Related papers: DeepRWCap: Neural-Guided Random-Walk Capacitance S…
The accuracy of floating-random-walk (FRW) based capacitance extraction stands only when the recursive FRW transitions are sampled unbiasedly according to surrounding dielectrics. Advanced technology profiles, featuring complicated…
As random walk is a powerful tool in many graph processing, mining and learning applications, this paper proposes an efficient in-memory random walk engine named ThunderRW. Compared with existing parallel systems on improving the…
We briefly review the principles, mathematical bases, numerical shortcuts and applications of fast random walk (FRW) algorithms. This Monte Carlo technique allows one to simulate individual trajectories of diffusing particles in order to…
Graph Random Walks (GRWs) offer efficient approximations of key graph properties and have been widely adopted in many applications. However, GRW workloads are notoriously difficult to accelerate due to their strong data dependencies,…
Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with…
Dynamic graph random walk (DGRW) emerges as a practical tool for capturing structural relations within a graph. Effectively executing DGRW on GPU presents certain challenges. First, existing sampling methods demand a pre-processing buffer,…
The reliable deployment of deep learning in medical imaging requires uncertainty quantification that provides rigorous error guarantees while remaining anatomically meaningful. Conformal prediction (CP) is a powerful distribution-free…
Graph kernels used to be the dominant approach to feature engineering for structured data, which are superseded by modern GNNs as the former lacks learnability. Recently, a suite of Kernel Convolution Networks (KCNs) successfully…
The study of quasar light curves poses two problems: inference of the power spectrum and interpolation of an irregularly sampled time series. A baseline approach to these tasks is to interpolate a time series with a Damped Random Walk (DRW)…
We consider random walks on discrete state spaces, such as general undirected graphs, where the random walkers are designed to approximate a target quantity over the network topology via sampling and neighborhood exploration in the form of…
Dynamic random walks are fundamental to various graph analysis applications, offering advantages by adapting to evolving graph properties. Their runtime-dependent transition probabilities break down the pre-computation strategy that…
Relaxed random walk (RRW) models of trait evolution introduce branch-specific rate multipliers to modulate the variance of a standard Brownian diffusion process along a phylogeny and more accurately model overdispersed biological data.…
Current digital computers are about to hit basic physical boundaries with respect to integration density, clock frequencies, and particularly energy consumption. This requires the application of new computing paradigms, such as quantum and…
We present a graph random walk (GRW) method for the study of charge transport properties of complex molecular materials in the time-of-flight regime. The molecules forming the material are represented by the vertices of a directed weighted…
We introduce a set of techniques that allow for efficiently generating many independent random walks in the Massive Parallel Computation (MPC) model with space per machine strongly sublinear in the number of vertices. In this…
Random walk sampling methods have been widely used in graph sampling in recent years, while it has bias towards higher degree nodes in the sample. To overcome this deficiency, classical methods such as MHRW design weighted walking by…
Computing stands to be radically improved by neuromorphic computing (NMC) approaches inspired by the brain's incredible efficiency and capabilities. Most NMC research, which aims to replicate the brain's computational structure and…
Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a triangular mesh -…
Monte Carlo path tracer renders noisy image sequences at low sampling counts. Although great progress has been made on denoising such sequences, existing methods still suffer from spatial and temporary artifacts. In this paper, we tackle…
Graph dynamic random walks (GDRWs) have recently emerged as a powerful paradigm for graph analytics and learning applications, including graph embedding and graph neural networks. Despite the fact that many existing studies optimize the…