Alert button
Picture for Sewoong Oh

Sewoong Oh

Alert button

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

May 20, 2023
Boxin Wang, Yibo Jacky Zhang, Yuan Cao, Bo Li, H. Brendan McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer

Figure 1 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 2 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 3 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 4 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Viaarxiv icon

DataComp: In search of the next generation of multimodal datasets

May 03, 2023
Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt

Figure 1 for DataComp: In search of the next generation of multimodal datasets
Figure 2 for DataComp: In search of the next generation of multimodal datasets
Figure 3 for DataComp: In search of the next generation of multimodal datasets
Figure 4 for DataComp: In search of the next generation of multimodal datasets
Viaarxiv icon

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

Feb 20, 2023
Arun Ganesh, Daogao Liu, Sewoong Oh, Abhradeep Thakurta

Figure 1 for Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Figure 2 for Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Figure 3 for Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Viaarxiv icon

Why Is Public Pretraining Necessary for Private Model Training?

Feb 19, 2023
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang

Figure 1 for Why Is Public Pretraining Necessary for Private Model Training?
Figure 2 for Why Is Public Pretraining Necessary for Private Model Training?
Figure 3 for Why Is Public Pretraining Necessary for Private Model Training?
Figure 4 for Why Is Public Pretraining Necessary for Private Model Training?
Viaarxiv icon

One-shot Empirical Privacy Estimation for Federated Learning

Feb 08, 2023
Galen Andrew, Peter Kairouz, Sewoong Oh, Alina Oprea, H. Brendan McMahan, Vinith Suriyakumar

Figure 1 for One-shot Empirical Privacy Estimation for Federated Learning
Figure 2 for One-shot Empirical Privacy Estimation for Federated Learning
Figure 3 for One-shot Empirical Privacy Estimation for Federated Learning
Figure 4 for One-shot Empirical Privacy Estimation for Federated Learning
Viaarxiv icon

Near Optimal Private and Robust Linear Regression

Jan 30, 2023
Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Sai Suggala

Figure 1 for Near Optimal Private and Robust Linear Regression
Figure 2 for Near Optimal Private and Robust Linear Regression
Figure 3 for Near Optimal Private and Robust Linear Regression
Figure 4 for Near Optimal Private and Robust Linear Regression
Viaarxiv icon

Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes

Jan 16, 2023
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath

Figure 1 for Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Figure 2 for Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Figure 3 for Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Figure 4 for Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Viaarxiv icon

MAUVE Scores for Generative Models: Theory and Practice

Dec 30, 2022
Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck, Swabha Swayamdipta, Rowan Zellers, Sewoong Oh, Yejin Choi, Zaid Harchaoui

Figure 1 for MAUVE Scores for Generative Models: Theory and Practice
Figure 2 for MAUVE Scores for Generative Models: Theory and Practice
Figure 3 for MAUVE Scores for Generative Models: Theory and Practice
Figure 4 for MAUVE Scores for Generative Models: Theory and Practice
Viaarxiv icon

Learning to Generate Image Embeddings with User-level Differential Privacy

Nov 20, 2022
Zheng Xu, Maxwell Collins, Yuxiao Wang, Liviu Panait, Sewoong Oh, Sean Augenstein, Ting Liu, Florian Schroff, H. Brendan McMahan

Figure 1 for Learning to Generate Image Embeddings with User-level Differential Privacy
Figure 2 for Learning to Generate Image Embeddings with User-level Differential Privacy
Figure 3 for Learning to Generate Image Embeddings with User-level Differential Privacy
Figure 4 for Learning to Generate Image Embeddings with User-level Differential Privacy
Viaarxiv icon