent work on self-consistency (SC) provides a promising remedy to this issue, accessible even for empirical data (without ground-truth labels). In this work, we investigate how SC can improve amortized model comparison conceptualized in four different ways. Across two synthetic and two real-world case studies, we find that approaches for model comparison that estimate marginal likelihoods through approximate parameter posteriors consistently outperform methods that directly approximate model evidence or posterior model probabilities. SC training improves robustness when the likelihood is available, even under severe model misspecification. The benefits of SC for methods without access of analytic likelihoods are more limited and inconsistent. Our results suggest practical guidance for reliable amortized Bayesian model comparison: prefer parameter posterior-based methods and augment them with SC training on empirical datasets to mitigate extrapolation bias under model misspecification.

Former chancellor George Osborne is joining artificial intelligence (AI) giant OpenAI. He will lead its OpenAI for Countries programme, which is aimed at helping governments increase their AI capacity. Announcing his new London-based role, Osborne said it was a privilege to be joining the company. I recently asked myself the question: what's the most exciting and promising company in the world right now? The answer I believe is OpenAI, he said on X.

Negotiations over a technology deal between the UK and US have stalled due to stumbling blocks in wider trade negotiations between the two sides. The Technology Prosperity Deal - which was billed as historic when it was unveiled during US President Donald Trump's state visit in September - saw both countries pledge to co-operate in areas such as AI. However, talks on the agreement are now being held up because of US concerns about what it considers to be wider UK trade barriers. A government spokesperson said our special relationship with the US remains strong and the UK is firmly committed to ensuring the Tech Prosperity Deal delivers opportunity for hardworking people in both countries. The New York Times - which first reported the story - said there were broader disagreements between the two sides, including over digital regulations and food safety rules.

The head of Amazon Web Services has big plans to offer AI tools to businesses, but says that replacing coders with AI is "a non-starter for anyone who's trying to build a long-term company." Amid the breathless coverage and relentless AI hype of recent years, one of the world's biggest tech companies--Amazon--has been notably absent. Matt Garman, the CEO of Amazon Web Services, is looking to change that. At the recent AWS re:Invent conference, Garman announced a bunch of frontier AI models, as well as a tool designed to let AWS customers build models of their own. That tool, Nova Forge, allows companies to engage in what's known as custom pretraining--adding their data in the process of building a base model--which should allow for vastly more customized models that suit a given company's needs. Sure, it doesn't quite have the sexiness of a Sora 2 announcement, but that's not Garman's goal: He's less interested in mass consumer use of AI and more interested in enterprise solutions that'll integrate AI into all of AWS's offerings--and have a material impact on a corporate P&L. For this week's episode of, I caught up with Garman after AWS re:Invent to talk about what the company announced, whether he feels behind in the AI race, how he thinks about managing huge teams (and managing internal dissent), and why he's not convinced that AI is (or should be) the great job thief of our era. We always start these conversations with some very quick questions, like a warmup. If AWS had a mascot, what would it be? We have a big S3 bucket sometimes that goes around, so we'll call it that. Sorry, what is an S3 bucket? An S3 bucket is like a thing that you store your S3 objects in, but we actually have a large foam big bucket that walks around and actually looks like a paint bucket. So you do have a mascot. Well, S3 has a bucket, it has a mascot. It's probably the closest we have, and I like it. What's the most expensive mistake you've ever made? Personally, the most expensive mistake I ever made was playing basketball too long and I tore my Achilles. So that cost me about nine months of being able to walk. I probably should have known that into my thirties I was well past basketball-playing age.

Ben & Jerry's row deepens as three board members removed Three members of Ben & Jerry's independent board will no longer be eligible to serve in their roles, after the ice cream company introduced a new set of governance practices. These include a nine-year limit set on board members' terms. Chair Anuradha Mittal, who earlier said she had no plans to resign under pressure, is among those affected. The move was criticised by the company's co-founder Ben Cohen, who called it a blatant power grab designed to strip the board of legal authority and independence. His remarks are the latest in a long-running row between Ben and Jerry's and its owner over the Cherry Garcia maker's social activism and the continued independence of its board.

What is in the 28-point US plan for Ukraine? 'Ukraine is running out of men, money and time' Can the US get all sides to end the war? Why is Europe opposing Trump's peace plan? A Russian drone attack killed a 62-year-old Ukrainian man as he was riding a bicycle in the Velyka Pysarivka community of Ukraine's Sumy region, Governor Oleh Hryhorov said in a post on the Telegram messaging app. Russian forces launched 850 attacks on Ukraine's Zaporizhia region in a single day, injuring 14 people and damaging houses, cars and infrastructure, Governor Ivan Fedorov said on Telegram.

UK launches taskforce to'break down barriers' for women in technology The government has launched a new taskforce it says will help women enter, stay and lead in the UK tech sector. Led by technology secretary Liz Kendall, it will see female leaders from tech companies and organisations advise the government on how to boost diversity and economic growth in the industry. BCS, the Chartered Institute for IT, recently suggested women accounted for only 22% of those working in IT specialist roles in the UK. Ms Kendall said the Women in Tech group would break down the barriers that still hold too many people back. When women are inspired to take on a role in tech and have a seat at the table, the sector can make more representative decisions, build products that serve everyone, she said.

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.

Proper quantification of predictive uncertainty is essential for the use of machine learning in safety-critical applications. V arious uncertainty measures have been proposed for this purpose, typically claiming superiority over other measures. In this paper, we argue that there is no single best measure. Instead, uncertainty quantification should be tailored to the specific application. To this end, we use a flexible family of uncertainty measures that distinguishes between total, aleatoric, and epistemic uncertainty of second-order distributions. These measures can be instantiated with specific loss functions, so-called proper scoring rules, to control their characteristics, and we show that different characteristics are useful for different tasks. In particular, we show that, for the task of selective prediction, the scoring rule should ideally match the task loss. On the other hand, for out-of-distribution detection, our results confirm that mutual information, a widely used measure of epistemic uncertainty, performs best. Furthermore, in an active learning setting, epistemic uncertainty based on zero-one loss is shown to consistently outperform other uncertainty measures.

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve diagnosis, risk assessment, and patient outcomes. However, existing methods for time series pattern discovery face major challenges, including high computational complexity, limited interpretability, and difficulty in capturing meaningful temporal structures. To address these gaps, we introduce a novel learning framework that jointly trains two Transformer models using complementary time series representations: shapelet-based representations to capture localized temporal structures and traditional feature engineering to encode statistical properties. The learned shapelets serve as interpretable signatures that differentiate time series across classification labels. Additionally, we develop a visual analytics system -- SigTIme -- with coordinated views to facilitate exploration of time series signatures from multiple perspectives, aiding in useful insights generation. We quantitatively evaluate our learning framework on eight publicly available datasets and one proprietary clinical dataset. Additionally, we demonstrate the effectiveness of our system through two usage scenarios along with the domain experts: one involving public ECG data and the other focused on preterm labor analysis.