Restless bandit problems are instances of non-stationary multi-armed bandits.

Ganesh Gopalan, chief executive officer of Indian voice biometrics firm Gnani.ai will be the country's representative at the Global Partnership on Artificial Intelligence (GPAI). In an announcement, Gnani.ai said its CEO will be part of the multistakeholder collaboration working to bridge the gap between theory and practice in the field of AI by enhancing innovative research and carrying out applied initiatives on key AI-related priorities. "It is a privilege to be invited to join GPAI and participate in the creation of ethical AI solutions that can positively impact society. At Gnani.ai, our goal is to create AI that is transparent, ethical, and inclusive and I am excited to exchange knowledge with other experts in the field and contribute our own insights," says Gopalan. The Gnani.ai executive also expressed gratitude to India's Minister of State for Electronics and Information Technology Shri Rajeev Chandrasekhar for his motivation.

Robots acting in human-scale environments must plan under uncertainty in large state–action spaces and face constantly changing reward functions as requirements and goals change. Planning under uncertainty in large state–action spaces requires hierarchical abstraction for efficient computation. We introduce a new hierarchical planning framework called Abstract Markov Decision Processes (AMDPs) that can plan in a fraction of the time needed for complex decision making in ordinary MDPs. AMDPs provide abstract states, actions, and transition dynamics in multiple layers above a base-level "flat" MDP. AMDPs decompose problems into a series of subtasks with both local reward and local transition functions used to create policies for subtasks. The resulting hierarchical planning method is independently optimal at each level of abstraction, and is recursively optimal when the local reward and transition functions are correct. We present empirical results showing significantly improved planning speed, while maintaining solution quality, in the Taxi domain and in a mobile-manipulation robotics problem. Furthermore, our approach allows specification of a decision-making model for a mobile-manipulation problem on a Turtlebot, spanning from low-level control actions operating on continuous variables all the way up through high-level object manipulation tasks.

As more companies use conversational AI bots as a front line of customer service for consumers, the experience can typically be either helpful or maddening. Ganesh Gopalan, the CEO and co-founder of conversational AI vendor Gnani.ai, Early conversational AI systems were built around keywords, which when mentioned by a consumer caller, would then invoke a related response, said Gopalan. The problem was that this process often lacked context and did not adjust for regional dialects or casual wordings. For users, that could be frustrating because when the bot did not understand them, they were transferred to a live agent and had to repeat all they had already shared with the bot.

In machine learning, the notion of multi-armed bandits (MAB) refers to a class of online learning problems, in which a learner is supposed to simultaneously explore and exploit a given set of choice alternatives (metaphorically referred to as "arms") in the course of a sequential decision process (Lattimore and Szepesvári, 2019). In this paper, we consider an extension of the basic setting, which is practically motivated by the problem of preselection as recently introduced by Saha and Gopalan (2018b) and Bengs and Hüllermeier (2019): Instead of selecting a single arm, the learner is only supposed to preselect a promising subset of arms. The final choice is then made by a selector, for example a human user or another algorithm. In information retrieval, for instance, the role of the learner is played by a search engine, and the selector is the user who seeks a certain information. Another application, which served as a concrete motivation of our setting and will also be used in our experimental study, is the problem of algorithm (pre-)selection (Kerschke et al., 2018).

Modelling sparse and large data sets is highly in demand yet challenging in recommender systems. With the computation only on the non-zero ratings, Poisson Factorization (PF) enabled by variational inference has shown its high efficiency in scalable recommendation, e.g., modeling millions of ratings. However, as PF learns the ratings by individual users on items with the Gamma distribution, it cannot capture the coupling relations between users (items) and the rating popularity (i.e., favorable rating scores that are given to one item) and rating sparsity (i.e., those users (items) with many zero ratings) for one item (user). This work proposes Coupled Poisson Factorization (CPF) to learn the couplings between users (items), and the user/item attributes (i.e., metadata) are integrated into CPF to form the Metadata-integrated CPF (mCPF) to not only handle sparse but also popular ratings in very large-scale data. Our empirical results show that the proposed models significantly outperform PF and address the key limitations in PF for scalable recommendation.

Velodyne re-asserted its dominance of the lidar market today by announcing a product with 128 laser beams, twice as many as its previous top-of-the-line model. "The VLS-128 is the best LiDAR sensor on the planet, delivering the most advanced real-time 3D vision for safe driving," Mike Jellen, the president of Velodyne LiDAR, said in a statement. The announcement, which had been widely anticipated, leaves out the one detail that everyone most wants to know: the price. The company's previous top-of-the-line product originally sold for more than US $70,000. Today, though, a host of rival companies are on the scene, some of them promising solid-state products that cost less because they have no moving parts.

We present a non-negative inductive latent factor model for binary- and count-valued matrices containing dyadic data, with side information along the rows and/or the columns of the matrix. The side information is incorporated by conditioning the row and column latent factors on the available side information via a regression model. Our model can not only perform matrix factorization and completion with side-information, but also infers interpretable latent topics that explain/summarize the data. An appealing aspect of our model is in the full local conjugacy of all parts of the model, including the main latent factor model, as well as for the regression model that leverages the side information. This enables us to design scalable and simple to implement Gibbs sampling and Expectation Maximization algorithms for doing inference in the model. Inference cost in our model scales in the number of nonzeros in the data matrix, which makes it particularly attractive for massive, sparse matrices. We demonstrate the effectiveness of our model on several real-world data sets, comparing it with state-of-the-art baselines.

Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods. Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very well despite being ``frustratingly easy'' to implement. However, in practice, the target domain is often unlabeled, requiring unsupervised adaptation. We propose a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL). CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. Even though it is extraordinarily simple--it can be implemented in four lines of Matlab code--CORAL performs remarkably well in extensive evaluations on standard benchmark datasets.