36 citations · 90 across the 10 of their papers we have counts for
13 papers
FastFill: Efficient Compatible Model Update
Florian Jaeckle, Fartash Faghri, Ali Farhadi +2
In many retrieval systems the original high dimensional data (e.g., images) is mapped to a lower dimensional feature through a learned embedding model. The task of retrieving the m…
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
Fartash Faghri, Hadi Pouransari, Sachin Mehta +4
We propose Dataset Reinforcement, a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no addition…
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
Vivek Ramanujan, Pavan Kumar Anasosalu Vasu, Ali Farhadi +2
In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the…
Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution
Hadi Pouransari, Mojan Javaheripi, Vinay Sharma +1
Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model…
Least squares binary quantization of neural networks
Hadi Pouransari, Zhucheng Tu, Oncel Tuzel
Quantizing weights and activations of deep neural networks results in significant improvement in inference efficiency at the cost of lower accuracy. A source of the accuracy gap be…
Democratizing Production-Scale Distributed Deep Learning
Minghuang Ma, Hadi Pouransari, Daniel Chao +5
The interest and demand for training deep neural networks have been experiencing rapid growth, spanning a wide range of applications in both academia and industry. However, trainin…
A distributed-memory hierarchical solver for general sparse linear systems
Chao Chen, Hadi Pouransari, Sivasankaran Rajamanickam +2
We present a parallel hierarchical solver for general sparse linear systems on distributed-memory machines. For large-scale problems, this fully algebraic algorithm is faster and m…
Particle-to-fluid heat transfer in particle-laden turbulence
Hadi Pouransari, Ali Mani
Preferential concentration of inertial particles by turbulence is a well recognized phenomenon. This study investigates how this phenomenon impacts the mean heat transfer between t…
Sparse Hierarchical Solvers with Guaranteed Convergence
Kai Yang, Hadi Pouransari, Eric Darve
Solving sparse linear systems from discretized PDEs is challenging. Direct solvers have in many cases quadratic complexity (depending on geometry), while iterative solvers require…
Parallel variable-density particle-laden turbulence simulation
Hadi Pouransari, Milad Mortazavi, Ali Mani
We have developed a fully parallel C++/MPI based simulation code for variable-density particle-laden turbulent flows. The fluid is represented through a uniform Eulerian staggered…
Fast hierarchical solvers for sparse matrices using extended sparsification and low-rank approximation
Hadi Pouransari, Pieter Coulier, Eric Darve
Inversion of sparse matrices with standard direct solve schemes is robust, but computationally expensive. Iterative solvers, on the other hand, demonstrate better scalability; but,…
Optimizing the adaptive fast multipole method for fractal sets
Hadi Pouransari, Eric Darve
We have performed a detailed analysis of the fast multipole method (FMM) in the adaptive case, in which the depth of the FMM tree is non-uniform. Previous works in this area have f…
The inverse fast multipole method: using a fast approximate direct solver as a preconditioner for dense linear systems
Pieter Coulier, Hadi Pouransari, Eric Darve
Although some preconditioners are available for solving dense linear systems, there are still many matrices for which preconditioners are lacking, in particular in cases where the…