This study considers online learning with general directed feedback graphs.

Heavy-tailed bandits have been extensively studied since the seminal work of \citet{Bubeck2012BanditsWH}. In particular, heavy-tailed linear bandits, enabling efficient learning with both a large number of arms and heavy-tailed noises, have recently attracted significant attention \citep{ShaoYKL18,XueWWZ20,ZhongHYW21,Wang2025heavy,tajdini2025improved}. However, prior studies focus almost exclusively on stochastic regimes, with few exceptions limited to the special case of heavy-tailed multi-armed bandits (MABs) \citep{Huang0H22,ChengZ024,Chen2024uniINF}. In this work, we propose a general framework for adversarial heavy-tailed bandit problems, which performs follow-the-regularized-leader (FTRL) over the loss estimates shifted by a bonus function. Via a delicate setup of the bonus function, we devise the first FTRL-type best-of-both-worlds (BOBW) algorithm for heavy-tailed MABs, which does not require the truncated non-negativity assumption and achieves an $\widetilde{O}(T^{\frac{1}{\varepsilon}})$ worst-case regret in the adversarial regime as well as an $\widetilde{O}(\log T)$ gap-dependent regret in the stochastic regime. We then extend our framework to the linear case, proposing the first algorithm for adversarial heavy-tailed linear bandits with finite arm sets. This algorithm achieves an $\widetilde{O}(d^{\frac{1}{2}}T^{\frac{1}{\varepsilon}})$ regret, matching the best-known worst-case regret bound in stochastic regimes. Moreover, we propose a general data-dependent learning rate, termed \textit{heavy-tailed noise aware stability-penalty matching} (HT-SPM). We prove that HT-SPM guarantees BOBW regret bounds for general heavy-tailed bandit problems once certain conditions are satisfied. By using HT-SPM and, in particular, a variance-reduced linear loss estimator, we obtain the first BOBW result for heavy-tailed linear bandits.

The linear bandit problem has been studied for many years in both stochastic and adversarial settings. Designing an algorithm that can optimize the environment without knowing the loss type attracts lots of interest. Lee et al. (2021) propose an algorithm that actively detects the loss type and then switches between different algorithms specially designed for specific settings. However, such an approach requires meticulous designs to perform well in all environments. Follow-theregularized-leader (FTRL) is another type of popular algorithm that can adapt to different environments. This algorithm is of simple design and the regret bounds are shown to be optimal in traditional multi-armed bandit problems compared with the detect-switch type. Designing an FTRL-type algorithm for linear bandits is an important question that has been open for a long time. In this paper, we prove that the FTRL algorithm with a negative entropy regularizer can achieve the best-of-three-world results for the linear bandit problem. Our regret bounds achieve the same or nearly the same order as the previous detect-switch type algorithm but with a much simpler algorithmic design.

Research in artificial intelligence (AI) is addressing a growing number of tasks through a rapidly growing number of models and methodologies. This makes it difficult to keep track of where novel AI methods are successfully -- or still unsuccessfully -- applied, how progress is measured, how different advances might synergize with each other, and how future research should be prioritized. To help address these issues, we created the Intelligence Task Ontology and Knowledge Graph (ITO), a comprehensive, richly structured and manually curated resource on artificial intelligence tasks, benchmark results and performance metrics. The current version of ITO contain 685,560 edges, 1,100 classes representing AI processes and 1,995 properties representing performance metrics. The goal of ITO is to enable precise and network-based analyses of the global landscape of AI tasks and capabilities. ITO is based on technologies that allow for easy integration and enrichment with external data, automated inference and continuous, collaborative expert curation of underlying ontological models. We make the ITO dataset and a collection of Jupyter notebooks utilising ITO openly available.

If Anna Matsumoto had listened to her teachers, she would have kept her inquisitive mind to herself -- asking questions, they told her, interrupted class. And when, at age 15, she had to choose a course of study in her Japanese high school, she would have avoided science, a track that her male teachers said was difficult for girls. Instead, Matsumoto plans to become an engineer. Japan could use a lot more young women like her. Despite its tech-savvy image and economic heft, the country is a digital laggard, with a traditional paperbound office culture where fax machines and personal seals known as hanko remain common.

The last time stocks in Tokyo were this high, things were a little different. Orders now silently processed in milliseconds were shouted across smoky open outcry trading floors. Yuriko Koike, now Tokyo's governor, was a fresh-faced TV presenter on the country's leading business news show. The U.S. fretted over "Japan as number one," while China was an economic backwater. That's how long it's been since the 225-issue Nikkei stock average of the Tokyo Stock Exchange passed 30,000, an event which first took place in December 1988.

The irony of the ethical scandal enveloping Joichi Ito, the former director of the MIT Media Lab, is that he used to lead academic initiatives on ethics. After the revelation of his financial ties to Jeffrey Epstein, the financier charged with sex trafficking underage girls as young as 14, Ito resigned from multiple roles at MIT, a visiting professorship at Harvard Law School, and the boards of the John D. and Catherine T. MacArthur Foundation, the John S. and James L. Knight Foundation, and the New York Times Company. Many spectators are puzzled by Ito's influential role as an ethicist of artificial intelligence. Indeed, his initiatives were crucial in establishing the discourse of "ethical AI" that is now ubiquitous in academia and in the mainstream press. In 2016, then-President Barack Obama described him as an "expert" on AI and ethics. Since 2017, Ito financed many projects through the $27 million Ethics and Governance of AI Fund, an initiative anchored by the MIT Media Lab and the Berkman Klein Center for Internet and Society at Harvard University.

This short week was filled with tough ethical debates at two of the top AI institutions in the United States. A petition and letter of support circulating at MIT is calling Media Lab director Joi Ito courageous for his public apology in the wake of the Epstein sex trafficking scandal and asking Ito to remain in his position following public pressure to resign. Ito took funding for the MIT Media Lab, and startups he backs, from the now-deceased billionaire and accused sex trafficker Jeffrey Epstein, years after Epstein was accused of running an extensive sex trafficking network, accusations that led to a controversial federal plea deal. In response to Ito's admission, MIT Center for Civic Media director Ethan Zuckerman resigned his post, a position he had held since 2012. Shortly after, MIT Media Lab visiting scholar and Cornell University assistant professor J. Nathan Matias also resigned, saying he could no longer in good conscience stay at the school.

When athletes and organizers descend on Tokyo for the 2020 Olympic Games, they'll be ferried around in autonomous cars, while torch relay runners will be accompanied by AI-equipped cars. Robots will ferry javelins and hammers. All told, Toyota Motor Corp. will provide 3,700 vehicles, including dozens of self-driving cars, about 500 fuel-cell vehicles and 850 battery-electric cars to the international sports competition. As a top sponsor of the Tokyo Olympics and an automaker facing a murky future when gasoline-powered engines will fade away, Toyota is doing everything it can to market its transition into an eventual provider of on-demand transportation for consumers and businesses, instead of being merely an industrial manufacturer. "We want to use the Olympics and Paralympics that happen every two years as a milestone," Masaaki Ito, general manager of Toyota's Olympic and Paralympic Division, said in an interview.

Sixty-two years ago this summer, Dartmouth professor John McCarthy coined the term artificial intelligence. Joi Ito, director of MIT's Media Lab, has come to think it's unhelpful. Talk of AI has become hard to avoid due to surging investment from companies hoping to profit from advances in machine learning. Ito believes the term has also become tainted by the assumption that humans and machines must be in opposition--think debates about jobs stolen by robots, or superintelligence threatening humanity. "Instead of thinking about AI as separate or adversarial to humans, it's more helpful and accurate to think about machines augmenting our collective intelligence and society," Ito says.