research
∙
05/11/2023
Computing Unique Information for Poisson and Multinomial Systems
Bivariate Partial Information Decomposition (PID) describes how the mutu...
share
research
∙
11/19/2022
PATHFINDER: Designing Stimuli for Neuromodulation through data-driven inverse estimation of non-linear functions
There has been tremendous interest in designing stimuli (e.g. electrical...
research
∙
10/26/2022
Extracting Unique Information Through Markov Relations
We propose two new measures for extracting the unique information in X a...
research
∙
06/16/2022
Quantifying Feature Contributions to Overall Disparity Using Information Theory
When a machine-learning algorithm makes biased decisions, it can be help...
research
∙
11/09/2021
Can Information Flows Suggest Targets for Interventions in Neural Circuits?
Motivated by neuroscientific and clinical applications, we empirically e...
research
∙
10/02/2021
A Minimal Intervention Definition of Reverse Engineering a Neural Circuit
In neuroscience, researchers have developed informal notions of what it ...
research
∙
06/14/2020
Fairness Under Feature Exemptions: Counterfactual and Observational Measures
With the growing use of AI in highly consequential domains, the quantifi...
research
∙
03/04/2019
CodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors
This work proposes the first strategy to make distributed training of ne...
research
∙
02/06/2019
Information Flow in Computational Systems
We develop a theoretical framework for defining and identifying flows of...
research
∙
12/16/2018
Coded Elastic Computing
Cloud providers have recently introduced low-priority machines to reduce...
research
∙
11/28/2018
An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation
We propose a novel application of coded computing to the problem of the ...
research
∙
11/27/2018
A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication
This paper has two contributions. First, we propose a novel coded matrix...
research
∙
06/15/2018
Straggler-Resilient and Communication-Efficient Distributed Iterative Linear Solver
We propose a novel distributed iterative linear inverse solver method. O...
research
∙
05/24/2018
Coded FFT and Its Communication Overhead
We propose a coded computing strategy and examine communication costs of...
research
∙
05/15/2018
Coded Iterative Computing using Substitute Decoding
In this paper, we propose a new coded computing technique called "substi...
research
∙
01/31/2018