Sewoong Oh

Sewoong Oh

University of Washington

H-index: 44

North America-United States

About Sewoong Oh

Sewoong Oh, With an exceptional h-index of 44 and a recent h-index of 39 (since 2020), a distinguished researcher at University of Washington, specializes in the field of Machine Learning, Privacy.

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

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares

On the Convergence of Differentially-Private Fine-tuning: To Linearly Probe or to Fully Fine-tune?

Privacy-Preserving Instructions for Aligning Large Language Models

DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning

A learned score function improves the power of mass spectrometry database search

Advancing differential privacy: Where we are now and future directions for real-world deployment

Can Public Large Language Models Help Private Cross-device Federated Learning?

DataComp: In search of the next generation of multimodal datasets

Sewoong Oh Information

University

Position

Paul G. Allen School of Computer Science and Engineering

Citations(all)

11197

Citations(since 2020)

7297

Cited By

6867

hIndex(all)

44

hIndex(since 2020)

39

i10Index(all)

95

i10Index(since 2020)

78

Email

University Profile Page

Google Scholar

Sewoong Oh Skills & Research Interests

Machine Learning

Privacy

Top articles of Sewoong Oh

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares

arXiv preprint arXiv:2404.15409

2024/4/23

On the Convergence of Differentially-Private Fine-tuning: To Linearly Probe or to Fully Fine-tune?

arXiv preprint arXiv:2402.18905

2024/2/29

Giulia Fanti
Giulia Fanti

H-Index: 21

Sewoong Oh
Sewoong Oh

H-Index: 32

Privacy-Preserving Instructions for Aligning Large Language Models

arXiv preprint arXiv:2402.13659

2024/2/21

DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning

arXiv preprint arXiv:2402.08864

2024/2/14

Sewoong Oh
Sewoong Oh

H-Index: 32

Pramod Viswanath
Pramod Viswanath

H-Index: 33

A learned score function improves the power of mass spectrometry database search

bioRxiv

2024/1/30

Can Public Large Language Models Help Private Cross-device Federated Learning?

arXiv preprint arXiv:2305.12132

2023/5/20

Why Is Public Pretraining Necessary for Private Model Training?

2023/7/3

One-shot empirical privacy estimation for federated learning

arXiv preprint arXiv:2302.03098

2023/2/6

Sewoong Oh
Sewoong Oh

H-Index: 32

Alina Oprea
Alina Oprea

H-Index: 27

Sequence-to-sequence translation from mass spectra to peptides with a transformer model

BioRxiv

2023/1/3

Learning to generate image embeddings with user-level differential privacy

2023

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency

Advances in Neural Information Processing Systems

2024/2/13

Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks

Advances in Neural Information Processing Systems

2024/2/13

Arun Ganesh
Arun Ganesh

H-Index: 2

Sewoong Oh
Sewoong Oh

H-Index: 32

Label Poisoning is All You Need

NeurIPS 2023

2023/10/29

Sewoong Oh
Sewoong Oh

H-Index: 32

Evaluating proteomics imputation methods with improved criteria

Journal of Proteome Research

2023/10/20

Sewoong Oh
Sewoong Oh

H-Index: 32

DPzero: Dimension-independent and differentially private zeroth-order optimization

arXiv preprint arXiv:2310.09639

2023/10/14

Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning

arXiv preprint arXiv:2310.04627

2023/10/6

Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes

IEEE Journal on Selected Areas in Information Theory

2023/7/25

On the Connection between Pre-training Data Diversity and Fine-tuning Robustness

Advances in Neural Information Processing Systems

2024/2/13

See List of Professors in Sewoong Oh University(University of Washington)

Co-Authors

academic-engine