Wei Zhang

Affiliations:
  • IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA
  • University of Wisconsin-Madison, WI, USA (PhD 2013)


According to our database1, Wei Zhang authored at least 46 papers between 2005 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2023
Activity-weight duality in feed-forward neural networks reveals two co-determinants for generalization.
Nat. Mac. Intell., August, 2023

Soft Random Sampling: A Theoretical and Empirical Analysis.
CoRR, 2023

2022
Robustness to Unbounded Smoothness of Generalized SignSGD.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
Asynchronous Decentralized Distributed Training of Acoustic Models.
IEEE ACM Trans. Audio Speech Lang. Process., 2021

Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent.
CoRR, 2021

Project CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks.
CoRR, 2021

CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

4-Bit Quantization of LSTM-Based Speech Recognition Models.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

2020
Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition: A comparison of current training strategies.
IEEE Signal Process. Mag., 2020

Change Detection from Remote Sensing to Guide OpenStreetMap Labeling.
ISPRS Int. J. Geo Inf., 2020

Adam<sup>+</sup>: A Stochastic Method with Adaptive Variance Reduction.
CoRR, 2020

Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition.
CoRR, 2020

A Decentralized Parallel Algorithm for Training Generative Adversarial Nets.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Map Generation from Large Scale Incomplete and Inaccurate Data Labels.
Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets.
Proceedings of the 8th International Conference on Learning Representations, 2020

Improving Efficiency in Large-Scale Decentralized Distributed Training.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
Decentralized Parallel Algorithm for Training Generative Adversarial Nets.
CoRR, 2019

Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Highly Efficient Distributed Deep Learning System for Automatic Speech Recognition.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition.
Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Distributed Deep Learning Strategies for Automatic Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2019

2018
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Asynchronous Decentralized Parallel Stochastic Gradient Descent.
Proceedings of the 35th International Conference on Machine Learning, 2018

Forecast of Solar Energy Production - A Deep Learning Approach.
Proceedings of the 2018 IEEE International Conference on Big Knowledge, 2018

2017
Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Model Accuracy and Runtime Tradeoff in Distributed Deep Learning: A Systematic Study.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Accelerator Design for Deep Learning Training: Extended Abstract: Invited.
Proceedings of the 54th Annual Design Automation Conference, 2017

2016
X10 and APGAS at Petascale.
ACM Trans. Parallel Comput., 2016

META: Middleware for Events, Transactions, and Analytics.
IBM J. Res. Dev., 2016

Staleness-Aware Async-SGD for Distributed Deep Learning.
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

AQuA: adaptive quality analytics.
Proceedings of the 10th ACM International Conference on Distributed and Event-based Systems, 2016

2015
Model Accuracy and Runtime Tradeoff in Distributed Deep Learning.
CoRR, 2015

Fixing, preventing, and recovering from concurrency bugs.
Sci. China Inf. Sci., 2015

2014
GLB: lifeline-based global load balancing library in x10.
Proceedings of the first workshop on Parallel programming for analytics applications, 2014

2013
ConMem: Detecting Crash-Triggering Concurrency Bugs through an Effect-Oriented Approach.
ACM Trans. Softw. Eng. Methodol., 2013

Efficient concurrency-bug detection across inputs.
Proceedings of the 2013 ACM SIGPLAN International Conference on Object Oriented Programming Systems Languages & Applications, 2013

ConAir: featherweight concurrency bug recovery via single-threaded idempotent execution.
Proceedings of the Architectural Support for Programming Languages and Operating Systems, 2013

2012
Automated Concurrency-Bug Fixing.
Proceedings of the 10th USENIX Symposium on Operating Systems Design and Implementation, 2012

Understanding the Interleaving-Space Overlap across Inputs and Software Versions.
Proceedings of the 4th USENIX Workshop on Hot Topics in Parallelism, 2012

2011
Automated atomicity-violation fixing.
Proceedings of the 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation, 2011

ConSeq: detecting concurrency bugs through sequential errors.
Proceedings of the 16th International Conference on Architectural Support for Programming Languages and Operating Systems, 2011

2010
Applying scalable phonetic context similarity in unit selection of concatenative text-to-speech.
Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

ConMem: detecting severe concurrency bugs through an effect-oriented approach.
Proceedings of the 15th International Conference on Architectural Support for Programming Languages and Operating Systems, 2010

2008
Developing high performance asr in the IBM multilingual speech-to-speech translation system.
Proceedings of the IEEE International Conference on Acoustics, 2008

2005
Toward multiple-language TTS: experiments in English and Mandarin.
Proceedings of the 9th European Conference on Speech Communication and Technology, 2005


  Loading...