Various theoretical results provideupper bounds onthedistance between the target and marginal distribution after a fixed number of iterations.

Although it is, at least according to the Library of Congress, the most-watched movie of all time, The Wizard of Oz was a costly failure at the box office, and only became a perennial favorite thanks to the regular TV airings that began in the 1950s. But in the decades since it's become a metonym for the wonder of the big screen, a movie even people who prefer their content streaming will make the effort to see in a movie theater. Beginning on Labor Day weekend, audiences will get to experience the movie on perhaps the largest screen ever created. But it won't be The Wizard of Oz as we've come to know it for the better part of a century. The version of the movie that will fill Las Vegas' Sphere starting Aug. 28 has been retooled to fit the venue's curved shell, its images enhanced and expanded to fill four football fields' worth of 16K LED screens--the foundation of an immersive presentation that also includes flames, gusts of wind, and inflatable flying monkeys piloted by drone. It is, to quote the title of a CBS news report, "The Wizard of Oz as you've never seen it before."

This paper introduces an LLM-based Latin-to-English translation platform designed to address the challenges of translating Latin texts. We named the model LITERA, which stands for Latin Interpretation and Translations into English for Research Assistance. Through a multi-layered translation process utilizing a fine-tuned version of GPT-4o-mini and GPT-4o, LITERA offers an unprecedented level of accuracy, showcased by greatly improved BLEU scores, particularly in classical Latin, along with improved BLEURT scores. The development of LITERA involved close collaboration with Duke University's Classical Studies Department, which was instrumental in creating a small, high-quality parallel Latin-English dataset. This paper details the architecture, fine-tuning methodology, and prompting strategies used in LITERA, emphasizing its ability to produce literal translations.

A vast literature on algorithms, tips, and tricks is testament to the success of Markov chain Monte Carlo (MCMC), which remains the most popular approach to numerical approximation of probability distributions characterised up to an intractable normalisation constant. Yet the breadth of methodology also presents a difficulty in selecting an appropriate algorithm for a specific task. The goal of adaptive MCMC is to automate, as much as possible, the design of a fast-mixing Markov transition kernel. To achieve this, one alternates between observing the performance of the current transition kernel, and updating the transition kernel in a manner that is expected to improve its future performance (Andrieu and Thoms, 2008). Though the online adaptation of a Markov transition kernel in principle sacrifices the ergodicy of MCMC, there are several ways to prove that ergodicity is in fact retained if the transition kernel converges fast enough (in an appropriate sense) to a sensible limit.

Variational Inference (VI) is an attractive alternative to Markov Chain Monte Carlo (MCMC) due to its computational efficiency in the case of large datasets and/or complex models with high-dimensional parameters. However, evaluating the accuracy of variational approximations remains a challenge. Existing methods characterize the quality of the whole variational distribution, which is almost always poor in realistic applications, even if specific posterior functionals such as the component-wise means or variances are accurate. Hence, these diagnostics are of practical value only in limited circumstances. To address this issue, we propose the TArgeted Diagnostic for Distribution Approximation Accuracy (TADDAA), which uses many short parallel MCMC chains to obtain lower bounds on the error of each posterior functional of interest. We also develop a reliability check for TADDAA to determine when the lower bounds should not be trusted. Numerical experiments validate the practical utility and computational efficiency of our approach on a range of synthetic distributions and real-data examples, including sparse logistic regression and Bayesian neural network models.

Researchers in Carnegie Mellon University's School of Computer Science are studying how humans organize their days and how they react to changes in their schedules to help build better artificial intelligence tools. Students have teamed up with Stephanie Rosenthal, an assistant teaching professor in the Computer Science Department, to work on the project through Summer Undergraduate Research Fellowship grants. This past summer, Elchanan Haas, a junior studying computer science, built on previous work to create problem-solving strategies that mimic and ultimately improve on human decision-making. "This could someday be adapted in a number of ways," Haas said. "Delivery companies are using algorithms to schedule their car fleets, but this complex mixture -- pickups, deliveries, appointments, tasks -- there's nothing on the robotics market today able to consider and efficiently schedule all of those activities at the same time."

Recent advances in artificial intelligence (AI) have achieved human-scale speed and accuracy for classification tasks. In turn, these capabilities have made AI a viable replacement for many human activities that at their core involve classification, such as basic mechanical and analytical tasks in low-level service jobs. Current systems do not need to be conscious to recognize patterns and classify them. However, for AI to progress to more complicated tasks requiring intuition and empathy, it must develop capabilities such as metathinking, creativity, and empathy akin to human self-awareness or consciousness. We contend that such a paradigm shift is possible only through a fundamental shift in the state of artificial intelligence toward consciousness, a shift similar to what took place for humans through the process of natural selection and evolution. As such, this paper aims to theoretically explore the requirements for the emergence of consciousness in AI. It also provides a principled understanding of how conscious AI can be detected and how it might be manifested in contrast to the dominant paradigm that seeks to ultimately create machines that are linguistically indistinguishable from humans.

That's powered by AI too. Even your email spam filter uses AI, though it's clear sometimes important information winds up in your spam folder for no discernible reason. The real promise of AI for those with pancreatic cancer lies in its astounding ability to digest and parse huge amounts of data and identify patterns that can elude even the most skilled physicians. Taken together, these AI attributes could potentially pave the way for earlier detection for a disease that is often diagnosed too late for potentially curative surgery. However, finding ways to tap into the full potential of AI requires skill sets spanning medicine, computer science, engineering, mathematics, industry, government, and more.

We revisit the problem of \emph{missing mass concentration}, developing a new method of estimating concentration of heterogenic sums, in spirit of celebrated Rosenthal's inequality. As a result we slightly improve the state-of-art bounds due to Ben-Hamou at al., and simplify the proofs.

The Markov Chain Monte Carlo (MCMC) methods are popular when considering sampling from a high-dimensional random variable $\mathbf{x}$ with possibly unnormalised probability density $p$ and observed data $\mathbf{d}$. However, MCMC requires evaluating the posterior distribution $p(\mathbf{x}|\mathbf{d})$ of the proposed candidate $\mathbf{x}$ at each iteration when constructing the acceptance rate. This is costly when such evaluations are intractable. In this paper, we introduce a new non-Markovian sampling algorithm called Moving Target Monte Carlo (MTMC). The acceptance rate at $n$-th iteration is constructed using an iteratively updated approximation of the posterior distribution $a_n(\mathbf{x})$ instead of $p(\mathbf{x}|\mathbf{d})$. The true value of the posterior $p(\mathbf{x}|\mathbf{d})$ is only calculated if the candidate $\mathbf{x}$ is accepted. The approximation $a_n$ utilises these evaluations and converges to $p$ as $n \rightarrow \infty$. A proof of convergence and estimation of convergence rate in different situations are given.