Prime Day is here again. Actually, Amazon's second coming of Prime Day is now called Prime Big Deal Days--a bold choice, to say the least. We'll still be calling it Amazon Prime Day, and you hereby have permission from this humble WIRED writer to do the same. We've rounded up the best Prime Day deals under $50-- nothing feels more like a deal than when it's affordable, but it can be hard to find what's a good cheap deal and what isn't. We did the work for you (you're welcome!).

It's no secret that Amazon Prime Day is one of the best times of the year to pick up an Echo speaker. That was true for the main sales event in July, and it's true again for October. Most of Amazon's smart speakers and smart displays are down to record-low prices, or close to them, so Prime members can pick them up for some of the best prices we've seen all year. If you've wanted to add to your smart home setup, or build one from scratch, now's a great time to get an Alexa-enabled device. Here are all of the best Prime Day deals on Echo Dots, Echo Show displays and more.

Public art shapes our shared spaces. Public art should speak to community and context, and yet, recent work has demonstrated numerous instances of art in prominent institutions favoring outdated cultural norms and legacy communities. Motivated by this, we develop a novel recommender system to curate public art exhibits with built-in equity objectives and a local value-based allocation of constrained resources. We develop a cost matrix by drawing on Schelling's model of segregation. Using the cost matrix as an input, the scoring function is optimized via a projected gradient descent to obtain a soft assignment matrix. Our optimization program allocates artwork to public spaces in a way that de-prioritizes "in-group" preferences, by satisfying minimum representation and exposure criteria. We draw on existing literature to develop a fairness metric for our algorithmic output, and we assess the effectiveness of our approach and discuss its potential pitfalls from both a curatorial and equity standpoint.

The contextual linear bandit is an important online learning problem where given arm features, a learning agent selects an arm at each round to maximize the cumulative rewards in the long run. A line of works, called the clustering of bandits (CB), utilize the collaborative effect over user preferences and have shown significant improvements over classic linear bandit algorithms. However, existing CB algorithms require well-specified linear user models and can fail when this critical assumption does not hold. Whether robust CB algorithms can be designed for more practical scenarios with misspecified user models remains an open problem. In this paper, we are the first to present the important problem of clustering of bandits with misspecified user models (CBMUM), where the expected rewards in user models can be perturbed away from perfect linear models. We devise two robust CB algorithms, RCLUMB and RSCLUMB (representing the learned clustering structure with dynamic graph and sets, respectively), that can accommodate the inaccurate user preference estimations and erroneous clustering caused by model misspecifications. We prove regret upper bounds of $O(\epsilon_*T\sqrt{md\log T} + d\sqrt{mT}\log T)$ for our algorithms under milder assumptions than previous CB works (notably, we move past a restrictive technical assumption on the distribution of the arms), which match the lower bound asymptotically in $T$ up to logarithmic factors, and also match the state-of-the-art results in several degenerate cases. The techniques in proving the regret caused by misclustering users are quite general and may be of independent interest. Experiments on both synthetic and real-world data show our outperformance over previous algorithms.

Recommender systems (RSs) play a central role in connecting users to content, products, and services, matching candidate items to users based on their preferences. While traditional RSs rely on implicit user feedback signals, conversational RSs interact with users in natural language. In this work, we develop a comPelling, Precise, Personalized, Preference-relevant language model (P4LM) that recommends items to users while putting emphasis on explaining item characteristics and their relevance. P4LM uses the embedding space representation of a user's preferences to generate compelling responses that are factually-grounded and relevant w.r.t. the user's preferences. Moreover, we develop a joint reward function that measures precision, appeal, and personalization, which we use as AI-based feedback in a reinforcement learning-based language model framework. Using the MovieLens 25M dataset, we demonstrate that P4LM delivers compelling, personalized movie narratives to users.

We're just a couple days away from Amazon's October Prime Day sale, which kicks off on Tuesday and goes through Wednesday. Prime Big Deal Days is the company's second site-wide sale of 2023 and there are already plenty of early deals to be found. You'll need a Prime membership for some, but other discounts are open to everyone. We'll be rounding up the best of what's out there on October 10 and 11, but in the meantime, you can get a jump on a few sales that are already live. This week's best tech deals include lots of Amazon devices like Echo speakers, Echo Show smart displays, Blink cameras, Ring doorbells and the Kindle Kids ereader. Apple's AirPods Pro now come with USB-C charging. They're still the "best for iOS" pick in our wireless earbuds buying guide, as they provide pleasing audio quality, strong active noise cancellation (ANC) and a range of iPhone-friendly features.

In this effort, we consider the impact of regularization on the diversity of actions taken by policies generated from reinforcement learning agents trained using a policy gradient. Policy gradient agents are prone to entropy collapse, which means certain actions are seldomly, if ever, selected. We augment the optimization objective function for the policy with terms constructed from various $\varphi$-divergences and Maximum Mean Discrepancy which encourages current policies to follow different state visitation and/or action choice distribution than previously computed policies. We provide numerical experiments using MNIST, CIFAR10, and Spotify datasets. The results demonstrate the advantage of diversity-promoting policy regularization and that its use on gradient-based approaches have significantly improved performance on a variety of personalization tasks. Furthermore, numerical evidence is given to show that policy regularization increases performance without losing accuracy.

Sequential user modeling, a critical task in personalized recommender systems, focuses on predicting the next item a user would prefer, requiring a deep understanding of user behavior sequences. Despite the remarkable success of Transformer-based models across various domains, their full potential in comprehending user behavior remains untapped. In this paper, we re-examine Transformer-like architectures aiming to advance state-of-the-art performance. We start by revisiting the core building blocks of Transformer-based methods, analyzing the effectiveness of the item-to-item mechanism within the context of sequential user modeling. After conducting a thorough experimental analysis, we identify three essential criteria for devising efficient sequential user models, which we hope will serve as practical guidelines to inspire and shape future designs. Following this, we introduce ConvFormer, a simple but powerful modification to the Transformer architecture that meets these criteria, yielding state-of-the-art results. Additionally, we present an acceleration technique to minimize the complexity associated with processing extremely long sequences. Experiments on four public datasets showcase ConvFormer's superiority and confirm the validity of our proposed criteria.

There is limited information on how voice assistants may spread misinformation, yet some researchers argue they could be particularly effective vectors for falsehoods. Users have "higher trust" in the assistants due to their humanlike characteristics, according to a paper written by researchers at King's College London. Customers may also think the information they're getting is coming directly from the tech companies, rather than a third-party provider, making it seem more reliable, according to the paper.

Recommender systems have emerged as a crucial component of the modern web ecosystem. The effectiveness and accuracy of such systems are critical for providing users with personalized recommendations that meet their specific interests and needs. In this paper, we introduce a novel model that utilizes a Graph Neural Network (GNN) in conjunction with sentence transformer embeddings to predict anime recommendations for different users. Our model employs the task of link prediction to create a recommendation system that considers both the features of anime and user interactions with different anime. The hybridization of the GNN and transformer embeddings enables us to capture both inter-level and intra-level features of anime data.Our model not only recommends anime to users but also predicts the rating a specific user would give to an anime. We utilize the GraphSAGE network for model building and weighted root mean square error (RMSE) to evaluate the performance of the model. Our approach has the potential to significantly enhance the accuracy and effectiveness of anime recommendation systems and can be extended to other domains that require personalized recommendations.