We propose Diffusion Model Variational Inference (DMVI), a novel method for automated approximate inference in probabilistic programming languages (PPLs). DMVI utilizes diffusion models as variational approximations to the true posterior distribution by deriving a novel bound to the marginal likelihood objective used in Bayesian modelling. DMVI is easy to implement, allows hassle-free inference in PPLs without the drawbacks of, e.g., variational inference using normalizing flows, and does not make any constraints on the underlying neural network model. We evaluate DMVI on a set of common Bayesian models and show that its posterior inferences are in general more accurate than those of contemporary methods used in PPLs while having a similar computational cost and requiring less manual tuning.
相關內容
The vast majority of approaches to speaker anonymization involve the extraction of fundamental frequency estimates, linguistic features and a speaker embedding which is perturbed to obfuscate the speaker identity before an anonymized speech waveform is resynthesized using a vocoder. Recent work has shown that x-vector transformations are difficult to control consistently: other sources of speaker information contained within fundamental frequency and linguistic features are re-entangled upon vocoding, meaning that anonymized speech signals still contain speaker information. We propose an approach based upon neural audio codecs (NACs), which are known to generate high-quality synthetic speech when combined with language models. NACs use quantized codes, which are known to effectively bottleneck speaker-related information: we demonstrate the potential of speaker anonymization systems based on NAC language modeling by applying the evaluation framework of the Voice Privacy Challenge 2022.
The paper introduces a tree-based varying coefficient model (VCM) where the varying coefficients are modelled using the cyclic gradient boosting machine (CGBM) from Delong et al. (2023). Modelling the coefficient functions using a CGBM allows for dimension-wise early stopping and feature importance scores. The dimension-wise early stopping not only reduces the risk of dimension-specific overfitting, but also reveals differences in model complexity across dimensions. The use of feature importance scores allows for simple feature selection and easy model interpretation. The model is evaluated on the same simulated and real data examples as those used in Richman and W\"uthrich (2023), and the results show that it produces results in terms of out of sample loss that are comparable to those of their neural network-based VCM called LocalGLMnet.
Building robust, interpretable, and secure AI system requires quantifying and representing uncertainty under a probabilistic perspective to mimic human cognitive abilities. However, probabilistic computation presents significant challenges for most conventional artificial neural network, as they are essentially implemented in a deterministic manner. In this paper, we develop an efficient probabilistic computation framework by truncating the probabilistic representation of neural activation up to its mean and covariance and construct a moment neural network that encapsulates the nonlinear coupling between the mean and covariance of the underlying stochastic network. We reveal that when only the mean but not the covariance is supervised during gradient-based learning, the unsupervised covariance spontaneously emerges from its nonlinear coupling with the mean and faithfully captures the uncertainty associated with model predictions. Our findings highlight the inherent simplicity of probabilistic computation by seamlessly incorporating uncertainty into model prediction, paving the way for integrating it into large-scale AI systems.
User interaction is one of the most effective ways to improve the ontology alignment quality. However, this approach faces the challenge of how users can participate effectively in the matching process. To solve this challenge. In this paper, an interactive ontology alignment approach using compact differential evolution algorithm with adaptive parameter control (IOACDE) is proposed. In this method, the ontology alignment process is modeled as an interactive optimization problem and users are allowed to intervene in matching in two ways. One is that the mapping suggestions generated by IOACDE as a complete candidate alignment is evaluated by user during optimization process. The other is that the user ameliorates the alignment results by evaluating single mapping after the automatic matching process. To demonstrate the effectiveness of the proposed algorithm, the neural embedding model and K nearest neighbor (KNN) is employed to simulate user for the ontologies of the real world. The experimental results show that the proposed interactive approach can improve the alignment quality compared to the non-interactive. Compared with the state-of-the-art methods from OAEI, the results show that the proposed algorithm has a better performance under the same error rate.
There is currently a focus on statistical methods which can use historical trial information to help accelerate the discovery, development and delivery of medicine. Bayesian methods can be constructed so that the borrowing is "dynamic" in the sense that the similarity of the data helps to determine how much information is used. In the time to event setting with one historical data set, a popular model for a range of baseline hazards is the piecewise exponential model where the time points are fixed and a borrowing structure is imposed on the model. Although convenient for implementation this approach effects the borrowing capability of the model. We propose a Bayesian model which allows the time points to vary and a dependency to be placed between the baseline hazards. This serves to smooth the posterior baseline hazard improving both model estimation and borrowing characteristics. We explore a variety of prior structures for the borrowing within our proposed model and assess their performance against established approaches. We demonstrate that this leads to improved type I error in the presence of prior data conflict and increased power. We have developed accompanying software which is freely available and enables easy implementation of the approach.
MGARD: A multigrid framework for high-performance, error-controlled data compression and refactoring
We describe MGARD, a software providing MultiGrid Adaptive Reduction for floating-point scientific data on structured and unstructured grids. With exceptional data compression capability and precise error control, MGARD addresses a wide range of requirements, including storage reduction, high-performance I/O, and in-situ data analysis. It features a unified application programming interface (API) that seamlessly operates across diverse computing architectures. MGARD has been optimized with highly-tuned GPU kernels and efficient memory and device management mechanisms, ensuring scalable and rapid operations.
We enumerate several classes of pattern-avoiding rectangulations. We establish bijective links with pattern-avoiding permutations, prove that their generating functions are algebraic, and confirm several conjectures by Merino and M\"utze. We also analyze a new class of rectangulations, called whirls, using a generating tree.
The STATIS method, proposed by L'Hermier des Plantes and Escoufier, is used to analyze multiple data tables in which is very common that each of the tables have information concerning the same set of individuals. The differences and similitudes between said tables are analyzed by means of a structure called the \emph{compromise}. In this paper we present a new algorithm for applying the STATIS method when the input consists of interval data. This proposal is based on Moore's interval arithmetic and the Centers Method for Principal Component Analysis with interval data, proposed by Cazes el al. \cite{cazes1997}. In addition to presenting the INTERSTATIS method in an algorithmic way, an execution example is shown, alongside the interpretation of its results.
When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum, and then discuss practical solutions including careful initialization and normalization methods. Second, we review generic optimization methods used in training neural networks, such as SGD, adaptive gradient methods and distributed methods, and theoretical results for these algorithms. Third, we review existing research on the global issues of neural network training, including results on bad local minima, mode connectivity, lottery ticket hypothesis and infinite-width analysis.
In recent years, object detection has experienced impressive progress. Despite these improvements, there is still a significant gap in the performance between the detection of small and large objects. We analyze the current state-of-the-art model, Mask-RCNN, on a challenging dataset, MS COCO. We show that the overlap between small ground-truth objects and the predicted anchors is much lower than the expected IoU threshold. We conjecture this is due to two factors; (1) only a few images are containing small objects, and (2) small objects do not appear enough even within each image containing them. We thus propose to oversample those images with small objects and augment each of those images by copy-pasting small objects many times. It allows us to trade off the quality of the detector on large objects with that on small objects. We evaluate different pasting augmentation strategies, and ultimately, we achieve 9.7\% relative improvement on the instance segmentation and 7.1\% on the object detection of small objects, compared to the current state of the art method on MS COCO.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191