Amazon knows you'll ask Alexa all sorts of questions about the midterms and politics in general, so it's been preparing the voice assistant for the event. It has teamed up with nonprofit digital encyclopedia Ballotpedia to equip Alexa with answers first-time voters will find especially helpful. You can ask the assistant when the polls will open and what's on your ballot. Alexa can even answer what it means to vote yes or no for a certain ballot measure and can list nominees running for a specific position. On Election Day itself, you can ask Alexa for a general update by asking "Alexa, what's my election update?"

A security researcher discovered a series of commands that could be used to brick the Google Home Hub. According to Jeremy Gamblin, it's possible to exploit a "undocumented (and amazingly unsecured)" API. It can be used to force the device to reboot or reveal data about a victim's network. Gamblin wrote in a blog post that after he purchased the Google Home Hub and set it up in his home, he noticed a number of open ports being used by the device. Curiosity got the best of him, and he started using the command prompt on his computer to text the smart display's security.

Spotify has a treat in store for Premium for Family subscribers in the US: you can claim a free Google Home Mini. The offer will be available for current and new master account holders starting Thursday, and you have until the end of the year to register for the smart speaker. Those on the $15/month plan can share their Spotify subscriptions among six family members, who can use Premium on their own accounts. With the Voice Match feature, Home Mini can recognize who's speaking and personalize music playback for them. It should snag Spotify some new subscribers, while Google could get more people hooked on YouTube Music Premium -- Home Mini comes with a three-month trial of that service.

New to the smart display fray: Google's Home Hub, which marries a small voice-activated Google Assistant speaker with a 7-inch display that you can tap and swipe. Unlike other smart displays, there is no front-facing camera on the Home Hub--a signal from Google that the Home Hub is safe and private enough to put in your bedroom or your bathroom. When you're not using it to watch YouTube or follow step-by-step recipes, the Home Hub will show a photo slideshow of curated artistic images, or photos from your Google Photos library. But if Google Assistant is already running your house like an invisible AI butler, then this is the best way to give the thing a face.

Facebook's Portal looked like a slick alternative to the Amazon Echo speaker when it launched earlier this month, but problems abounded behind the scenes. Facebook had already delayed the video-calling device due to privacy concerns around the Cambridge Analytica scandal. And when it finally did launch, there was a glaring omission: no voice assistant from Facebook. Instead it came with Alexa, meaning anyone who bought the 15.6-inch version for $350 got an awkward gateway to Amazon, whose competing Echo Show cost at least $100 less. It also meant Facebook was blocked from collecting any speech data to train its voice technology further.

Spotify reached 83 million subscribers. Spotify is giving a Google Home Mini speaker to family plan subscribers for a song – free. The music streaming service said Wednesday it would give master account owners of Premium for Family plans a free speaker that uses the artificial intelligence-infused, voice-driven Google Assistant. Spotify Premium for Family subscribers can have personalized Spotify accounts for up to six family members for $14.99 a month. You can already ask Google Home devices to play music on Spotify, but this deal aims to increase the reach of both the music service and the voice-friendly speakers.

Learning to rank is an important problem in machine learning and recommender systems. In a recommender system, a user is typically recommended a list of items. Since the user is unlikely to examine the entire recommended list, partial feedback arises naturally. At the same time, diverse recommendations are important because it is challenging to model all tastes of the user in practice. In this paper, we propose the first algorithm for online learning to rank diverse items from partial-click feedback. We assume that the user examines the list of recommended items until the user is attracted by an item, which is clicked, and does not examine the rest of the items. This model of user behavior is known as the cascade model. We propose an online learning algorithm, cascadelsb, for solving our problem. The algorithm actively explores the tastes of the user with the objective of learning to recommend the optimal diverse list. We analyze the algorithm and prove a gap-free upper bound on its n-step regret. We evaluate cascadelsb on both synthetic and real-world datasets, compare it to various baselines, and show that it learns even when our modeling assumptions do not hold exactly.

Exploiting low-rank structure of the user-item rating matrix has been the crux of many recommendation engines. However, existing recommendation engines force raters with heterogeneous behavior profiles to map their intrinsic rating scales to a common rating scale (e.g. 1-5). This non-linear transformation of the rating scale shatters the low-rank structure of the rating matrix, therefore resulting in a poor fit and consequentially, poor recommendations. In this paper, we propose Clustered Monotone Transforms for Rating Factorization (CMTRF), a novel approach to perform regression up to unknown monotonic transforms over unknown population segments. Essentially, for recommendation systems, the technique searches for monotonic transformations of the rating scales resulting in a better fit. This is combined with an underlying matrix factorization regression model that couples the user-wise ratings to exploit shared low dimensional structure. The rating scale transformations can be generated for each user, for a cluster of users, or for all the users at once, forming the basis of three simple and efficient algorithms proposed in this paper, all of which alternate between transformation of the rating scales and matrix factorization regression. Despite the non-convexity, CMTRF is theoretically shown to recover a unique solution under mild conditions. Experimental results on two synthetic and seven real-world datasets show that CMTRF outperforms other state-of-the-art baselines.

We consider the tensor completion problem of predicting the missing entries of a tensor. The commonly used CP model has a triple product form, but an alternate family of quadratic models which are the sum of pairwise products instead of a triple product have emerged from applications such as recommendation systems. Non-convex methods are the method of choice for learning quadratic models, and this work examines their sample complexity and error guarantee. Our main result is that with the number of samples being only linear in the dimension, all local minima of the mean squared error objective are global minima and recover the original tensor accurately. The techniques lead to simple proofs showing that convex relaxation can recover quadratic tensors provided with linear number of samples. We substantiate our theoretical results with experiments on synthetic and real-world data, showing that quadratic models have better performance than CP models in scenarios where there are limited amount of observations available.

Match says its lawsuit is anything but baseless -- detailing, in hundreds of pages of court documents, numerous similarities between the two apps. In the process, Match has accused Bumble of "almost every type of [intellectual property] infringement you could think of," says Sarah Burstein, a professor at the University of Oklahoma College of Law whose research focuses on design patents. One of the central questions revolves around Tinder's patented system for connecting people over the Internet. The matching is based on mutual interest, as expressed through a swiping motion.