Search Results for author:
Found 10 papers, 3 papers with code
Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale
We share in this paper our search strategies to adapt reference recommendation models to low-precision hardware, our optimization of low-precision compute kernels, and the design and development of tool chain so as to maintain our models' accuracy throughout their lifespan during which topic trends and users' interests inevitably evolve.
Mixed-Precision Embedding Using a Cache
We propose a novel change to embedding tables using a cache memory architecture, where the majority of rows in an embedding is trained in low precision, and the most frequently or recently accessed rows cached and trained in full precision.
Training Recommender Systems at Scale: Communication-Efficient Model and Data Parallelism
This is done by identifying and updating only the most relevant neurons of the neural network for each training sample in the data.
Sparse Dictionary Learning by Dynamical Neural Networks
A dynamical neural network consists of a set of interconnected neurons that interact over time continuously.
Dictionary Learning by Dynamical Neural Networks
A dynamical neural network consists of a set of interconnected neurons that interact over time continuously.
A Progressive Batching L-BFGS Method for Machine Learning
The standard L-BFGS method relies on gradient approximations that are not dominated by noise, so that search directions are descent directions, the line search is reliable, and quasi-Newton updating yields useful quadratic models of the objective function.
Sparse Coding by Spiking Neural Networks: Convergence Theory and Computational Results
With a moderate but well-defined assumption, we prove that the SNN indeed solves sparse coding.
Enabling Sparse Winograd Convolution by Native Pruning
Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs.
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks.
Faster CNNs with Direct Sparse Convolutions and Guided Pruning
Pruning CNNs in a way that increase inference speed often imposes specific sparsity structures, thus limiting the achievable sparsity levels.
