相关论文: Enhancing Actuarial Non-Life Pricing Models via Tr…

Recent work in deep learning has opened new possibilities for solving classical algorithmic tasks using end-to-end learned models. In this work, we investigate the fundamental task of solving linear systems, particularly those that are…

The performance analytics domain in High Performance Computing (HPC) uses tabular data to solve regression problems, such as predicting the execution time. Existing Machine Learning (ML) techniques leverage the correlations among features…

Variational auto-encoder frameworks have demonstrated success in reducing complex nonlinear dynamics in molecular simulation to a single non-linear embedding. In this work, we illustrate how this non-linear latent embedding can be used as a…

Electric guitar tone modeling typically focuses on the non-linear transformation from clean to amplifier-rendered audio. Traditional methods rely on one-to-one mappings, incorporating device parameters into neural models to replicate…

To pricing health insurance plan, statisticians use mathematical models to predict customers' future health condition. General Addictive Model (GAM) is a wide accepted method for this problem. However, it have several limitations. To solve…

Fine-tuning pre-trained models provides significant advantages in downstream performance. The ubiquitous nature of pre-trained models such as BERT and its derivatives in natural language processing has also led to a proliferation of…

Many real-world problems can be naturally described by mathematical formulas. The task of finding formulas from a set of observed inputs and outputs is called symbolic regression. Recently, neural networks have been applied to symbolic…

Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between weights, which can be problematic when there are insufficient…

Region proposal based methods like R-CNN and Faster R-CNN models have proven to be extremely successful in object detection and segmentation tasks. Recently, Transformers have also gained popularity in the domain of Computer Vision, and are…

To analyze the scaling potential of deep tabular representation learning models, we introduce a novel Transformer-based architecture specifically tailored to tabular data and cross-table representation learning by utilizing table-specific…

Enhancing the existing solution for pricing of fixed income instruments within Black-Karasinski model structure, with neural network at various parameterisation points to demonstrate that the method is able to achieve superior outcomes for…

This article introduces a nonlinear generalized matrix factor model (GMFM) that allows for mixed-type variables, extending the scope of linear matrix factor models (LMFM) that are so far limited to handling continuous variables. We…

We propose an adaptation method for factorized neural transducers (FNT) with external language models. We demonstrate that both neural and n-gram external LMs add significantly more value when linearly interpolated with predictor output…

Deep neural networks have revolutionized many fields, but their black-box nature also occasionally prevents their wider adoption in fields such as healthcare and finance, where interpretable and explainable models are required. The recent…

This paper studies the prediction task of tensor-on-tensor regression in which both covariates and responses are multi-dimensional arrays (a.k.a., tensors) across time with arbitrary tensor order and data dimension. Existing methods either…

Graphs are pervasive in the real-world, such as social network analysis, bioinformatics, and knowledge graphs. Graph neural networks (GNNs) have great ability in node classification, a fundamental task on graphs. Unfortunately, conventional…

Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole,…

Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a…

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

Remaining useful life prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the…