Europe seen to be falling behind in future technologies President Emmanuel Macron is rolling out France's strategy to close an artificial-intelligence gap with the U.S. and China, saying it'll require Europeans to get more comfortable with sharing data. After a buildup that includes naming one of the world's top mathematicians as his point man, Macron is expected to propose higher government funding for research and updated rules on data use in his speech Thursday at a former 13th-century Cistercian college in Paris. He also plans to tout incentives for scientists and companies to move to France. "With the digital revolution, we must be at the side of French industrial companies in the disruptive dynamic of innovation," Macron told French business executives this week. European powers risk falling behind in the global competition for future technologies as Google, Apple, Facebook and China's AI companies plow ahead.

Brian Villani, 26, tall and in khakis, extroverted, both opinionated and earnest, shares a garden-level apartment with two roommates in greater Boston that's outfitted with the material culture of young adulthood: big overstuffed couch, multiple gaming systems, oversize posters, a clutter of plastic kitchenware. He commutes by train to a job he's held for years at a corporate mail room downtown, a job he loves--"I pick up all the packages, and all my vendors know me," he says. He lives close--"but not too close," he says wryly--to his parents and has an abiding passion for sports, especially the art of play-by-play announcing. He is counting down the days to his brother's wedding. Villani moves through life, home to work and back again, with an extended set of technologies that are a mix of the familiar and distinctive.

Actor-critic (AC) algorithms, empowered by neural networks, have had significant empirical success in recent years. However, most of the existing theoretical support for AC algorithms focuses on the case of linear function approximations, or linearized neural networks, where the feature representation is fixed throughout training. Such a limitation fails to capture the key aspect of representation learning in neural AC, which is pivotal in practical problems. In this work, we take a mean-field perspective on the evolution and convergence of feature-based neural AC. Specifically, we consider a version of AC where the actor and critic are represented by overparameterized two-layer neural networks and are updated with two-timescale learning rates. The critic is updated by temporal-difference (TD) learning with a larger stepsize while the actor is updated via proximal policy optimization (PPO) with a smaller stepsize. In the continuous-time and infinite-width limiting regime, when the timescales are properly separated, we prove that neural AC finds the globally optimal policy at a sublinear rate. Additionally, we prove that the feature representation induced by the critic network is allowed to evolve within a neighborhood of the initial one.

O PTIMAL T RANSPORT, C YCLEGAN, AND P ENALIZED LS FOR U NSUPERVISEDL EARNING IN I NVERSE P ROB-LEMS Byeongsu Sim 1 Gyutaek Oh 2 Sungjun Lim 2 Jong Chul Y e 1,2 1 Department of Mathematical Sciences, KAIST, Daejeon, Republic of Korea 2 Department of Bio and Brain Engineering, KAIST, Daejeon, Republic of Korea A BSTRACT The penalized least squares (PLS) is a classic approach to inverse problems, where a regularization term is added to stabilize the solution. Optimal transport (OT) is another mathematical framework for computer vision tasks by providing means to transport one measure to another at minimal cost. Cycle-consistent generative adversarial network (cycleGAN) is a recent extension of GAN to learn target distributions with less mode collapsing behavior. Although similar in that no supervised training is required, the algorithms look different, so the mathematical relationship between these approaches is not clear. In this article, we provide an important advance to unveil the missing link. Specifically, we reveal that a cycle-GAN architecture can be derived as a dual formulation of the optimal transport problem, if the PLS with a deep learning penalty is used as a transport cost between the two probability measures from measurements and unknown images. This suggests that cycleGAN can be considered as stochastic generalization of classical PLS approaches. Our derivation is so general that various types of cy-cleGAN architecture can be easily derived by merely changing the transport cost.

From the shiny corridors of BlackRock's Palo Alto laboratory, to the cramped shared workspaces of scientifically minded hedge fund start-ups, to the hallways of quantitative investing stalwarts such as Renaissance Technologies and Two Sigma, artificial intelligence (AI) is being adopted as the new temple of asset management. Even discretionary managers are starting to bring in data scientists and machine learning experts. Most attempts to apply AI so far have been in stock price forecasting. But risk managers are asking how the technology can be harnessed in their domain also. One area of exploration is the use of machine learning to replace traditional approaches to risk modelling.

This paper provides a simple procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs). The approach is based on two principles: (a) if the source randomness of the network is a continuous distribution (the "semi-discrete" setting), then the Wasserstein distance is realized by a deterministic optimal transport mapping; (b) given an optimal transport mapping between a generator network and a target distribution, the Wasserstein distance may be decreased via a regression between the generated data and the mapped target points. The procedure here therefore alternates these two steps, forming an optimal transport and regressing against it, gradually adjusting the generator network towards the target distribution. Mathematically, this approach is shown to minimize the Wasserstein distance to both the empirical target distribution, and also its underlying population counterpart. Empirically, good performance is demonstrated on the training and testing sets of the MNIST and Thin-8 data. The paper closes with a discussion of the unsuitability of the Wasserstein distance for certain tasks, as has been identified in prior work [Arora et al., 2017, Huang et al., 2017].

Antoine Bruel, head of growth at Braincities and Céline Pluijm, key account manager at Wiidii share their thoughts on why France is fast-becoming a leader in establishing'AI for humanity', fresh from Hello Tomorrow… Artificial Intelligence (AI) is everywhere. Across industry verticals, it's being used to enable businesses and organisations to work smarter and faster than ever before. From automating repetitive transactions and manual tasks to powering customer support platforms, AI is transforming the way we work, live and interact with the world. According to PwC research, AI is estimated to provide $15.7 trillion in economic growth by 2030, creating opportunities for innovation on a global scale. AI, however, is as much a source of fascination as it is a cause for concern.

In his office in Paris's National Assembly, Cédric Villani opens a parcel: it contains a metallic spider. "Lovely," he says, putting it on a shelf, where a collection of spider-shaped objects sits next to his scientific decorations and a photo of him with Mark Zuckerberg. Villani is on a mission. Well, on several missions: the French mathematician, winner of the 2010 Fields Medal – often described as maths' Nobel Prize – sits as an MP for Emmanuel Macron's party La République en Marche, teaches at the University of Lyon, and is running for the Paris 2020 mayoralty. But the expert in mathematical analysis, famous for his academic achievements as well as for wearing spider-shaped pins on his three-piece suits, has a bigger goal: making France a leader in artificial intelligence. Appointed by the French president to set out a national AI strategy, in 2018 Villani published a report, "AI for Humanity", setting clear lines for the sector: "We must valorise our research, define our industrial priorities, work on the ethical and legal framework and on AI training," Villani says, sat among his spiders – one as big a pillow – in his office.

PARIS (Reuters) - French President Emmanuel Macron promised 1.5 billion euros ($1.85 billion) of public funding into artificial intelligence by 2022 in a bid to reverse a brain drain and catch up with the dominant U.S. and Chinese tech giants. The investment is part of an AI strategy laid out by the centrist leader at the elite College de France research institute in Paris and builds on a report that points to the assets and drawbacks of France in the field. Business-friendly Macron wants to turn France into a "start up nation" and bets that easing labor laws and higher investments technology will create jobs, alleviate the domination of Alphabet's Google, Facebook and lay out the seeds for Europe-based champions. "There's no chance of controlling any effects (of these technologies) or having a say on any adverse effect if we've missed the start of the war," the president said on Thursday in front of a row of ministers and top executives, including BNP Paribas Jean-Laurent Bonnafé. He spoke between two black boards covered with complex equations in the main amphitheatre of the institute, founded in the 16th century.

The investment is part of an AI strategy laid out by President Emmanuel Macron at the elite College de France research institute in Paris, the French presidency said. The goal is to make better use of the French higher education system that trains computer engineers and mathematicians only to see them leave for jobs at top U.S. tech companies. Some of them have secured high-level positions at Alphabet, the parent company of search engine Google, and Facebook, which opened an AI research centre in Paris in 2015. Macron's AI plan was inspired by a government-commissioned report by Cedric Villani, the self-styled "Lady Gaga of Mathematics" and winner of the mathematics equivalent of the Nobel Prize. Villani, who is also a lawmaker in Macron's party, said in the report the brain drain to Silicon Valley companies showed the excellence of French schools.