Economics and social science research often require analyzing datasets of sensitive personal information at fine granularity, with models fit to small subsets of the data. Unfortunately, such fine-grained analysis can easily reveal sensitive individual information. We study algorithms for simple linear regression that satisfy differential privacy, a constraint which guarantees that an algorithm's output reveals little about any individual input data record, even to an attacker with arbitrary side information about the dataset. We consider the design of differentially private algorithms for simple linear regression for small datasets, with tens to hundreds of datapoints, which is a particularly challenging regime for differential privacy. Focusing on a particular application to small-area analysis in economics research, we study the performance of a spectrum of algorithms we adapt to the setting. We identify key factors that affect their performance, showing through a range of experiments that algorithms based on robust estimators (in particular, the Theil-Sen estimator) perform well on the smallest datasets, but that other more standard algorithms do better as the dataset size increases.

A recent line of work has shown a qualitative equivalence between differentially private PAC learning and online learning: A concept class is privately learnable if and only if it is online learnable with a finite mistake bound. However, both directions of this equivalence incur significant losses in both sample and computational efficiency. Studying a special case of this connection, Gonen, Hazan, and Moran (NeurIPS 2019) showed that uniform or highly sample-efficient pure-private learners can be time-efficiently compiled into online learners. We show that, assuming the existence of one-way functions, such an efficient conversion is impossible even for general pure-private learners with polynomial sample complexity. This resolves a question of Neel, Roth, and Wu (FOCS 2019).

We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For any MDP with $S$ states, $A$ actions, $\Gamma \leq S$ next states and diameter $D$, the regret of UCRL2B is bounded as $\widetilde{O}(\sqrt{D\Gamma S A T})$.

The amount of real-time communication between agents in an information system has increased rapidly since the beginning of the decade. This is because the use of these systems, e. g. social media, has become commonplace in today's society. This requires analytical algorithms to learn and predict this stream of information in real-time. The nature of these systems is non-static and can be explained, among other things, by the fast pace of trends. This creates an environment in which algorithms must recognize changes and adapt. Recent work shows vital research in the field, but mainly lack stable performance during model adaptation. In this work, a concept drift detection strategy followed by a prototype-based adaptation strategy is proposed. Validated through experimental results on a variety of typical non-static data, our solution provides stable and quick adjustments in times of change.

We've got the roads, the rail and the airport to keep growing this nation, keep getting those products out of the warehouses and into people's shops and into people's homes," he said. Amazon's new hub is a "boost for this community," said NSW Premier Gladys Berejiklian. "People won't need to travel those longer distances to get the best jobs available. They'll be able to live and work near their communities, which is exactly what we want," Berejiklian said. Other retailers in Australia are gearing up for an increase in automation in their own logistics.

We are encouraging questions from readers about electric vehicles, and charging, and whatever else you want to learn. So please send them through and we will get our experts to respond, and invite other people to contribute through the comments section. Hi Bryce –To future proof an EV purchase, which models available in Australia have an autonomous mode that can be switched on when the law of the land allows it to happen? Hi John – you ask an interesting question, although I think I'll reframe it slightly to ask'what is autonomous driving, and is it safe?' At the end of that explanation, I am hoping you will be able to answer your own question without my help!

Australia and the UK have opened a joint investigation into Clearview AI. Specifically, the regulatory bodies are concerned with Clearview's practice of using "scraped" data and biometrics. The two countries aren't the first to question Clearview AI, the company behind the controversial facial recognition program. Clearview AI claims to have a database with three billion images gathered from the open web. It offers that database to law enforcement, supposedly so they can identify criminals and victims.

The UK's Information Commissioner's Office and the Australian Information Commissioner have announced a joint investigation into Clearview AI. The data watchdogs will focus "on the company's use of'scraped' data and biometrics of individuals" they said in a statement. The investigation follows a similar announcement by the Office of the Privacy Commissioner of Canada, which also has opened an investigation into Clearview AI. "The joint investigation was initiated in the wake of media reports which stated that Clearview AI was using its technology to collect images and make facial recognition available to law enforcement in the context of investigations" the Canadian statement says. "Reports have also indicated the US-based company provides services in a number of countries to a broad range of organizations, including retailers, financial institutions and various government institutions." The company had advised the privacy protection authorities that, in response to their investigation, it would be withdrawing its services from Canada.

Clearview's facial recognition software, popular with law enforcement, uses images scraped from the internet and social media Data regulators in the UK and Australia have announced a joint investigation into practices of facial recognition app Clearview AI. The UK Information Commissioner's Office (ICO) and the Office of the Australian Information Commissioner (OAIC) said they are looking into the firm's use of data "scraped" from the internet. Clearview AI uses its facial recognition software to help law enforcement match photos of unknown people to other images online by using the company's database of photos which have been taken from publicly accessible social media platforms, including Facebook, and other websites. The controversial system has raised questions about privacy and consent to data gathering but has been used by a number of law enforcement agencies in the US. A report by Buzzfeed earlier this year also claimed that a number of UK law enforcement agencies had registered with Clearview, including the Metropolitan Police and the National Crime Agency as well as other regional police forces.

Paris – Native Americans and Polynesians bridged vast expanses of open ocean around the year 1200 and mingled, leaving incontrovertible proof of their encounter in the DNA of present-day populations, scientists revealed Wednesday. Whether peoples from what is today Colombia or Ecuador drifted thousands of kilometers to tiny islands in the middle of the Pacific, or whether seafaring Polynesians sailed upwind to South America and then back again is still unknown. But what is certain, according to a study in Nature, is that the hook up took place hundreds of years before Europeans set foot in either region, and left individuals scattered across French Polynesia with signature traces of the New World in their DNA. "These findings change our understanding of one of the most unknown chapters in the history of our species' great continental expansions," senior author Andreas Moreno-Estrada, principal investigator at Mexico's National Laboratory of Genomics for biodiversity, said. Archeologists and historians have tussled for decades over whether Oceana islanders and native Americans crossed paths during the Middle Ages, and how, if they did, that contact might have unfolded.