53 skills found · Page 1 of 2
taichi-dev / TaichiProductive, portable, and performant GPU programming in Python.
casadi / CasadiCasADi is a symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrix-valued computational graphs. It supports self-contained C-code generation and interfaces state-of-the-art codes such as SUNDIALS, IPOPT etc. It can be used from C++, Python or Matlab/Octave.
dcmocanu / Sparse Evolutionary Artificial Neural NetworksAlways sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).
JuliaDiff / SparseDiffTools.jlFast jacobian computation through sparsity exploitation and matrix coloring
Tencent-Hunyuan / Flex Block Attnflex-block-attn: an efficient block sparse attention computation library
EBD-CREST / NsparseSparse matrix computation library for GPU
livey / GAMP SBLComputationally Efficient Sparse Bayesian Learning via Generalized Approximate Message Passing
YukeWang96 / TC GNN ATC23Artifact for USENIX ATC'23: TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs.
willcrichton / Corrset BenchmarkA repository to test different performance optimizations in a sparse matrix computation.
alexcaselli / Federated Learning For Human Mobility ModelsThanks to the proliferation of smart devices, such as smartphones and wearables, which are equipped with computation, communication and sensing capabilities, a plethora of new location-based services and applications are available for the users at any time and everywhere. Understanding human mobility has gain importance to offer better services able to provide valuable products to the user whenever it's required. The ability to predict when and where individuals will go next allows enabling smart recommendation systems or a better organization of resources such as public transport vehicles or taxis. Network providers can predict future activities of individuals and groups to optimize network handovers, while transport systems can provide more vehicles or lines where required, reducing waiting time and discomfort to their clients. The representation of the movements of individuals or groups of mobile entities are called human mobility models. Such models replicate real human mobility characteristics, enabling to simulate movements of different individuals and infer their future whereabouts. The development of these models requires to collect in a centralized location, as a server, the information related to the users' locations. Such data represents sensitive information, and the collection of those threatens the privacy of the users involved. The recent introduction of federated learning, a privacy-preserving approach to build machine and deep learning models, represents a promising technique to solve the privacy issue. Federated learning allows mobile devices to contribute with their private data to the model creation without sharing them with a centralized server. In this thesis, we investigate the application of the federated learning paradigm to the field of human mobility modelling. Using three different mobility datasets, we first designed and developed a robust human mobility model by investigating different classes of neural networks and the influence of demographic data over models' performance. Second, we applied federated learning to create a human mobility model based on deep learning which does not require the collection of users' mobility traces, achieving promising results on two different datasets. Users' data remains so distributed over the big number of devices which have generated them, while the model is shared and trained among the server and the devices. Furthermore, the developed federated model has been the subject of different analyses including: the effects of sparse availability of the clients; The communication costs required by federated settings; The application of transfer-learning techniques and model refinement through federated learning and, lastly, the influence of differential privacy on the model’s prediction performance, also called utility
gridap / SparseMatricesCSR.jlSparse matrices in CSR format for Julia computations
ParCIS / FlashSparseFlashSparse significantly reduces the computation redundancy for unstructured sparsity (for SpMM and SDDMM) on Tensor Cores through a Swap-and-Transpose mapping strategy. FlashSparse is accepted by PPoPP 2025.
SparseLinearAlgebra / SplaAn open-source generalized sparse linear algebra library with vendor-agnostic GPUs accelerated computations
metinaktas / Acoustic Direction Finding Using Single Acoustic Vector Sensor Under High ReverberationWe propose a novel and robust method for acoustic direction finding, which is solely based on acoustic pressure and pressure gradient measurements from single Acoustic Vector Sensor (AVS). We do not make any stochastic and sparseness assumptions regarding the signal source and the environmental characteristics. Hence, our method can be applied to a wide range of wideband acoustic signals including the speech and noise-like signals in various environments. Our method identifies the “clean” time frequency bins that are not distorted by multipath signals and noise, and estimates the 2D-DOA angles at only those identified bins. Moreover, the identification of the clean bins and the corresponding DOA estimation are performed jointly in one framework in a computationally highly efficient manner. We mathematically and experimentally show that the false detection rate of the proposed method is zero, i.e., none of the time-frequency bins with multiple sources are wrongly labeled as single-source, when the source directions do not coincide. Therefore, our method is significantly more reliable and robust compared to the competing state-of-the-art methods that perform the time-frequency bin selection and the DOA estimation separately. The proposed method, for performed simulations, estimates the source direction with high accuracy (less than 1 degree error) even under significantly high reverberation conditions.
LijunChang / Cohesive Subgraph BookCode for monograph "Cohesive Subgraph Computation over Large Sparse Graphs"
LijunChang / MC BRBMaximum clique computation over large sparse graphs
WayneDW / Parallel Solvers For Linear SystemParallel Solver for Large-Scale Sparse Matrix Computations (MPI)
Jittor / JSparseJSparse is a high-performance auto-differentiation library for sparse voxels computation and point cloud processing based on TorchSparse and Jittor.
SparseLinearAlgebra / SpblaSparse Boolean linear algebra for Nvidia Cuda, OpenCL and CPU computations
mikebianco / Locally Sparse TomographyLocally sparse travel time tomography (LST) is a tomography algorithm which uses sparse modeling and dictionary learning to estimate 2D geophysical images based on wave travel times across sensor arrays. This repository is an implementation of the IEEE paper: M.J. Bianco and P. Gerstoft, "Travel time tomography with adaptive dictionaries," IEEE Trans. on Computational Imaging, Vol. 4, No. 4, 2018.
