Related papers: ANPP: the Adapted Normalized Power Prior for Borro…
Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy…
In the field of computational physics and material science, the efficient sampling of rare events occurring at atomic scale is crucial. It aids in understanding mechanisms behind a wide range of important phenomena, including protein…
Hidden Markov model (HMM) has been successfully used for sequential data modeling problems. In this work, we propose to power the modeling capacity of HMM by bringing in neural network based generative models. The proposed model is termed…
To enable DNNs on edge devices like mobile phones, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a…
Architecture-based Performance Prediction (AbPP) allows evaluation of the performance of systems and to answer what-if questions without measurements for all alternatives. A difficulty when creating models is that Performance Model…
Time series analysis has become increasingly important in various domains, and developing effective models relies heavily on high-quality benchmark datasets. Inspired by the success of Natural Language Processing (NLP) benchmark datasets in…
We study prediction of future outcomes with supervised models that use privileged information during learning. The privileged information comprises samples of time series observed between the baseline time of prediction and the future…
This article addresses issues of model criticism and model comparison in Bayesian contexts, and focusses on the use of the so-called posterior predictive p-values (ppp values). These involve a general discrepancy or conflict measure and…
Deep neural networks can be fooled by adversarial attacks: adding carefully computed small adversarial perturbations to clean inputs can cause misclassification on state-of-the-art machine learning models. The reason is that neural networks…
In this work, we introduce a learning model designed to meet the needs of applications in which computational resources are limited, and robustness and interpretability are prioritized. Learning problems can be formulated as constrained…
Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a…
We study the problem of learning shared structure \emph{across} a sequence of dynamic pricing experiments for related products. We consider a practical formulation where the unknown demand parameters for each product come from an unknown…
Test Case Prioritization (TCP) techniques aim at proposing new test case execution orders to favor the achievement of certain testing goal, such as fault detection. Current TCP research focus mainly on code-based regression testing; however…
Inferring the parameters of a stochastic model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e. when distinct sets of parameters…
Distributed training of deep neural networks has received significant research interest, and its major approaches include implementations on multiple GPUs and clusters. Parallelization can dramatically improve the efficiency of training…
Conditional Neural Processes~(CNPs) formulate distributions over functions and generate function observations with exact conditional likelihoods. CNPs, however, have limited expressivity for high-dimensional observations, since their…
The widespread availability of large public datasets is a key factor behind the recent successes of statistical inference and machine learning methods. However, these datasets often contain some low-quality or contaminated data, to which…
Deep learning models face persistent challenges in training, particularly due to internal covariate shift and label shift. While single-mode normalization methods like Batch Normalization partially address these issues, they are constrained…
Data parallelism has emerged as a necessary technique to accelerate the training of deep neural networks (DNN). In a typical data parallelism approach, the local workers push the latest updates of all the parameters to the parameter server…
There is growing interest in Bayesian clinical trial designs with informative prior distributions, e.g. for extrapolation of adult data to pediatrics, or use of external controls. While the classical type I error is commonly used to…