Sewoong Oh

46

Papers

359

Total Citations

Papers (46)

Estimating Mutual Information for Discrete-Continuous Mixtures

NeurIPS 2017arXiv

Achieving budget-optimality with adaptive schemes in crowdsourcing

NeurIPS 2016arXiv

Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation

NeurIPS 2016arXiv

Optimal Sample Complexity of M-wise Data for Top-K Ranking

Computational and Statistical Tradeoffs in Learning to Rank

NeurIPS 2016arXiv

PLeaS - Merging Models with Permutations and Least Squares

Matrix Norm Estimation from a Few Entries

Discovering Potential Correlations via Hypercontractivity

NeurIPS 2017arXiv

Scalable Fingerprinting of Large Language Models

DPZero: Private Fine-Tuning of Language Models without Backpropagation

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

Privacy-Preserving Instructions for Aligning Large Language Models

Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy

Learning To Generate Image Embeddings With User-Level Differential Privacy

Collaboratively Learning Preferences from Ordinal Data

NeurIPS 2015arXiv

Secure Multi-party Differential Privacy

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

Improving multimodal datasets with image captioning

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

DataComp: In search of the next generation of multimodal datasets

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

Unleashing the Power of Randomization in Auditing Differentially Private ML

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

Label Poisoning is All You Need

The Composition Theorem for Differential Privacy

Data-driven Rank Breaking for Efficient Rank Aggregation

Metadata-conscious anonymous messaging

Optimality of Belief Propagation for Crowdsourced Classification

Conditional Dependence via Shannon Capacity: Axioms, Estimators and Applications

Rate Distortion For Model Compression:From Theory To Practice

Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms

PacGAN: The power of two samples in generative adversarial networks

Deepcode: Feedback Codes via Deep Learning

Robustness of conditional GANs to noisy labels

Efficient Algorithms for Smooth Minimax Optimization

Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels

Minimax Optimal Estimation of Approximate Differential Privacy on Neighboring Databases

Robust Meta-learning for Mixed Linear Regression with Small Batches

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

Robust and differentially private mean estimation

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals

Statistically and Computationally Efficient Linear Meta-representation Learning

Gradient Inversion with Generative Image Prior

Zonotope Domains for Lagrangian Neural Network Verification

NeurIPS 2022arXiv

Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP

DP-PCA: Statistically Optimal and Differentially Private PCA