The evaluation of recommender systems from a practical perspective is a topic of ongoing discourse within the research community. While many current evaluation methods reduce performance to a single value metric as an easy way to compare models, it relies on the assumption that the methods' performance remains constant over time. In this study, we examine this assumption and propose the Cross-Validation Thought Time (CVTT) technique as a more comprehensive evaluation method, focusing on model performance over time. By utilizing the proposed technique, we conduct an in-depth analysis of the performance of popular RecSys algorithms. Our findings indicate that (1) the performance of the recommenders varies over time for all reviewed datasets, (2) using simple evaluation approaches can lead to a substantial decrease in performance in real-world evaluation scenarios, and (3) excessive data usage can lead to suboptimal results.

Current tractography methods use the local orientation information to propagate streamlines from seed locations. Many such seeds provide streamlines that stop prematurely or fail to map the true white matter pathways because some bundles are "harder-to-track" than others. This results in tractography reconstructions with poor white and gray matter spatial coverage. In this work, we propose a generative, autoencoder-based method, named GESTA (Generative Sampling in Bundle Tractography using Autoencoders), that produces streamlines achieving better spatial coverage. Compared to other deep learning methods, our autoencoder-based framework uses a single model to generate streamlines in a bundle-wise fashion, and does not require to propagate local orientations. GESTA produces new and complete streamlines for any given white matter bundle, including hard-to-track bundles. Applied on top of a given tractogram, GESTA is shown to be effective in improving the white matter volume coverage in poorly populated bundles, both on synthetic and human brain in vivo data. Our streamline evaluation framework ensures that the streamlines produced by GESTA are anatomically plausible and fit well to the local diffusion signal. The streamline evaluation criteria assess anatomy (white matter coverage), local orientation alignment (direction), and geometry features of streamlines, and optionally, gray matter connectivity. GESTA is thus a novel deep generative bundle tractography method that can be used to improve the tractography reconstruction of the white matter.

While coreference resolution typically involves various linguistic challenges, recent models are based on a single pairwise scorer for all types of pairs. We present LingMess, a new coreference model that defines different categories of coreference cases and optimize multiple pairwise scorers, where each scorer learns a specific set of linguistic challenges. Our model substantially improves pairwise scores for most categories and outperforms cluster-level performance on Ontonotes and 5 additional datasets. Our model is available in https://github.com/shon-otmazgin/lingmess-coref

The performance of deep neural networks is strongly influenced by the training dataset setup. In particular, when attributes with a strong correlation with the target attribute are present, the trained model can provide unintended prejudgments and show significant inference errors (i.e., the dataset bias problem). Various methods have been proposed to mitigate dataset bias, and their emphasis is on weakly correlated samples, called bias-conflicting samples. These methods are based on explicit bias labels provided by humans. However, such methods require human costs. Recently, several studies have sought to reduce human intervention by utilizing the output space values of neural networks, such as feature space, logits, loss, or accuracy. However, these output space values may be insufficient for the model to understand the bias attributes well. In this study, we propose a debiasing algorithm leveraging gradient called Per-sample Gradient-based Debiasing (PGD). PGD is comprised of three steps: (1) training a model on uniform batch sampling, (2) setting the importance of each sample in proportion to the norm of the sample gradient, and (3) training the model using importance-batch sampling, whose probability is obtained in step (2). Compared with existing baselines for various datasets, the proposed method showed state-of-the-art accuracy for the classification task. Furthermore, we describe theoretical understandings of how PGD can mitigate dataset bias. Dataset bias (Torralba & Efros, 2011; Shrestha et al., 2021) is a bad training dataset problem that occurs when unintended easier-to-learn attributes (i.e., bias attributes), having a high correlation with the target attribute, are present (Shah et al., 2020; Ahmed et al., 2020). This is due to the fact that the model can infer outputs by focusing on the bias features, which could lead to testing failures. For example, most "camel" images include a "desert background," and this unintended correlation can provide a false shortcut for answering "camel" on the basis of the "desert." In (Nam et al., 2020; Lee et al., 2021), samples of data that have a strong correlation (like the aforementioned desert/camel) are called "bias-aligned samples," while samples of data that have a weak correlation (like "camel on the grass" images) are termed "bias-conflicting samples." To reduce the dataset bias, initial studies (Kim et al., 2019; McDuff et al., 2019; Singh et al., 2020; Li & Vasconcelos, 2019) have frequently assumed a case where labels with bias attributes are provided, but these additional labels provided through human effort are expensive. Alternatively, the bias-type, such as "background," is assumed in (Lee et al., 2019; Geirhos et al., 2018; Bahng et al., 2020; Cadene et al., 2019; Clark et al., 2019). However, assuming biased knowledge from humans is still unreasonable, since even humans cannot predict the type of bias that may exist in a large dataset (Schäfer, 2016).

BARCELONA, SPAIN - FEBRUARY 28: A visitor enjoys a Virtual Reality experience at the SK telecom ... [ ] booth on day 1 of the GSMA Mobile World Congress on February 28, 2022 in Barcelona, Spain. A pattern we see in many industries is that technology changes alongside culture and society, and this remains true for entertainment. The most obvious to consumers has been the shift from terrestrial television to streaming services like Netflix NFLX and Amazon AMZN Prime. The greater flexibility allowed consumers to decouple themselves from an entertainment schedule, being dictated by broadcast times. OTT platforms are aligned with the changing patterns of casualized work and study that focus on individual freedom.

Netflix is rolling out changes to account sharing in Canada, New Zealand, Portugal and Spain after trialing the change in Latin America. If you live in one of these countries, you must set a primary location for where you use it. Then, if you have friends or family who want to share your account, you'll have to subscribe to either the Standard or Premium tier and pay a fee ($8 in Canada and New Zealand, €4 in Portugal and €6 in Spain) for up to two extra users outside of your home. In Netflix's words, "Today, over 100 million households are sharing accounts – impacting our ability to invest in great new TV and films." It's not clear how new regions will take to the policy.

As Google's AI-powered Bard prepares to compete against ChatGPT, don't count on the chatbot programs always being right: A recent demo of Bard shows it spouting inaccurate information. Bard, which Google announced on Monday, is slated to arrive in the coming weeks. To promote the AI program, the company posted a GIF on social media that shows Bard answering a question about what new discoveries NASA's James Webb Space Telescope has made. The program lists three discoveries the space telescope made in an easy-to-read, bulleted format. Hence, through Bard, a user can quickly learn information, without having to scroll through a long list of search results to find the applicable site.

Studies show dramatic increase in elderly population of Western Europe over the next few decades, which will put pressure on healthcare systems. Measures must be taken to meet these social challenges. Healthcare robots investigated to facilitate independent living for elderly. This paper aims to review recent projects in robotics for healthcare from 2008 to 2021. We provide an overview of the focus in this area and a roadmap for upcoming research. Our study was initiated with a literature search using three digital databases. Searches were performed for articles, including research projects containing the words elderly care, assisted aging, health monitoring, or elderly health, and any word including the root word robot. The resulting 20 recent research projects are described and categorized in this paper. Then, these projects were analyzed using thematic analysis. Our findings can be summarized in common themes: most projects have a strong focus on care robots functionalities; robots are often seen as products in care settings; there is an emphasis on robots as commercial products; and there is some limited focus on the design and ethical aspects of care robots. The paper concludes with five key points representing a roadmap for future research addressing robotic for elderly people.

We develop new tools in the theory of nonlinear random matrices and apply them to study the performance of the Sum of Squares (SoS) hierarchy on average-case problems. The SoS hierarchy is a powerful optimization technique that has achieved tremendous success for various problems in combinatorial optimization, robust statistics and machine learning. It's a family of convex relaxations that lets us smoothly trade off running time for approximation guarantees. In recent works, it's been shown to be extremely useful for recovering structure in high dimensional noisy data. It also remains our best approach towards refuting the notorious Unique Games Conjecture. In this work, we analyze the performance of the SoS hierarchy on fundamental problems stemming from statistics, theoretical computer science and statistical physics. In particular, we show subexponential-time SoS lower bounds for the problems of the Sherrington-Kirkpatrick Hamiltonian, Planted Slightly Denser Subgraph, Tensor Principal Components Analysis and Sparse Principal Components Analysis. These SoS lower bounds involve analyzing large random matrices, wherein lie our main contributions. These results offer strong evidence for the truth of and insight into the low-degree likelihood ratio hypothesis, an important conjecture that predicts the power of bounded-time algorithms for hypothesis testing. We also develop general-purpose tools for analyzing the behavior of random matrices which are functions of independent random variables. Towards this, we build on and generalize the matrix variant of the Efron-Stein inequalities. In particular, our general theorem on matrix concentration recovers various results that have appeared in the literature. We expect these random matrix theory ideas to have other significant applications.

A/B testing, or controlled experiments, is the gold standard approach to causally compare the performance of algorithms on online platforms. However, conventional Bernoulli randomization in A/B testing faces many challenges such as spillover and carryover effects. Our study focuses on another challenge, especially for A/B testing on two-sided platforms -- budget constraints. Buyers on two-sided platforms often have limited budgets, where the conventional A/B testing may be infeasible to be applied, partly because two variants of allocation algorithms may conflict and lead some buyers to exceed their budgets if they are implemented simultaneously. We develop a model to describe two-sided platforms where buyers have limited budgets. We then provide an optimal experimental design that guarantees small bias and minimum variance. Bias is lower when there is more budget and a higher supply-demand rate. We test our experimental design on both synthetic data and real-world data, which verifies the theoretical results and shows our advantage compared to Bernoulli randomization.