We propose a technique for decomposing the parameter learning problem in Bayesian networks into independent learning problems. Our technique applies to incomplete datasets and exploits variables that are either hidden or observed in the given dataset. We show empirically that the proposed technique can lead to orders-of-magnitude savings in learning time. We explain, analytically and empirically, the reasons behind our reported savings, and compare the proposed technique to related ones that are sometimes used by inference algorithms.

Large language models (LLMs) have fundamentally transformed artificial intelligence, catalyzing recent advancements while imposing substantial environmental and computational burdens. We introduce TRAWL (Tensor Reduced and Approximated Weights for Large Language Models), a novel methodology for optimizing LLMs through tensor decomposition. TRAWL leverages diverse strategies to exploit matrices within transformer-based architectures, realizing notable performance enhancements without necessitating retraining. The most significant improvements were observed through a layer-by-layer intervention strategy, particularly when applied to fully connected weights of the final layers, yielding up to 16% enhancement in accuracy without the need for additional data or fine-tuning. These results underscore the importance of targeted and adaptive techniques in increasing the efficiency and effectiveness of large language model optimization, thereby promoting the development of more sustainable and accessible AI systems.

We propose a technique for decomposing the parameter learning problem in Bayesian networks into independent learning problems. Our technique applies to incomplete datasets and exploits variables that are either hidden or observed in the given dataset. We show empirically that the proposed technique can lead to orders-of-magnitude savings in learning time. We explain, analytically and empirically, the reasons behind our reported savings, and compare the proposed technique to related ones that are sometimes used by inference algorithms.

Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deploy on small battery-powered Internet-of-Things (IoT) devices with limited computing resources. Deployment of DNNs on Internet-of-Things devices, such as traffic cameras, can improve public safety by enabling applications such as automatic accident detection and emergency response.Through this paper, we survey the recent advances in low-power and energy-efficient DNN implementations that improve the deployability of DNNs without significantly sacrificing accuracy. In general, these techniques either reduce the memory requirements, the number of arithmetic operations, or both. The techniques can be divided into three major categories: neural network compression, network architecture search and design, and compiler and graph optimizations. In this paper, we survey both low-power techniques for both convolutional and transformer DNNs, and summarize the advantages, disadvantages, and open research problems.

Generating forecasts for time series with multiple seasonal cycles is an important use-case for many industries nowadays. Accounting for the multi-seasonal patterns becomes necessary to generate more accurate and meaningful forecasts in these contexts. In this paper, we propose Long Short-Term Memory Multi-Seasonal Net (LSTM-MSNet), a decompositionbased, unified prediction framework to forecast time series with multiple seasonal patterns. The current state of the art in this space are typically univariate methods, in which the model parameters of each time series are estimated independently. Consequently, these models are unable to include key patterns and structures that may be shared by a collection of time series. In contrast, LSTM-MSNet is a globally trained Long Short-Term Memory network (LSTM), where a single prediction model is built across all the available time series to exploit the crossseries knowledge in a group of related time series. Furthermore, our methodology combines a series of state-of-the-art multiseasonal decomposition techniques to supplement the LSTM learning procedure. In our experiments, we are able to show that on datasets from disparate data sources, like e.g. the popular M4 forecasting competition, a decomposition step is beneficial, whereas in the common real-world situation of homogeneous series from a single application, exogenous seasonal variables or no seasonal preprocessing at all are better choices. All options are readily included in the framework and allow us to achieve competitive results for both cases, outperforming many state-ofthe-art multi-seasonal forecasting methods

We evaluate how modern outlier detection methods perform in identifying outliers in e-commerce conversion rate data. Based on the limitations identified, we then present a novel method to detect outliers in e-commerce conversion rate. This unsupervised method is made more business relevant by letting it automatically adjust the sensitivity based on the activity observed on the e-commerce platform. We call this outlier detection method the fluid IQR. Using real e-commerce conversion data acquired from a known store, we compare the performance of the existing and the new outlier detection methods. Fluid IQR method outperforms the existing outlier detection methods by a large margin when it comes to business-relevance. Furthermore, the fluids IQR method is the most robust outlier detection method in the presence of clusters of extreme outliers or level shifts. Future research will evaluate how the fluid IQR method perform in diverse e-business settings.

We propose a technique for decomposing the parameter learning problem in Bayesian networks into independent learning problems. Our technique applies to incomplete datasets and exploits variables that are either hidden or observed in the given dataset. We show empirically that the proposed technique can lead to orders-of-magnitude savings in learning time. We explain, analytically and empirically, the reasons behind our reported savings, and compare the proposed technique to related ones that are sometimes used by inference algorithms.