Learning aggregate population trends can allow for better data-driven decisions, and application of machine learning can improve user experience. Compared to learning from public curated datasets, learning from a larger population offers several benefits. As an example, a next-word prediction model trained on words typed by users (a) can better fit the actual distribution of language used on devices, (b) can adapt faster to shifts in distribution, and (c) can more faithfully represent smaller sub-populations that may not be well-represented in curated datasets. At the same time, training such models may involve sensitive user data.

Task-space quadratic programming (QP) is an elegant approach for controlling robots subject to constraints. Yet, in the case of kinematic-controlled (i.e., high-gains position or velocity) robots, closed-loop QP control scheme can be prone to instability depending on how the gains related to the tasks or the constraints are chosen. In this paper, we address such instability shortcomings. First, we highlight the non-robustness of the closed-loop system against non-modeled dynamics, such as those relative to joint-dynamics, flexibilities, external perturbations, etc. Then, we propose a robust QP control formulation based on high-level integral feedback terms in the task-space including the constraints. The proposed method is formally proved to ensure closed-loop robust stability and is intended to be applied to any kinematic-controlled robots under practical assumptions. We assess our approach through experiments on a fixed-base robot performing stable fast motions, and a floating-base humanoid robot robustly reacting to perturbations to keep its balance.

Complex interactions between two opposing agents frequently occur in domains of machine learning, game theory, and other application domains. Quantitatively analyzing the strategies involved can provide an objective basis for decision-making. One such critical scenario is shot-taking in football, where decisions, such as whether the attacker should shoot or pass the ball and whether the defender should attempt to block the shot, play a crucial role in the outcome of the game. However, there are currently no effective data-driven and/or theory-based approaches to analyzing such situations. To address this issue, we proposed a novel framework to analyze such scenarios based on game theory, where we estimate the expected payoff with machine learning (ML) models, and additional features for ML models were extracted with a theory-based shot block model. Conventionally, successes or failures (1 or 0) are used as payoffs, while a success shot (goal) is extremely rare in football. Therefore, we proposed the Expected Probability of Shot On Target (xSOT) metric to evaluate players' actions even if the shot results in no goal; this allows for effective differentiation and comparison between different shots and even enables counterfactual shot situation analysis. In our experiments, we have validated the framework by comparing it with baseline and ablated models. Furthermore, we have observed a high correlation between the xSOT and existing metrics. This alignment of information suggests that xSOT provides valuable insights. Lastly, as an illustration, we studied optimal strategies in the World Cup 2022 and analyzed a shot situation in EURO 2020.

In-context learning (ICL) for large language models has proven to be a powerful approach for many natural language processing tasks. However, determining the best method to select examples for ICL is nontrivial as the results can vary greatly depending on the quality, quantity, and order of examples used. In this paper, we conduct a case study on text simplification (TS) to investigate how to select the best and most robust examples for ICL. We propose Metric-Based in-context Learning (MBL) method that utilizes commonly used TS metrics such as SARI, compression ratio, and BERT-Precision for selection. Through an extensive set of experiments with various-sized GPT models on standard TS benchmarks such as TurkCorpus and ASSET, we show that examples selected by the top SARI scores perform the best on larger models such as GPT-175B, while the compression ratio generally performs better on smaller models such as GPT-13B and GPT-6.7B. Furthermore, we demonstrate that MBL is generally robust to example orderings and out-of-domain test sets, and outperforms strong baselines and state-of-the-art finetuned language models. Finally, we show that the behaviour of large GPT models can be implicitly controlled by the chosen metric. Our research provides a new framework for selecting examples in ICL, and demonstrates its effectiveness in text simplification tasks, breaking new ground for more accurate and efficient NLG systems.

Neural network (NN) potentials promise highly accurate molecular dynamics (MD) simulations within the computational complexity of classical MD force fields. However, when applied outside their training domain, NN potential predictions can be inaccurate, increasing the need for Uncertainty Quantification (UQ). Bayesian modeling provides the mathematical framework for UQ, but classical Bayesian methods based on Markov chain Monte Carlo (MCMC) are computationally intractable for NN potentials. By training graph NN potentials for coarse-grained systems of liquid water and alanine dipeptide, we demonstrate here that scalable Bayesian UQ via stochastic gradient MCMC (SG-MCMC) yields reliable uncertainty estimates for MD observables. We show that cold posteriors can reduce the required training data size and that for reliable UQ, multiple Markov chains are needed. Additionally, we find that SG-MCMC and the Deep Ensemble method achieve comparable results, despite shorter training and less hyperparameter tuning of the latter. We show that both methods can capture aleatoric and epistemic uncertainty reliably, but not systematic uncertainty, which needs to be minimized by adequate modeling to obtain accurate credible intervals for MD observables. Our results represent a step towards accurate UQ that is of vital importance for trustworthy NN potential-based MD simulations required for decision-making in practice.

Traditional machine learning paradigms are based on the assumption that both training and test data follow the same statistical pattern, which is mathematically referred to as Independent and Identically Distributed ($i.i.d.$). However, in real-world applications, this $i.i.d.$ assumption often fails to hold due to unforeseen distributional shifts, leading to considerable degradation in model performance upon deployment. This observed discrepancy indicates the significance of investigating the Out-of-Distribution (OOD) generalization problem. OOD generalization is an emerging topic of machine learning research that focuses on complex scenarios wherein the distributions of the test data differ from those of the training data. This paper represents the first comprehensive, systematic review of OOD generalization, encompassing a spectrum of aspects from problem definition, methodological development, and evaluation procedures, to the implications and future directions of the field. Our discussion begins with a precise, formal characterization of the OOD generalization problem. Following that, we categorize existing methodologies into three segments: unsupervised representation learning, supervised model learning, and optimization, according to their positions within the overarching learning process. We provide an in-depth discussion on representative methodologies for each category, further elucidating the theoretical links between them. Subsequently, we outline the prevailing benchmark datasets employed in OOD generalization studies. To conclude, we overview the existing body of work in this domain and suggest potential avenues for future research on OOD generalization. A summary of the OOD generalization methodologies surveyed in this paper can be accessed at http://out-of-distribution-generalization.com.

On weekdays, between homeschooling her two children, Michelle Curtis logs on to her computer to squeeze in a few hours of work. Her screen flashes with Google Search results, the writings of a Google chatbot, and the outputs of other algorithms, and she has a few minutes to respond to each--judging the usefulness of the blue links she's been provided, checking the accuracy of an AI's description of a praying mantis, or deciding which of two chatbot-written birthday poems is better. She never knows what she will have to assess in advance, and for the AI-related tasks, which have formed the bulk of her work since February, she says she has little guidance and not enough time to do a thorough job. Curtis is an AI rater. She works for the data company Appen, which is subcontracted by Google to evaluate the outputs of the tech giant's AI products and search algorithm.

That may have been science fiction but scientists say the terrifying prophecy could soon become a reality. That's because new research warns that the Atlantic Ocean current which drives the Gulf Stream could collapse at'any time' from 2025 thanks to climate change. Known formally as the Atlantic Meridional Overturning Circulation (AMOC), the current is the driving force which brings warm water from the Gulf of Mexico up to the UK and is responsible for mild winters in Western Europe. If it collapsed, however, the impact would be devastating. Europe would be plunged into a deep freeze, while most of Africa, the Caribbean, and South American countries such as Colombia, Peru and Bolivia would experience rocketing temperatures.

Cuckoos infiltrate the nests of other birds with similar-looking eggs, but drongos have evolved a highly effective way to snuff out the imposters. Their ability to recognise the uniquely patterned marks of their own eggs, like a signature, means they may reject up to 94 per cent of cuckoo eggs. Instead of caring for their own offspring, African cuckoos (Cuculus gularis) lay a single egg in the nests of fork-tailed drongos (Dicrurus adsimilis), tossing out a drongo egg to match the original clutch count. If the young cuckoo is adopted and hatches, it immediately pushes out the remaining drongo eggs to become its hosts' only charge. Jess Lund at the University of Cape Town, South Africa, and her colleagues gathered 192 eggs – including 26 that had been laid by cuckoos – from fork-tailed drongo nests in the forests of southern Zambia.

OpenAI's ChatGPT language model has gained popularity as a powerful tool for complex problem-solving and information retrieval. However, concerns arise about the reproduction of biases present in the language-specific training data. In this study, we address this issue in the context of the Israeli-Palestinian and Turkish-Kurdish conflicts. Using GPT-3.5, we employed an automated query procedure to inquire about casualties in specific airstrikes, in both Hebrew and Arabic for the former conflict and Turkish and Kurdish for the latter. Our analysis reveals that GPT-3.5 provides 27$\pm$11 percent lower fatality estimates when queried in the language of the attacker than in the language of the targeted group. Evasive answers denying the existence of such attacks further increase the discrepancy, creating a novel bias mechanism not present in regular search engines. This language bias has the potential to amplify existing media biases and contribute to information bubbles, ultimately reinforcing conflicts.