Search Results for author:
Found 7 papers, 0 papers with code
Linear Codes for Hyperdimensional Computing
One of the long-standing challenges in HDC is factoring a compositional representation to its constituent factors, also known as the recovery problem.
Beyond PCA: A Probabilistic Gram-Schmidt Approach to Feature Extraction
Specifically, by applying the GS process over a family of functions which presumably captures the nonlinear dependencies in the data, we construct a series of covariance matrices that can either be used to identify new large-variance directions, or to remove those dependencies from the principal components.
Enhancing Robustness of Neural Networks through Fourier Stabilization
The choice of which neurons to stabilize in a neural network is then a combinatorial optimization problem, and we propose several methods for approximately solving it.
CodNN -- Robust Neural Networks From Coded Classification
By our approach, either the data or internal layers of the DNN are coded with error correcting codes, and successful computation under noise is guaranteed.
What is the Value of Data? On Mathematical Methods for Data Quality Estimation
Data is one of the most important assets of the information age, and its societal impact is undisputed.
Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy
We consider a scenario involving computations over a massive dataset stored distributedly across multiple workers, which is at the core of distributed learning algorithms.
Gradient Coding from Cyclic MDS Codes and Expander Graphs
Gradient coding is a technique for straggler mitigation in distributed learning.
