Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this work, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is suitable for solving online learning problems that involve graphs, such as content-based recommendation. In this problem, each item we can recommend is a node of an undirected graph and its expected rating is similar to the one of its neighbors. The goal is to recommend items that have high expected ratings. We aim for the algorithms where the cumulative regret with respect to the optimal policy would not scale poorly with the number of nodes. In particular, we introduce the notion of an effective dimension, which is small in real-world graphs, and propose three algorithms for solving our problem that scale linearly and sublinearly in this dimension. Our experiments on content recommendation problem show that a good estimator of user preferences for thousands of items can be learned from just tens of node evaluations.

Follow this author to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. An eclectic crowd of leaders, artists, and innovators gathered Thursday night in New York City for the TIME100 Gala, celebrating the 100 Most Influential People of 2026 . Artists, actors, chefs, politicians, activists and business leaders brushed shoulders with each other as they shared in cocktails and conversations.

The answer may already be in your home. To achieve a smart home, you need a voice assistant to run it. A smart home assistant, usually folded into a smart speaker, will let you command your smart home with your voice and run your various routines. It also acts as a center for every gadget you want to add to your home. And you can add almost anything these days, from smart garage control to even voice-commanding your blinds .

Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which items are available to the ranker, changing the generator changes both the policy value and the data support used to estimate that value. This creates an offline selection problem that standard single-stage objectives do not capture: a policy may look good under a retrieval score or a raw off-policy value estimate, but still be unreliable if it depends on weakly supported generator-item pairs. We propose CASP (Coupled Action-Set Pessimism), a support-aware offline selector for finite libraries of two-stage recommender policies. CASP combines doubly robust value estimation with a support-burden penalty. We show that stagewise rules that ignore downstream continuation value can be arbitrarily suboptimal, and we derive population, finite-class, and reconstructed-propensity guarantees for conservative selection. In simulations and a reconstructed MovieLens 1M application, CASP selects lower-burden policies when estimated value and support credibility are in tension.

Follow this author to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Four experts spoke about the importance of investing in early childhood education in a TIME100 Talk moderated by TIME executive editor Nikhil Kumar at the TIME100 Summit in New York City on April 22. The panel featured Amanda Devercelli, senior education specialist at the World Bank; Emily Gustafsson-Wright, senior fellow in the global economy and development program at the Brookings Institution; Maria Adelaida Lopez, an artist and educator; and Dr. Jack Shonkoff, a professor of child health and development and founding director of the Center on the Developing Child at Harvard University.

Learning disentangled representations for user intentions from multi-feedback (i.e., positive and negative feedback) can enhance the accuracy and explainability of recommendation algorithms. However, learning such disentangled representations from multi-feedback data is challenging because i) multi-feedback is complex: there exist complex relations among different types of feedback (e.g., click, unclick, and dislike, etc) as well as various user intentions, and ii) multi-feedback is noisy: there exists noisy (useless) information both in features and labels, which may deteriorate the recommendation performance. Existing disentangled recommendation works only focus on positive feedback, failing to handle the complex relations and noise hidden in multi-feedback data. To solve this problem, in this work we propose a Curriculum Disentangled Recommendation (CDR) model that is capable of efficiently learning disentangled representations from complex and noisy multi-feedback for better recommendation.

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient descent, has been the workhorse in protecting user privacy without compromising model accuracy by much. However, applying DP-SGDnaively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. To address this issue, we present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models. Our algorithms achieve substantial reductions (106) in gradient size, while maintaining comparable levels of accuracy, on benchmark real-world datasets.