Based on this observation, we propose a new training objective that improves thegeneralization ofamortized inference.

In statistics and machine learning, when we train a fitted model on available data, we typically want to ensure that we are searching within a model class that contains at least one accurate model -- that is, we would like to ensure an upper bound on the model class risk (the lowest possible risk that can be attained by any model in the class). However, it is also of interest to establish lower bounds on the model class risk, for instance so that we can determine whether our fitted model is at least approximately optimal within the class, or, so that we can decide whether the model class is unsuitable for the particular task at hand. Particularly in the setting of interpolation learning where machine learning models are trained to reach zero error on the training data, we might ask if, at the very least, a positive lower bound on the model class risk is possible -- or are we unable to detect that "all models are wrong"? In this work, we answer these questions in a distribution-free setting by establishing a model-agnostic, fundamental hardness result for the problem of constructing a lower bound on the best test error achievable over a model class, and examine its implications on specific model classes such as tree-based methods and linear regression.

Agents featured prominently in Google's annual I/O conference in May, when the company unveiled its new AI agent called Astra, which allows users to interact with it using audio and video. OpenAI's new GPT-4o model has also been called an AI agent. And it's not just hype, although there is definitely some of that too. Tech companies are plowing vast sums into creating AI agents, and their research efforts could usher in the kind of useful AI we have been dreaming about for decades. Many experts, including Sam Altman, say they are the next big thing.

In this paper, we focus on the problem of conformal prediction with conditional guarantees. Prior work has shown that it is impossible to construct nontrivial prediction sets with full conditional coverage guarantees. A wealth of research has considered relaxations of full conditional guarantees, relying on some predefined uncertainty structures. Departing from this line of thinking, we propose Partition Learning Conformal Prediction (PLCP), a framework to improve conditional validity of prediction sets through learning uncertainty-guided features from the calibration data. We implement PLCP efficiently with alternating gradient descent, utilizing off-the-shelf machine learning models. We further analyze PLCP theoretically and provide conditional guarantees for infinite and finite sample sizes. Finally, our experimental results over four real-world and synthetic datasets show the superior performance of PLCP compared to state-of-the-art methods in terms of coverage and length in both classification and regression scenarios.

We develop a conformal inference method to construct joint confidence regions for structured groups of missing entries within a sparsely observed matrix. This method is useful to provide reliable uncertainty estimation for group-level collaborative filtering; for example, it can be applied to help suggest a movie for a group of friends to watch together. Unlike standard conformal techniques, which make inferences for one individual at a time, our method achieves stronger group-level guarantees by carefully assembling a structured calibration data set mimicking the patterns expected among the test group of interest. We propose a generalized weighted conformalization framework to deal with the lack of exchangeability arising from such structured calibration, and in this process we introduce several innovations to overcome computational challenges. The practicality and effectiveness of our method are demonstrated through extensive numerical experiments and an analysis of the MovieLens 100K data set.

In 2019, Greta Gerwig became the latest in a line of writers, directors, and producers to make a pilgrimage to a toy workshop in El Segundo, California. Touring the facility, the Mattel Design Center, has become a rite of passage for Hollywood types who are considering transforming one of the company's products into a movie--a list that now includes such names as J. J. Abrams (Hot Wheels) and Vin Diesel (Rock'Em Sock'Em Robots). The building has hundreds of workspaces for artists, model-makers, and project managers, and it houses elaborate museum-style exhibitions that document the company's history and core products. These displays can help a toy designer find inspiration; they can also offer a "brand immersion"--a crash course in a Mattel property slated for adaptation. When a V.I.P. visits, Richard Dickson, a tall, bespectacled man who is the company's chief operating officer, plays the role of Willy Wonka. He'll show off the sixty-five-year-old machines that are still used to affix fake hair to Barbies; he'll invite you to inspect life-size, road-ready replicas of Hot Wheels cars. The center even boasts a giant rendering of Castle Grayskull, the fearsome ancestral home of He-Man.

Since launching on the iPhone X back in 2017, facial recognition has become a staple feature in most smartphones. But while the technology is undeniably handy, it could land you in hot water if you have a smartphone from Honor, Motorola, Nokia, Oppo, Samsung, Vivo, or Xiaomi. Experts from Which? have warned that 19 phones from these popular brands have facial recognition systems that can easily be fooled by 2D photos. Lisa Barber, Tech Editor at Which?, said: 'It's unacceptable that brands are selling phones that can easily be duped using a 2D photo, particularly if they are not making their customers aware of this vulnerability. 'Our findings have really worrying implications for people's security and susceptibility to scams.' Since launching on the iPhone X back in 2017, facial recognition has become a staple feature in most smartphones.

Face shields offer no protection against coronavirus if an infected person nearby sneezes without a mask on, a study shows. Researchers used computer models to visualise the spread of droplets around a face shield ejected by a human sneeze from 3ft (1m) away. It reveals'vortex rings' produced by the sneeze carry infectious particles to the face shield in less than a second and stick to the edges of the plastic. Researchers say if the timing of this wave of coronavirus particles coincides with the face shield wearer breathing in, the person can become infected. Wearing a face mask has a negative impact on our ability to communicate with others, according to a new survey.

Artificial Intelligence has, quite literally, got a big data problem – and one that the COVID-19 crisis has now made impossible to ignore any longer. For businesses, governments, and individuals alike, the global pandemic has effectively redefined "normal" life; but while most of us have now adjusted to the change, the same cannot be said of AI systems, which base their predictions on what the past used to look like. Speaking at the CogX 2020 conference, British mathematician David Barber said: "The deployment of AI systems is currently clunky. Typically, you go out there, collect your data set, label it, train the system and then deploy it. And that's it – you don't revisit the deployed system. But that's not good if the environment is changing."

AI is everywhere, but as I've written before, it won't replace jobs in business development. Instead, it'll simply augment existing human capabilities, allowing us to do more with less, closing more leads, finding more relevant projects, and building more win-win situations for everyone. Perhaps we can even achieve that three-hour workday so famously imagined by economist John Maynard Keynes–but has proven elusive so far. Whether or not we drastically shorten our workweeks, however, one thing is clear. The effective, strategic use of AI promises that overstressed, harried BD professionals will be able to free themselves from the rote tasks of the job, and instead concentrate on doing what AI cannot: building relationships.