The Recommender then observes the Agent's selected item

Health Nutrition Gastronomists study 100 years of menus to reveal food's political power Menus from 457 diplomatic meals served in Portugal reveal how food can make and break alliances. Breakthroughs, discoveries, and DIY tips sent every weekday. A nice, warm meal is one of the great unifiers. Food communicates everything from love and tradition like a home cooked dinner with all of the trimmings and even political stances. At a state dinner, food has the power to cultivate understanding across cultures-or potentially create tensions.

We study hypothesis testing over a heterogeneous population of strategic agents with private information. Any single test applied uniformly across the population yields statistical error that is sub-optimal relative to the performance of an oracle given access to the private information. We show how it is possible to design menus of statistical contracts that pair type-optimal tests with payoff structures, inducing agents to self-select according to their private information. This separating menu elicits agent types and enables the principal to match the oracle performance even without a priori knowledge of the agent type. Our main result fully characterizes the collection of all separating menus that are instance-adaptive, matching oracle performance for an arbitrary population of heterogeneous agents. We identify designs where information elicitation is essentially costless, requiring negligible additional expense relative to a single-test benchmark, while improving statistical performance. Our work establishes a connection between proper scoring rules and menu design, showing how the structure of the hypothesis test constrains the elicitable information. Numerical examples illustrate the geometry of separating menus and the improvements they deliver in error trade-offs. Overall, our results connect statistical decision theory with mechanism design, demonstrating how heterogeneity and strategic participation can be harnessed to improve efficiency in hypothesis testing.

The paper presents a machine learning approach to design digital interfaces that can dynamically adapt to different users and usage strategies. The algorithm uses Bayesian statistics to model users' browsing behavior, focusing on their habits rather than g roup preferences. It is distinguished by its online incremental learning, allowing reliable predictions even with little data and in the case of a changing environment. This inference method generates a task model, providing a graphical representation of n avigation with the usage statistics of the current user. The algorithm learns new tasks while preserving prior knowledge. The theoretical framework is described, and simulations show the effectiveness of the approach in stationary and non - stationary environments. In conclusion, this research paves the way for adaptive systems that improve the user experience by helping them to better navigate and act on their inter face. The reasons given include that it would be too oriented toward machine learning to speak to a community of HCI researchers and not concrete enough, as well as other reasons that we largely dispute. In light of the comments from the two reviewers, it appears that our non - parametric Bayesian approach was not understood, nor the crucial issue of "sequential, continuous and robust learning" for the design of adaptive user interfaces. 2 1 INTRODUCTION Users are all different. Some have no particular constraints but have usage habits and preferences. Others, such as people with disabilities or seniors, may have, in addition to these habits, constraints when using a digital service. These constraints can be very diverse, of a perceptual nature (visual, auditory, tactile), of a motor nature (pointing, manipulation, speech) or cognitive (reasoning, memory, comprehension, reading...). Consequently, any service, any interface should be able to adjust to these constraints.

The Recommender then observes the Agent's selected item

With the rollout of iOS 18 this fall, Apple is introducing some big changes to its iPhones: more customization options for home screens, a redesigned Control Center, support for the RCS text messaging standard, and of course a bunch of generative AI features put under the umbrella of Apple Intelligence. Individual iOS apps are getting upgrades too, including Safari, and one of the new features you'll notice in the web browser once you've got iOS 18 installed is the option to remove "distracting" items from a page. It's called Distraction Control, and the idea is you can cut out pieces of a page you're not necessarily interested in, like images or menus. This isn't the Reader mode that reformats pages so only the main text and images are showing (and which itself is getting an update in iOS 18). It's not an ad blocker either, because you won't be able to persistently hide ads or any other frequently updated content. But it is a potentially useful tool to improve the web browsing experience.

Under fake pink cherry blossom, guests sipped House of Suntory cocktails and picked at plates of chicken karaage, prawn gyoza and cauliflower tempura from a kaitenzushi-style conveyor belt … This was the London launch of Waitrose's new Japanese range. But without knowing it, and even if you live hundreds of miles away, your food choices may have had a hand in shaping the supermarket's 26-dish Japan Menyū range. That is because it was developed with input from Tastewise, an artificial intelligence (AI) platform that analyses menus, social media and online recipes to pinpoint food trends. While many businesses and individuals are concerned that AI is going to eat their lunch rather than set the menu, the technology is becoming more prevalent in the food industry, with its use doubling since 2017, according to McKinsey's 2022 Global Survey on AI. This is probably because it offers under-pressure retailers and food manufacturers an understanding of what fickle shoppers will want to buy in the future. It takes a year to perfect a new food project, but even so most of them miss the mark, and in recent times, companies have instead been forced to play catch-up with trends that have exploded on social media.

Menu system design is a challenging task involving many design options and various human factors. For example, one crucial factor that designers need to consider is the semantic and systematic relation of menu commands. However, capturing these relations can be challenging due to limited available resources. With the advancement of neural language models, large language models can utilize their vast pre-existing knowledge in designing and refining menu systems. In this paper, we propose MenuCraft, an AI-assisted designer for menu design that enables collaboration between the designer and a dialogue system to design menus. MenuCraft offers an interactive language-based menu design tool that simplifies the menu design process and enables easy customization of design options. MenuCraft supports a variety of interactions through dialog that allows performing zero/few-shot learning.

We advance a recently flourishing line of work at the intersection of learning theory and computational economics by studying the learnability of two classes of mechanisms prominent in economics, namely menus of lotteries and two-part tariffs. The former is a family of randomized mechanisms designed for selling multiple items, known to achieve revenue beyond deterministic mechanisms, while the latter is designed for selling multiple units (copies) of a single item with applications in real-world scenarios such as car or bike-sharing services. We focus on learning high-revenue mechanisms of this form from buyer valuation data in both distributional settings, where we have access to buyers' valuation samples up-front, and the more challenging and less-studied online settings, where buyers arrive one-at-a-time and no distributional assumption is made about their values. Our main contribution is proposing the first online learning algorithms for menus of lotteries and two-part tariffs with strong regret-bound guarantees. In the general case, we provide a reduction to a finite number of experts, and in the limited buyer type case, we show a reduction to online linear optimization, which allows us to obtain no-regret guarantees by presenting buyers with menus that correspond to a barycentric spanner. In addition, we provide algorithms with improved running times over prior work for the distributional settings. The key difficulty when deriving learning algorithms for these settings is that the relevant revenue functions have sharp transition boundaries. In stark contrast with the recent literature on learning such unstructured functions, we show that simple discretization-based techniques are sufficient for learning in these settings.

The food industry is one of the biggest industries in the world, and it's constantly growing. Many people are interested in how things are changing in this industry and how they can take advantage of it. The fact that artificial intelligence has been able to enter this industry and make certain processes far more efficient than they were in the past has a lot of people interested in how learning and AI are changing food. According to market research, the global artificial intelligence market in the food and beverage market is growing rapidly, with a CAGR of 45.4% during the forecast period. This market was valued at USD 4.49 billion in 2021 and is expected to continue growing in the coming years. In this article, we'll understand how AI drives the future of food.