We consider the problem of recommending relevant labels (items) for a given data point (user). In particular, we are interested in the practically important setting where the evaluation is with respect to non-decomposable (over labels) performance metrics like the $F_1$ measure, \emph{and} training data has missing labels. To this end, we propose a generic framework that given a performance metric $\Psi$, can devise a regularized objective function and a threshold such that all the values in the predicted score vector above and only above the threshold are selected to be positive. We show that the regret or generalization error in the given metric $\Psi$ is bounded ultimately by estimation error of certain underlying parameters. In particular, we derive regret bounds under three popular settings: a) collaborative filtering, b) multilabel classification, and c) PU (positive-unlabeled) learning. For each of the above problems, we can obtain precise non-asymptotic regret bound which is small even when a large fraction of labels is missing. Our empirical results on synthetic and benchmark datasets demonstrate that by explicitly modeling for missing labels and optimizing the desired performance metric, our algorithm indeed achieves significantly better performance (like $F_1$ score) when compared to methods that do not model missing label information carefully.

We introduce the framework of {\em blind regression} motivated by {\em matrix completion} for recommendation systems: given $m$ users, $n$ movies, and a subset of user-movie ratings, the goal is to predict the unobserved user-movie ratings given the data, i.e., to complete the partially observed matrix. Following the framework of non-parametric statistics, we posit that user $u$ and movie $i$ have features $x_1(u)$ and $x_2(i)$ respectively, and their corresponding rating $y(u,i)$ is a noisy measurement of $f(x_1(u), x_2(i))$ for some unknown function $f$. In contrast with classical regression, the features $x = (x_1(u), x_2(i))$ are not observed, making it challenging to apply standard regression methods to predict the unobserved ratings. Inspired by the classical Taylor's expansion for differentiable functions, we provide a prediction algorithm that is consistent for all Lipschitz functions. In fact, the analysis through our framework naturally leads to a variant of collaborative filtering, shedding insight into the widespread success of collaborative filtering in practice. Assuming each entry is sampled independently with probability at least $\max(m^{-1+\delta},n^{-1/2+\delta})$ with $\delta > 0$, we prove that the expected fraction of our estimates with error greater than $\epsilon$ is less than $\gamma^2 / \epsilon^2$ plus a polynomially decaying term, where $\gamma^2$ is the variance of the additive entry-wise noise term. Experiments with the MovieLens and Netflix datasets suggest that our algorithm provides principled improvements over basic collaborative filtering and is competitive with matrix factorization methods.

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in industry, their outputs could affect business decision making, introducing incentives for an adversarial party to compromise the availability or integrity of such systems. We introduce a data poisoning attack on collaborative filtering systems. We demonstrate how a powerful attacker with full knowledge of the learner can generate malicious data so as to maximize his/her malicious objectives, while at the same time mimicking normal user behaviors to avoid being detected. While the complete knowledge assumption seems extreme, it enables a robust assessment of the vulnerability of collaborative filtering schemes to highly motivated attacks. We present efficient solutions for two popular factorization-based collaborative filtering algorithms: the alternative minimization formulation and the nuclear norm minimization method. Finally, we test the effectiveness of our proposed algorithms on real-world data and discuss potential defensive strategies.

We propose a novel and efficient algorithm for the collaborative preference completion problem, which involves jointly estimating individualized rankings for a set of entities over a shared set of items, based on a limited number of observed affinity values. Our approach exploits the observation that while preferences are often recorded as numerical scores, the predictive quantity of interest is the underlying rankings. Thus, attempts to closely match the recorded scores may lead to overfitting and impair generalization performance. Instead, we propose an estimator that directly fits the underlying preference order, combined with nuclear norm constraints to encourage low--rank parameters. Besides (approximate) correctness of the ranking order, the proposed estimator makes no generative assumption on the numerical scores of the observations. One consequence is that the proposed estimator can fit any consistent partial ranking over a subset of the items represented as a directed acyclic graph (DAG), generalizing standard techniques that can only fit preference scores. Despite this generality, for supervision representing total or blockwise total orders, the computational complexity of our algorithm is within a $\log$ factor of the standard algorithms for nuclear norm regularization based estimates for matrix completion. We further show promising empirical results for a novel and challenging application of collaboratively ranking of the associations between brain--regions and cognitive neuroscience terms.

Word embeddings are a powerful approach to capturing semantic similarity among terms in a vocabulary. In this paper, we develop exponential family embeddings, which extends the idea of word embeddings to other types of high-dimensional data. As examples, we studied several types of data: neural data with real-valued observations, count data from a market basket analysis, and ratings data from a movie recommendation system. The main idea is that each observation is modeled conditioned on a set of latent embeddings and other observations, called the context, where the way the context is defined depends on the problem. In language the context is the surrounding words; in neuroscience the context is close-by neurons; in market basket data the context is other items in the shopping cart. Each instance of an embedding defines the context, the exponential family of conditional distributions, and how the embedding vectors are shared across data. We infer the embeddings with stochastic gradient descent, with an algorithm that connects closely to generalized linear models. On all three of our applications—neural activity of zebrafish, users’ shopping behavior, and movie ratings—we found that exponential family embedding models are more effective than other dimension reduction methods. They better reconstruct held-out data and find interesting qualitative structure.

"Alexa, how are you different than Siri?" "I'm more of a home-body" I'm away from my desk, so I guess I can't ask Alexa. No problem, I've got an iPhone in my pocket. "Hey Siri, what's the status of my Amazon order?" "I wish I could, but Amazon hasn't set that up with me yet." IPAs (intelligent personal assistants*) are in their infancy, but they are a next major step in human-computer interaction. With the expected concurrent growth of IoT and connected devices, IPAs will be everywhere soon.

Google's new Pixel and Pixel XL phones come with some pretty awesome features. Google's new smart Assistant, unlimited cloud storage for photos and videos and it has one of the highest rated smartphone cameras. Here's a guide on how to make the most out of your new Google Pixel phone. Google Assistant is one of the best features of the new Pixel phones. You can use it on Google's new messaging app Allo and on the Google Home speaker.

LG is planning to show "advanced robot technologies" at CES 2017 next week to showcase new innovations in artificial intelligence. The robots aren't your run-of-the-mill smart toasters or vacuum bots either, with some being designed for public use outdoors. There looks to be three new AI bots on the way, one for use at home, serving as a "smart home gateway" and personal assistant for owners: think, I, Robot. Another model "will demonstrate new capabilities for tending to one's yard and garden": think, The Lawnmower Man. The third, and perhaps most interesting type of robot LG has lined up includes "models designed for commercial use in public spaces such as airports and hotels to help improve the traveler's experience": think, Johnny Cab in Total Recall.

Opinions expressed by Forbes Contributors are their own. The author is a Forbes contributor. The opinions expressed are those of the writer. Few moments in life are more humiliating than showing off your new voice-assistant toy to family. Only for it to miss-hear, not understand or play Bonjovi when you ask what the weather's like today. I'm sure, given how well Alexa appears to have sold this Christmas, others have been through a similar ordeal.

It started out in your phone. You would ask Siri to tell you the weather report or a silly joke. But artificial intelligence and digital assistants are no laughing matter: They are likely the way most Americans will experience the Internet of Things (IoT) explosion, and are finally a cheap and easy way for mere mortals to automate their homes as only the wealthy once could. Last year Amazon brought its AI Alexa to homes, but next year it's going to be in your home. Cheap and affordable voice-controlled artificial intelligences like Amazon's Alexa and Google's Home are going to be everywhere, and you'll see that in spades at CES. You'll hear from companies like Neura that "enhance products with AI." You'll read about it when you hear about Ara by Kolibree, the world's first toothbrush with embedded AI. (My brain hurts thinking about that.)