Search Results - "Hernandez, Eduin E."

RoboTwin Metaverse Platform for Robotic Random Bin Picking by Tsai, Cheng-Han, Hernandez, Eduin E., You, Xiu-Wen, Lin, Hsin-Yi, Chang, Jen-Yuan

“…Although vision-guided robotic picking systems are commonly used in factory environments, achieving rapid changeover for diverse workpiece types can still be…”
Get full text

Straggler Mitigation Through Unequal Error Protection for Distributed Approximate Matrix Multiplication by Tegin, Busra, Hernandez, Eduin E., Rini, Stefano, Duman, Tolga M.

“…Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing. The time required for…”
Get full text

DNN gradient lossless compression: Can GenNorm be the answer? by Chen, Zhong-Jing, Hernandez, Eduin E., Huang, Yu-Chih, Rini, Stefano

“…In this paper, the problem of optimal gradient lossless compression in Deep Neural Network (DNN) training is considered. Gradient compression is relevant in…”
Get full text

Straggler Mitigation through Unequal Error Protection for Distributed Matrix Multiplication by Tegin, Busra, Hernandez, Eduin E., Rini, Stefano, Duman, Tolga M.

“…Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing. The time required for…”
Get full text

Communication-Efficient Federated DNN Training: Convert, Compress, Correct by Chen, Zhong-Jing, Hernandez, Eduin E., Huang, Yu-Chih, Rini, Stefano

“…In the federated training of a Deep Neural Network (DNN), model updates are transmitted from the remote users to the Parameter Server (PS). In many scenarios…”
Get full text

Speeding-Up Back-Propagation in DNN: Approximate Outer Product with Memory by Hernandez, Eduin E, Rini, Stefano, Duman, Tolga M

“…In this paper, an algorithm for approximate evaluation of back-propagation in DNN training is considered, which we term Approximate Outer Product Gradient…”
Get full text

Straggler Mitigation through Unequal Error Protection for Distributed Approximate Matrix Multiplication by Tegin, Busra, Hernandez, Eduin. E, Rini, Stefano, Duman, Tolga M

“…Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing. The time required for…”
Get full text

Straggler Mitigation through Unequal Error Protection for Distributed Matrix Multiplication by Tegin, Busra, Hernandez, Eduin E, Rini, Stefano, Duman, Tolga M

“…Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing. The time required for…”
Get full text

How to Attain Communication-Efficient DNN Training? Convert, Compress, Correct by Chen, Zhong-Jing, Hernandez, Eduin E, Huang, Yu-Chih, Rini, Stefano

“…This paper introduces CO3 -- an algorithm for communication-efficient federated Deep Neural Network (DNN) training. CO3 takes its name from three processing…”
Get full text

Convert, compress, correct: Three steps toward communication-efficient DNN training by Chen, Zhong-Jing, Hernandez, Eduin E, Huang, Yu-Chih, Rini, Stefano

“…In this paper, we introduce a novel algorithm, $\mathsf{CO}_3$, for communication-efficiency distributed Deep Neural Network (DNN) training. $\mathsf{CO}_3$ is…”
Get full text

DNN gradient lossless compression: Can GenNorm be the answer? by Chen, Zhong-Jing, Hernandez, Eduin E, Huang, Yu-Chih, Rini, Stefano

“…In this paper, the problem of optimal gradient lossless compression in Deep Neural Network (DNN) training is considered. Gradient compression is relevant in…”
Get full text