Hanlin Tang

Hanlin Tang

University of Rochester

H-index: 8

North America-United States

About Hanlin Tang

Hanlin Tang, With an exceptional h-index of 8 and a recent h-index of 8 (since 2020), a distinguished researcher at University of Rochester, specializes in the field of Machine learning, Optimization, Distributed Learning.

His recent articles reflect a diverse array of research interests and contributions to the field:

Easyquant: An efficient data-free quantization algorithm for llms

1-bit LAMB: communication efficient large-scale large-batch training with LAMB’s convergence speed

Mkq-bert: Quantized bert with 4-bits weights and activations

ErrorCompensatedX: error compensation for variance reduced algorithms

PASTO: Strategic Parameter Optimization in Recommendation Systems--Probabilistic is Better than Deterministic

1-bit adam: Communication efficient large-scale training with adam’s convergence speed

Communication Efficient Machine Learning

Apmsqueeze: A communication efficient adam-preconditioned momentum sgd algorithm

Hanlin Tang Information

University

Position

___

Citations(all)

1084

Citations(since 2020)

1072

Cited By

368

hIndex(all)

8

hIndex(since 2020)

8

i10Index(all)

8

i10Index(since 2020)

8

Email

University Profile Page

Google Scholar

Hanlin Tang Skills & Research Interests

Machine learning

Optimization

Distributed Learning

Top articles of Hanlin Tang

Easyquant: An efficient data-free quantization algorithm for llms

arXiv preprint arXiv:2403.02775

2024/3/5

Hanlin Tang
Hanlin Tang

H-Index: 7

Kai Liu
Kai Liu

H-Index: 4

1-bit LAMB: communication efficient large-scale large-batch training with LAMB’s convergence speed

2022/12/18

Hanlin Tang
Hanlin Tang

H-Index: 7

Mkq-bert: Quantized bert with 4-bits weights and activations

arXiv preprint arXiv:2203.13483

2022/3/25

Hanlin Tang
Hanlin Tang

H-Index: 7

Kai Liu
Kai Liu

H-Index: 4

ErrorCompensatedX: error compensation for variance reduced algorithms

Advances in Neural Information Processing Systems

2021/12/6

PASTO: Strategic Parameter Optimization in Recommendation Systems--Probabilistic is Better than Deterministic

arXiv preprint arXiv:2108.09076

2021/8/20

1-bit adam: Communication efficient large-scale training with adam’s convergence speed

2021/7/1

Communication Efficient Machine Learning

2021

Hanlin Tang
Hanlin Tang

H-Index: 7

Apmsqueeze: A communication efficient adam-preconditioned momentum sgd algorithm

arXiv preprint arXiv:2008.11343

2020/8/26

See List of Professors in Hanlin Tang University(University of Rochester)

Co-Authors

academic-engine