arXiv subjects
Publications and source records attributed to You.
This note provides an interesting observation on casting partial least square (PLS) as a linearized self-attention so that PLS may be studied within the neural network paradigm. On the other hand, the dimensionality reduction and selection of predictors in PLS may indicate that self-attention includes certain degree of dimensionality normalization toward improved learning.
People leverage avatars to communicate nonverbal behaviors in immersive virtual reality (VR), like interpersonal distance [2, 6] and virtual touch [5]. However, violations of appropriate physical distancing and unsolicited intimate touching behavior in social virtual worlds represent potential social and psychological virtual harm to older adolescent users [4, 8]. Obtaining peer acceptance and social rewards, while avoiding social rejection can drive older adolescent behavior even in simulated virtual spaces [1, 3], and while "the beginning of adolescence is largely defined by a biological event, [...] the end of adolescence is often defined socially" [3] (p.912). Avatar crossing, the phenomenon of avatars walking through each other in virtual environments, is a unique capability of virtual embodiment, and others intriguing possibilities and ethical concerns for older adolescents experiencing social virtual spaces. For example, the ability to cross through and share positions with other avatars in a virtual classroom helps students concentrate on accessing and comprehending information without concerns about blocking others when navigating for better viewpoints [10]. However, the ability to cross through others in virtual spaces has been associated with a reduction in perceived presence and avatar realism, coupled with a greater level of discomfort and intimidation in comparison to avatar collisions [12]. In this article, we consider the potential benefits and harms of utilizing avatar crossing with adolescent users.
Given a data set, misleading conclusions can be drawn from it by cherry-picking selected samples. One important class of conclusions is a trend derived from a data set of values over time. Our goal is to evaluate whether the 'trends' described by the extracted samples are representative of the true situation represented in the data. We demonstrate MithraDetective, a system to compute a support score to indicate how cherry-picked a statement is; that is, whether the reported trend is well-supported by the data. The system can also be used to discover more supported alternatives. MithraDetective provides an interactive visual interface for both tasks.
Nonlinear function estimation is core to modern machine learning applications. In this paper, to perform nonlinear function estimation, we reduce a nonlinear inverse problem to a linear one using a polynomial kernel expansion. These kernels increase the feature set, and may result in poorly conditioned matrices. Nonetheless, we show several examples where the matrix in our linear inverse problem contains only mild linear correlations among columns. The coefficients vector is modeled within a Bayesian setting for which approximate message passing (AMP), an algorithmic framework for signal reconstruction, offers Bayes-optimal signal reconstruction quality. While the Bayesian setting limits the scope of our work, it is a first step toward estimation of real world nonlinear functions. The coefficients vector is estimated using two AMP-based approaches, a Bayesian one and empirical Bayes. Numerical results confirm that our AMP-based approaches learn the function better than LASSO, offering markedly lower error in predicting test data.
Approximate message passing (AMP) methods have gained recent traction in sparse signal recovery. Additional information about the signal, or \emph{side information} (SI), is commonly available and can aid in efficient signal recovery. This work presents an AMP-based framework that exploits SI and can be readily implemented in various settings for which the SI results in separable distributions. To illustrate the simplicity and applicability of our approach, this framework is applied to a Bernoulli-Gaussian (BG) model and a time-varying birth-death-drift (BDD) signal model, motivated by applications in channel estimation. We develop a suite of algorithms, called AMP-SI, and derive denoisers for the BDD and BG models. Numerical evidence demonstrating the advantages of our approach are presented alongside empirical evidence of the accuracy of a proposed state evolution.