Bayesian persuasion studies how an informed sender should partially disclose information to influence the behavior of a self-interested receiver. Classical models make the stringent assumption that the sender knows the receiver's utility. This can be relaxed by considering an online learning framework in which the sender repeatedly faces a receiver of an unknown, adversarially selected type. We study, for the first time, an online Bayesian persuasion setting with multiple receivers. We focus on the case with no externalities and binary actions, as customary in offline models. Our goal is to design no-regret algorithms for the sender with polynomial per-iteration running time. First, we prove a negative result: for any $0 < \alpha \leq 1$, there is no polynomial-time no-$\alpha$-regret algorithm when the sender's utility function is supermodular or anonymous. Then, we focus on the case of submodular sender's utility functions and we show that, in this case, it is possible to design a polynomial-time no-$(1 - \frac{1}{e})$-regret algorithm. To do so, we introduce a general online gradient descent scheme to handle online learning problems with a finite number of possible loss functions. This requires the existence of an approximate projection oracle. We show that, in our setting, there exists one such projection oracle which can be implemented in polynomial time.

We study the problem of sparse tensor principal component analysis: given a tensor $\pmb Y = \pmb W + \lambda x^{\otimes p}$ with $\pmb W \in \otimes^p\mathbb{R}^n$ having i.i.d. Gaussian entries, the goal is to recover the $k$-sparse unit vector $x \in \mathbb{R}^n$. The model captures both sparse PCA (in its Wigner form) and tensor PCA. For the highly sparse regime of $k \leq \sqrt{n}$, we present a family of algorithms that smoothly interpolates between a simple polynomial-time algorithm and the exponential-time exhaustive search algorithm. For any $1 \leq t \leq k$, our algorithms recovers the sparse vector for signal-to-noise ratio $\lambda \geq \tilde{\mathcal{O}} (\sqrt{t} \cdot (k/t)^{p/2})$ in time $\tilde{\mathcal{O}}(n^{p+t})$, capturing the state-of-the-art guarantees for the matrix settings (in both the polynomial-time and sub-exponential time regimes). Our results naturally extend to the case of $r$ distinct $k$-sparse signals with disjoint supports, with guarantees that are independent of the number of spikes. Even in the restricted case of sparse PCA, known algorithms only recover the sparse vectors for $\lambda \geq \tilde{\mathcal{O}}(k \cdot r)$ while our algorithms require $\lambda \geq \tilde{\mathcal{O}}(k)$. Finally, by analyzing the low-degree likelihood ratio, we complement these algorithmic results with rigorous evidence illustrating the trade-offs between signal-to-noise ratio and running time. This lower bound captures the known lower bounds for both sparse PCA and tensor PCA. In this general model, we observe a more intricate three-way trade-off between the number of samples $n$, the sparsity $k$, and the tensor power $p$.

The self-driving vehicle industry may be young, just a bit over a decade old, but already a meaningful trend is taking shape: it's proving to be more open to women CEOs and founders–including women of color–than the broader tech industry and for U.S. companies generally. With this week's news that Waabi founder and CEO Raquel Urtasun raised $83.5 million in a Series A round for her Toronto-based startup, three out of 12 leading autonomous technology companies in North America are now led by women. What's more, in a time when companies across all industries are working to improve diversity, two of the women leading self-driving tech companies, Zoox CEO Aicha Evans and Waymo co-CEO Tekedra Mawakana, are Black. "I've been really excited to see the number of women interested in autonomous technology. There's an appreciation for what it can do for people, what it's going to unlock," says Alisyn Malek, who left General Motors to cofound autonomous shuttle startup May Mobility in 2017 (and is currently executive director of the Washington-based Commission on the Future of Mobility).

Health care services in Africa are under-resourced & overused. There are only 20 pediatric radiologists in Africa, where pneumonia is the #1 cause of death in children under 5. Covid-19, tuberculosis and cancer are an increased burden on doctors globally and is another threat to our already fragile healthcare system. Misdiagnosis is common and human error can result in increased medical legal exposure to doctors. RADIFY AI for mammography assists with early detection of breast cancer. Radify AI for ultrasound is a point of care solution for detection of chest & breast diseases.

Tens of thousands of times a year, a technician places a drop of blood on a slide and peers at it under a microscope, searching for malaria parasites. Making a definitive diagnosis requires the technician to look at up to 300 different fields of view over roughly half an hour. This process is repeated over and over, day after day, on every continent except Antarctica. It's tedious work, but it saves lives. Malaria parasites infect over 200 million people and kill 400,000 every year, mostly children in Africa. Trained and experienced malaria microscopists are rare, however.

As AI systems are integrated into high stakes social domains, researchers now examine how to design and operate them in a safe and ethical manner. However, the criteria for identifying and diagnosing safety risks in complex social contexts remain unclear and contested. In this paper, we examine the vagueness in debates about the safety and ethical behavior of AI systems. We show how this vagueness cannot be resolved through mathematical formalism alone, instead requiring deliberation about the politics of development as well as the context of deployment. Drawing from a new sociotechnical lexicon, we redefine vagueness in terms of distinct design challenges at key stages in AI system development. The resulting framework of Hard Choices in Artificial Intelligence (HCAI) empowers developers by 1) identifying points of overlap between design decisions and major sociotechnical challenges; 2) motivating the creation of stakeholder feedback channels so that safety issues can be exhaustively addressed. As such, HCAI contributes to a timely debate about the status of AI development in democratic societies, arguing that deliberation should be the goal of AI Safety, not just the procedure by which it is ensured.

Recovery of support of a sparse vector from simple measurements is a widely studied problem, considered under the frameworks of compressed sensing, 1-bit compressed sensing, and more general single index models. We consider generalizations of this problem: mixtures of linear regressions, and mixtures of linear classifiers, where the goal is to recover supports of multiple sparse vectors using only a small number of possibly noisy linear, and 1-bit measurements respectively. The key challenge is that the measurements from different vectors are randomly mixed. Both of these problems were also extensively studied recently. In mixtures of linear classifiers, the observations correspond to the side of queried hyperplane a random unknown vector lies in, whereas in mixtures of linear regressions we observe the projection of a random unknown vector on the queried hyperplane. The primary step in recovering the unknown vectors from the mixture is to first identify the support of all the individual component vectors. In this work, we study the number of measurements sufficient for recovering the supports of all the component vectors in a mixture in both these models. We provide algorithms that use a number of measurements polynomial in $k, \log n$ and quasi-polynomial in $\ell$, to recover the support of all the $\ell$ unknown vectors in the mixture with high probability when each individual component is a $k$-sparse $n$-dimensional vector.

The EU is facing a backlash over new AI rules that allow for limited use of facial recognition by authorities -- with opponents warning the carveouts could usher in a new age of biometric surveillance. A coalition of digital rights and consumer protection groups across the globe, including Latin America, Africa and Asia are calling for a global ban on biometric recognition technologies that enable mass and discriminatory surveillance by both governments and corporations. In an open letter, 170 signatories in 55 countries argue that the use of technologies like facial recognition in public places goes against human rights and civil liberties. "It shows that organizations, groups, people, activists, technologists around the world who are concerned with human rights, agree to this call," said Daniel Leufer of U.S. digital rights group Access Now, which co-authored the letter. The use of facial recognition technology is becoming widespread.

AI drone may have'hunted down' and killed soldiers in Libya without human input By Charles Q. Choi - Live Science Contributor - June 3, 2021 KARGU a Rotary Wing Attack Drone Loitering Munition System A UN report suggests that at least one autonomous drone operated by artificial intelligence (AI) may have killed people for the first time last year in Libya, without any humans consulted prior to the attack, according to a U.N. report. According to a March report from the U.N. Panel of Experts on Libya, lethal autonomous aircraft may have "hunted down and remotely engaged" soldiers and convoys fighting for Libyan general Khalifa Haftar. It's not clear who exactly deployed these killer robots, though remnants of one such machine found in Libya came from the Kargu-2 drone, which is made by Turkish military contractor STM. Landmines are essentially simple autonomous weapons -- you step on them and they blow up," Zachary Kallenborn, a research affiliate with the National Consortium for the ...

Despite their popularity with kids, tablets and other connected devices are built on top of systems that weren't designed for them to easily understand or navigate. But adapting algorithms to interact with a child isn't without its complications--as no one child is exactly like another. Most recognition algorithms look for patterns and consistency to successfully identify objects. But kids are notoriously inconsistent. In this episode, we examine the relationship AI has with kids. This episode was reported and produced by Jennifer Strong, Anthony Green and Tanya Basu with Emma Cillekens. Jennifer: It wasn't long ago that playing hopscotch, board games or hosting tea parties with dolls was the norm for kids.... But... we've seen hopscotch turn to TicToc... board games become video games... and dolls at tea parties... do more than just talk back This is my digital makeover.. I insert my own Ipad and open my app .. and the mirror lights up..