Sewoong Oh

ORCID

Publication Activity (10 Years)

Years Active: 2008-2024
Publications (10 Years): 183

Top Venues

Publications

Wei-Ning Chen, Berivan Isik, Peter Kairouz, Albert No, Sewoong Oh, Zheng Xu
Mean Estimation under Streaming Differential Privacy. CoRR (2024)
Gavin Brown, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares. CoRR (2024)
Shuqi Ke, Charlie Hou, Giulia Fanti, Sewoong Oh
On the Convergence of Differentially-Private Fine-tuning: To Linearly Probe or to Fully Fine-tune? CoRR (2024)
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alexandros G. Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
DataComp-LM: In search of the next generation of training sets for language models. CoRR (2024)
Eugene Bagdasaryan, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage
Air Gap: Protecting Privacy-Conscious Conversational Agents. CoRR (2024)
S. Ashwin Hebbar, Sravan Kumar Ankireddy, Hyeji Kim, Sewoong Oh, Pramod Viswanath
DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning. CoRR (2024)
Da Yu, Peter Kairouz, Sewoong Oh, Zheng Xu
Privacy-Preserving Instructions for Aligning Large Language Models. CoRR (2024)
Anshul Nasery, Jonathan Hayase, Pang Wei Koh, Sewoong Oh
PLeaS - Merging Models with Permutations and Least Squares. CoRR (2024)
Gavin Brown, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended Abstract. COLT (2024)
Jonathan Hayase, Alisa Liu, Yejin Choi, Sewoong Oh, Noah A. Smith
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data? CoRR (2024)
Thao Nguyen, Matthew Wallingford, Sebastin Santy, Wei-Chiu Ma, Sewoong Oh, Ludwig Schmidt, Pang Wei Koh, Ranjay Krishna
Multilingual Diversity Improves Vision-Language Representations. CoRR (2024)
Divyansh Pareek, Simon S. Du, Sewoong Oh
Understanding the Gains from Repeated Self-Distillation. CoRR (2024)
Galen Andrew, Peter Kairouz, Sewoong Oh, Alina Oprea, Hugh Brendan McMahan, Vinith Menon Suriyakumar
One-shot Empirical Privacy Estimation for Federated Learning. ICLR (2024)
Thao Nguyen, Samir Yitzhak Gadre, Gabriel Ilharco, Sewoong Oh, Ludwig Schmidt
Improving Multimodal Datasets with Image Captioning. CoRR (2023)
Boxin Wang, Jacky Yibo Zhang, Yuan Cao, Bo Li, H. Brendan McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer
Can Public Large Language Models Help Private Cross-device Federated Learning? CoRR (2023)
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Guha Thakurta, Lun Wang
Why Is Public Pretraining Necessary for Private Model Training? ICML (2023)
Galen Andrew, Peter Kairouz, Sewoong Oh, Alina Oprea, H. Brendan McMahan, Vinith Suriyakumar
One-shot Empirical Privacy Estimation for Federated Learning. CoRR (2023)
Rishi D. Jha, Jonathan Hayase, Sewoong Oh
Label Poisoning is All You Need. CoRR (2023)
Liam Collins, Shanshan Wu, Sewoong Oh, Khe Chai Sim
Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning. CoRR (2023)
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
Why Is Public Pretraining Necessary for Private Model Training? CoRR (2023)
Vivek Ramanujan, Thao Nguyen, Sewoong Oh, Ali Farhadi, Ludwig Schmidt
On the Connection between Pre-training Data Diversity and Fine-tuning Robustness. NeurIPS (2023)
Zheng Xu, Maxwell D. Collins, Yuxiao Wang, Liviu Panait, Sewoong Oh, Sean Augenstein, Ting Liu, Florian Schroff, H. Brendan McMahan
Learning to Generate Image Embeddings with User-Level Differential Privacy. CVPR (2023)
Arun Ganesh, Daogao Liu, Sewoong Oh, Abhradeep Thakurta
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks. CoRR (2023)
Krishna Pillutla, Galen Andrew, Peter Kairouz, H. Brendan McMahan, Alina Oprea, Sewoong Oh
Unleashing the Power of Randomization in Auditing Differentially Private ML. CoRR (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 M. 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
DataComp: In search of the next generation of multimodal datasets. CoRR (2023)
Jonathan Hayase, Sewoong Oh
Few-shot Backdoor Attacks via Neural Tangent Kernels. ICLR (2023)
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes. IEEE J. Sel. Areas Inf. Theory 4 (2023)
Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz, Sewoong Oh
Private Federated Learning with Autotuned Compression. ICML (2023)
Rishi D. Jha, Jonathan Hayase, Sewoong Oh
Label Poisoning is All You Need. NeurIPS (2023)
Krishna Pillutla, Galen Andrew, Peter Kairouz, H. Brendan McMahan, Alina Oprea, Sewoong Oh
Unleashing the Power of Randomization in Auditing Differentially Private ML. NeurIPS (2023)
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes. CoRR (2023)
Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Sai Suggala
Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency. NeurIPS (2023)
Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh
Towards a Defense Against Federated Backdoor Attacks Under Continuous Training. Trans. Mach. Learn. Res. 2023 (2023)
Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Sai Suggala
Near Optimal Private and Robust Linear Regression. CoRR (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 M. Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander J. Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
DataComp: In search of the next generation of multimodal datasets. NeurIPS (2023)
S. Ashwin Hebbar, Viraj Vivek Nadkarni, Ashok Vardhan Makkuva, Suma Bhat, Sewoong Oh, Pramod Viswanath
CRISP: Curriculum based Sequential neural decoders for Polar code family. ICML (2023)
Thao Nguyen, Samir Yitzhak Gadre, Gabriel Ilharco, Sewoong Oh, Ludwig Schmidt
Improving multimodal datasets with image captioning. NeurIPS (2023)
Daogao Liu, Arun Ganesh, Sewoong Oh, Abhradeep Guha Thakurta
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks. NeurIPS (2023)
Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz, Sewoong Oh
Private Federated Learning with Autotuned Compression. CoRR (2023)
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie J. Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang
Challenges towards the Next Frontier in Privacy. CoRR (2023)
Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
DPZero: Dimension-Independent and Differentially Private Zeroth-Order Optimization. CoRR (2023)
Vivek Ramanujan, Thao Nguyen, Sewoong Oh, Ludwig Schmidt, Ali Farhadi
On the Connection between Pre-training Data Diversity and Fine-tuning Robustness. CoRR (2023)
Xiyang Liu, Weihao Kong, Sewoong Oh
Differential privacy and robust statistics in high dimensions. COLT (2022)
Kiran Koshy Thekumparampil, Niao He, Sewoong Oh
Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization. AISTATS (2022)
Zaïd Harchaoui, Sewoong Oh, Soumik Pal, Raghav Somani, Raghavendra Tripathi
Stochastic optimization on matrices and a graphon McKean-Vlasov limit. CoRR (2022)
Thao Nguyen, Gabriel Ilharco, Mitchell Wortsman, Sewoong Oh, Ludwig Schmidt
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP. NeurIPS (2022)
Liang Zhang, Kiran K. Thekumparampil, Sewoong Oh, Niao He
Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization. NeurIPS (2022)
Xingyu Wang, Sewoong Oh, Chang-Han Rhee
Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise. ICLR (2022)
Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh
Towards a Defense against Backdoor Attacks in Continual Federated Learning. CoRR (2022)
Jonathan Hayase, Sewoong Oh
Few-shot Backdoor Attacks via Neural Tangent Kernels. CoRR (2022)
Liam Collins, Aryan Mokhtari, Sewoong Oh, Sanjay Shakkottai
MAML and ANIL Provably Learn Representations. CoRR (2022)
Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck, Swabha Swayamdipta, Rowan Zellers, Sewoong Oh, Yejin Choi, Zaïd Harchaoui
MAUVE Scores for Generative Models: Theory and Practice. CoRR (2022)
Matt Jordan, Jonathan Hayase, Alex Dimakis, Sewoong Oh
Zonotope Domains for Lagrangian Neural Network Verification. NeurIPS (2022)
Melih Yilmaz, William Fondrie, Wout Bittremieux, Sewoong Oh, William S. Noble
De novo mass spectrometry peptide sequencing with a transformer model. ICML (2022)
S. Ashwin Hebbar, Viraj Nadkarni, Ashok Vardhan Makkuva, Suma Bhat, Sewoong Oh, Pramod Viswanath
CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family. CoRR (2022)
Xiyang Liu, Weihao Kong, Prateek Jain, Sewoong Oh
DP-PCA: Statistically Optimal and Differentially Private PCA. NeurIPS (2022)
Xiyang Liu, Weihao Kong, Prateek Jain, Sewoong Oh
DP-PCA: Statistically Optimal and Differentially Private PCA. CoRR (2022)
Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization. CoRR (2022)
Kiran Koshy Thekumparampil, Niao He, Sewoong Oh
Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization. CoRR (2022)
Zheng Xu, Maxwell D. Collins, Yuxiao Wang, Liviu Panait, Sewoong Oh, Sean Augenstein, Ting Liu, Florian Schroff, H. Brendan McMahan
Learning to Generate Image Embeddings with User-level Differential Privacy. CoRR (2022)
Charlie Hou, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
FedChain: Chained Algorithms for Near-optimal Communication Cost in Federated Learning. ICLR (2022)
Thao Nguyen, Gabriel Ilharco, Mitchell Wortsman, Sewoong Oh, Ludwig Schmidt
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP. CoRR (2022)
Matt Jordan, Jonathan Hayase, Alexandros G. Dimakis, Sewoong Oh
Zonotope Domains for Lagrangian Neural Network Verification. CoRR (2022)
Liam Collins, Aryan Mokhtari, Sewoong Oh, Sanjay Shakkottai
MAML and ANIL Provably Learn Representations. ICML (2022)
Sen Lin, Ming Shi, Anish Arora, Raef Bassily, Elisa Bertino, Constantine Caramanis, Kaushik R. Chowdhury, Eylem Ekici, Atilla Eryilmaz, Stratis Ioannidis, Nan Jiang, Gauri Joshi, Jim Kurose, Yingbin Liang, Zhiqiang Lin, Jia Liu, Mingyan Liu, Tommaso Melodia, Aryan Mokhtari, Rob Nowak, Sewoong Oh, Srini Parthasarathy, Chunyi Peng, Hulya Seferoglu, Ness Shroff, Sanjay Shakkottai, Kannan Srinivasan, Ameet Talwalkar, Aylin Yener, Lei Ying
Leveraging Synergies Between AI and Networking to Build Next Generation Edge Networks. CIC (2022)
Vivek Kumar Bagaria, Amir Dembo, Sreeram Kannan, Sewoong Oh, David Tse, Pramod Viswanath, Xuechao Wang, Ofer Zeitouni
Proof-of-Stake Longest Chain Protocols: Security vs Predictability. ConsensusDay@CCS (2022)
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Statistically and Computationally Efficient Linear Meta-representation Learning. NeurIPS (2021)
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding. CoRR (2021)
Xingyu Wang, Sewoong Oh, Chang-Han Rhee
Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise. CoRR (2021)
Xiyang Liu, Weihao Kong, Sewoong Oh
Differential privacy and robust statistics in high dimensions. CoRR (2021)
Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh
Defense against backdoor attacks via robust covariance estimation. ICML (2021)
Jinwoo Jeon, Jaechang Kim, Kangwook Lee, Sewoong Oh, Jungseul Ok
Gradient Inversion with Generative Image Prior. CoRR (2021)
Xiyang Liu, Weihao Kong, Sham M. Kakade, Sewoong Oh
Robust and differentially private mean estimation. NeurIPS (2021)
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding. ISIT (2021)
Charlie Hou, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
Reducing the Communication Cost of Federated Learning through Multistage Optimization. CoRR (2021)
Charlie Hou, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh
Efficient Algorithms for Federated Saddle Point Optimization. CoRR (2021)
Ashok Vardhan Makkuva, Xiyang Liu, Mohammad Vahid Jamali, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning. ICML (2021)
Sewoong Oh, Soumik Pal, Raghav Somani, Raghav Tripathi
Gradient flows on graphons: existence, convergence, continuity equations. CoRR (2021)
Jinwoo Jeon, Jaechang Kim, Kangwook Lee, Sewoong Oh, Jungseul Ok
Gradient Inversion with Generative Image Prior. NeurIPS (2021)
Xiyang Liu, Weihao Kong, Sham M. Kakade, Sewoong Oh
Robust and Differentially Private Mean Estimation. CoRR (2021)
Ashok Vardhan Makkuva, Xiyang Liu, Mohammad Vahid Jamali, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning. CoRR (2021)
Lang Liu, Krishna Pillutla, Sean Welleck, Sewoong Oh, Yejin Choi, Zaïd Harchaoui
Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals. NeurIPS (2021)
Lang Liu, Krishna Pillutla, Sean Welleck, Sewoong Oh, Yejin Choi, Zaïd Harchaoui
Divergence Frontiers for Generative Models: Sample Complexity, Quantization Level, and Frontier Integral. CoRR (2021)
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Sample Efficient Linear Meta-Learning by Alternating Minimization. CoRR (2021)
Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh
SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics. CoRR (2021)
Weihao Kong, Raghav Somani, Zhao Song, Sham M. Kakade, Sewoong Oh
Meta-learning for mixed linear regression. CoRR (2020)
Weihao Kong, Raghav Somani, Zhao Song, Sham M. Kakade, Sewoong Oh
Meta-learning for Mixed Linear Regression. ICML (2020)
Weizhao Tang, Weina Wang, Giulia C. Fanti, Sewoong Oh
Privacy-Utility Tradeoffs in Routing Cryptocurrency over Payment Channel Networks. Proc. ACM Meas. Anal. Comput. Syst. 4 (2) (2020)
Hyeji Kim, Sewoong Oh, Pramod Viswanath
Physical Layer Communication via Deep Learning. IEEE J. Sel. Areas Inf. Theory 1 (1) (2020)
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method. CoRR (2020)
Weizhao Tang, Weina Wang, Giulia C. Fanti, Sewoong Oh
Privacy-Utility Tradeoffs in Routing Cryptocurrency over Payment Channel Networks. SIGMETRICS (Abstracts) (2020)
Weihao Kong, Raghav Somani, Sham M. Kakade, Sewoong Oh
Robust Meta-learning for Mixed Linear Regression with Small Batches. NeurIPS (2020)
Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee
Optimal transport mapping via input convex neural networks. ICML (2020)
Ashok Vardhan Makkuva, Sewoong Oh, Sreeram Kannan, Pramod Viswanath
Learning in Gated Neural Networks. AISTATS (2020)
Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
Deepcode and Modulo-SK are Designed for Different Settings. CoRR (2020)
Weihao Kong, Raghav Somani, Sham M. Kakade, Sewoong Oh
Robust Meta-learning for Mixed Linear Regression with Small Batches. CoRR (2020)
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method. NeurIPS (2020)
Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
Deepcode: Feedback Codes via Deep Learning. IEEE J. Sel. Areas Inf. Theory 1 (1) (2020)
Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sewoong Oh, Sreeram Kannan, Pramod Viswanath
Feedback Turbo Autoencoder. ICASSP (2020)
Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
LEARN Codes: Inventing Low-Latency Codes via Recurrent Neural Networks. IEEE J. Sel. Areas Inf. Theory 1 (1) (2020)

Sewoong Oh.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Sewoong Oh