Conformal prediction (CP) quantifies the uncertainty of machine learning models by constructing sets of plausible outputs. These sets are constructed by leveraging a so-called conformity score, a quantity computed using the input point of interest, a prediction model, and past observations. CP sets are then obtained by evaluating the conformity score of all possible outputs, and selecting them according to the rank of their scores. Due to this ranking step, most CP approaches rely on a score functions that are univariate. The challenge in extending these scores to multivariate spaces lies in the fact that no canonical order for vectors exists. To address this, we leverage a natural extension of multivariate score ranking based on optimal transport (OT). Our method, OTCP, offers a principled framework for constructing conformal prediction sets in multidimensional settings, preserving distribution-free coverage guarantees with finite data samples. We demonstrate tangible gains in a benchmark dataset of multivariate regression problems and address computational \& statistical trade-offs that arise when estimating conformity scores through OT maps.

Intel is expected to report a sharp drop in quarterly earnings, hurt by a rapidly shrinking market for personal computers that its chips go into. The company after the closing bell Thursday is projected to post sales of about $15 billion during the quarter ended in September, a retreat of more than 21% from the year-earlier period, according to a FactSet survey of analysts. Net income likely fell by around 93% to $494 million, the analysts estimate. Intel and other chip makers cashed in on a boom in computer and electronics sales at the outset of the pandemic with the shift toward remote work and distance learning. The market has turned, though, with high inflation, rising interest rates and recession fears that have weighed on demand.

China's biggest-listed companies Tencent and Alibaba are expected to report a fall in profits and slowing revenue growth in the July-September quarter, hurt by the year-long regulatory crackdown that has upended its technology industry. Beijing has reasserted control over its once-freewheeling internet sector, punishing well-known names for engaging in what were previously considered regular market practices and drafting new rules to change how they compete and engage users. "We believe the financial impact of regulatory headwinds in China will be reflected in (third quarter) earnings and (fourth quarter) guidance," KGI Asia analysts said in a note last month. Tencent Holdings Ltd – the country's largest firm by market value and its first Big Tech name to report earnings on Wednesday – is expected to post a 12 percent fall in quarterly profit, its first drop in two years, according to Refinitiv data. The gaming giant's revenue is expected to rise 16.4 percent, the slowest pace since the first quarter of 2019, after the government imposed new limits on the amount of time minors can spend playing video games.

The covid-19 pandemic has caused a slump in the sale of electronic devices and a resulting fall in electronic waste, UN researchers have found. This may offer governments an opportunity to improve e-waste recycling, but the decline in sales has mostly affected poorer countries, which could widen the digital divide. In 2019, the global population created 53.6 million tonnes of e-waste – discarded electronics that contain toxic substances such as brominated flame retardants, lead and mercury. East and South-East Asia accounted for over 22 million tonnes of this waste, while Europe and North America generated slightly less than 20 million tonnes. Despite an increase in sales of devices like laptops and games consoles driven by home working and demand for entertainment during isolation and quarantine, the sale of electronic equipment worldwide decreased by 6.4 per cent in the first nine months of 2020 compared with sales estimates based on previous years.

November's got quite a few releases though, so there are a handful of launch trailers below for Hitman 2 and Battlefield V, plus a release date for Tannenberg, more monsters for Assassin's Creed: Odyssey, and an obituary for strategy guide printer Prima Games. This is gaming news for November 5 to 9. I already sunk 60-plus hours into Assassin's Creed: Odyssey so the prospect of going back for more is...daunting. If you're looking to extend your stay in Ancient Greece however, Ubisoft's adding a bunch of stuff to the game in November--new questlines, a new mythological creature, more items, and a level cap bump. Check out the video below for more details. Sunset Overdrive's all-but-confirmed for a PC release at this point, but in case you needed further confirmation: PC Gamer spotted this listing on SteamDB that quite clearly features Sunset Overdrive key art, despite no other details.

Sales of industrial robots in China, the world's biggest market, will grow this year at only about a third the pace seen last year as an escalating Sino-U.S. trade war hits spending on equipment, a global robot group said on Thursday. In its annual report, the International Federation of Robotics (IFR) forecast Chinese demand for robots will grow 15-20 percent this year after surging 59 percent to 137,920 units last year. With China accounting for 36 percent of the global robot market and with its sales volume exceeding the total of Europe and the Americas combined, slowing demand growth in the Asian nation is also impacting global demand. IFR, which brings together nearly 60 global robot suppliers and integrators, predicts worldwide industrial robot sales this year will grow 10 percent compared to last year's 30 percent. Because of the trade war, many global manufacturers "are now in a wait-and-see mode, wondering whether to shift production (away from China) to, let's say, Vietnam or the United States," IFR President Junji Tsuda said in an interview.

It will take a while for the direction of the trade war to be clear, Tsuda said. "But global demand for smartphones, semiconductors and autos have been solid, and the time will eventually come that they can wait no longer and will resume investment to meet the demand."

The 71-year-old fast-fashion chain is aiming to arrest a slump in same-store sales that has lasted 10 straight quarters as it faces problems bedeviling the industry: A spike in online shopping has led to fewer customers visiting stores, and digital startups are putting up fierce competition. H&M has repeatedly slashed prices to clear out $4 billion of unsold goods, and its shares are down 56% in the past three years. H&M, like most retailers, relies on a team of designers to figure out what shoppers want to buy. Now, it's using algorithms to analyze store receipts, returns and loyalty-card data to better align supply and demand, with the goal of reducing markdowns. As a result, some stores have started carrying more fashion and fewer basics such as T-shirts and leggings.

Despite the success of "Resident Evil" and "Dead Rising 4," Capcom's revenue and profits declined in the nine-month period that ended last December 2016. This week, the Japanese video game developer and publisher expressed its desire to transition to become a VR-focused company. According to VR Focus, Capcom is planning to invest more in virtual reality technology in hopes of establishing a new market. This is after the publisher made its earnings public via a press release early this week. Based on the figures presented, Capcom's sales and profits saw a decline compared to the previous period.

Microsoft's recent purchase of LinkedIn for a reported 26.2 billion may be the biggest acquisition news so far in 2016. But Twitter is betting that its own recent acquisition of Magic Pony Technology – a neural networks/machine learning company – for a mere 150 million will pay big dividends down the stretch. Commenting on the acquisition in a recent Twitter blog, Twitter CEO and co-founder Jack Dorsey said, "Machine learning is increasingly at the core of everything we build at Twitter." Dorsey went on to say that, "Magic Pony's machine learning technology will help us build strength into our deep learning teams with world-class talent, so Twitter can continue to be the best place to see what's happening and why it matters, first. We value deep learning research to help make our world better, and we will keep doing our part to share our work and learnings with the community." Magic Pony Technology is the third machine-learning startup that Twitter has acquired since Madbits in 2014, which begs the question: Why is Twitter so heavily focused on machine learning?