b'Sewoong Oh'

research

∙ 07/24/2023

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

Pre-training has been widely adopted in deep learning to improve model p...

0 Vivek Ramanujan, et al. ∙

research

∙ 07/20/2023

Private Federated Learning with Autotuned Compression

We propose new techniques for reducing communication in private federate...

0 Enayat Ullah, et al. ∙

research

∙ 07/19/2023

Improving Multimodal Datasets with Image Captioning

Massive web datasets play a key role in the success of large vision-lang...

0 Thao Nguyen, et al. ∙

research

∙ 05/29/2023

Unleashing the Power of Randomization in Auditing Differentially Private ML

We present a rigorous methodology for auditing differentially private ma...

0 Krishna Pillutla, et al. ∙

research

∙ 05/20/2023

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

We study (differentially) private federated learning (FL) of language mo...

0 Boxin Wang, et al. ∙

research

∙ 04/27/2023

DataComp: In search of the next generation of multimodal datasets

Large multimodal datasets have been instrumental in recent breakthroughs...

0 Samir Yitzhak Gadre, et al. ∙

research

∙ 02/20/2023

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

We consider the problem of minimizing a non-convex objective while prese...

0 Arun Ganesh, et al. ∙

research

∙ 02/19/2023

Why Is Public Pretraining Necessary for Private Model Training?

In the privacy-utility tradeoff of a model trained on benchmark language...

0 Arun Ganesh, et al. ∙

research

∙ 02/06/2023

One-shot Empirical Privacy Estimation for Federated Learning

Privacy auditing techniques for differentially private (DP) algorithms a...

0 Galen Andrew, et al. ∙

research

∙ 01/30/2023

Near Optimal Private and Robust Linear Regression

We study the canonical statistical estimation problem of linear regressi...

0 Xiyang Liu, et al. ∙

research

∙ 01/16/2023

Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes

Reed-Muller (RM) codes achieve the capacity of general binary-input memo...

0 Mohammad Vahid Jamali, et al. ∙

research

∙ 11/20/2022

Learning to Generate Image Embeddings with User-level Differential Privacy

Small on-device models have been successfully trained with user-level di...

0 Zheng Xu, et al. ∙

research

∙ 10/14/2022

Zonotope Domains for Lagrangian Neural Network Verification

Neural network verification aims to provide provable bounds for the outp...

0 Matt Jordan, et al. ∙

research

∙ 10/12/2022

Few-shot Backdoor Attacks via Neural Tangent Kernels

In a backdoor attack, an attacker injects corrupted examples into the tr...

0 Jonathan Hayase, et al. ∙

research

∙ 10/02/2022

Stochastic optimization on matrices and a graphon McKean-Vlasov limit

We consider stochastic gradient descents on the space of large symmetric...

0 Zaid Harchaoui, et al. ∙

research

∙ 10/01/2022

CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family

Polar codes are widely used state-of-the-art codes for reliable communic...

0 S Ashwin Hebbar, et al. ∙

research

∙ 08/10/2022

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

Web-crawled datasets have enabled remarkable generalization capabilities...

9 Thao Nguyen, et al. ∙

research

∙ 06/01/2022

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

We study differentially private (DP) algorithms for smooth stochastic mi...

0 Liang Zhang, et al. ∙

research

∙ 05/27/2022

DP-PCA: Statistically Optimal and Differentially Private PCA

We study the canonical statistical task of computing the principal compo...

4 Xiyang Liu, et al. ∙

research

∙ 05/24/2022

Towards a Defense against Backdoor Attacks in Continual Federated Learning

Backdoor attacks are a major concern in federated learning (FL) pipeline...

0 Shuaiqi Wang, et al. ∙

research

∙ 02/07/2022

MAML and ANIL Provably Learn Representations

Recent empirical evidence has driven conventional wisdom to believe that...

0 Liam Collins, et al. ∙

research

∙ 01/19/2022

Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization

We study the bilinearly coupled minimax problem: min_xmax_y f(x) + y^⊤ A...

0 Kiran Koshy Thekumparampil, et al. ∙

research

∙ 11/18/2021

Gradient flows on graphons: existence, convergence, continuity equations

Wasserstein gradient flows on probability measures have found a host of ...

0 Sewoong Oh, et al. ∙

research

∙ 11/12/2021

Differential privacy and robust statistics in high dimensions

We introduce a universal framework for characterizing the statistical ef...

0 Xiyang Liu, et al. ∙

research

∙ 10/28/2021

Gradient Inversion with Generative Image Prior

Federated Learning (FL) is a distributed learning framework, in which th...

3 Jinwoo Jeon, et al. ∙

research

∙ 08/29/2021

KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning

Landmark codes underpin reliable physical layer communication, e.g., Ree...

0 Ashok Vardhan Makkuva, et al. ∙

research

∙ 08/16/2021

Reducing the Communication Cost of Federated Learning through Multistage Optimization

A central question in federated learning (FL) is how to design optimizat...

0 Charlie Hou, et al. ∙

research

∙ 06/15/2021

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Level, and Frontier Integral

The spectacular success of deep generative models calls for quantitative...

0 Lang Liu, et al. ∙

research

∙ 05/18/2021

Sample Efficient Linear Meta-Learning by Alternating Minimization

Meta-learning synthesizes and leverages the knowledge from a given set o...

7 Kiran Koshy Thekumparampil, et al. ∙

research

∙ 04/22/2021

SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics

Modern machine learning increasingly requires training on a large collec...

17 Jonathan Hayase, et al. ∙

research

∙ 02/18/2021

Robust and Differentially Private Mean Estimation

Differential privacy has emerged as a standard requirement in a variety ...

0 Xiyang Liu, et al. ∙

research

∙ 02/12/2021

Efficient Algorithms for Federated Saddle Point Optimization

We consider strongly convex-concave minimax problems in the federated se...

0 Charlie Hou, et al. ∙

research

∙ 02/08/2021

Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise

The empirical success of deep learning is often attributed to SGD's myst...

0 Xingyu Wang, et al. ∙

research

∙ 02/02/2021

Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding

Reed-Muller (RM) codes are conjectured to achieve the capacity of any bi...

0 Mohammad Vahid Jamali, et al. ∙

research

∙ 10/05/2020

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

We consider the classical setting of optimizing a nonsmooth Lipschitz co...

21 Kiran Koshy Thekumparampil, et al. ∙

research

∙ 08/18/2020

Deepcode and Modulo-SK are Designed for Different Settings

We respond to [1] which claimed that "Modulo-SK scheme outperforms Deepc...

17 Hyeji Kim, et al. ∙

research

∙ 06/17/2020

Robust Meta-learning for Mixed Linear Regression with Small Batches

A common challenge faced in practical supervised learning, such as medic...

29 Weihao Kong, et al. ∙

research

∙ 02/20/2020

Meta-learning for mixed linear regression

In modern supervised learning, there are a large number of tasks, but ma...

6 Weihao Kong, et al. ∙

research

∙ 11/08/2019

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

Designing codes that combat the noise in a communication medium has rema...

0 Yihan Jiang, et al. ∙

research

∙ 10/05/2019

Proof-of-Stake Longest Chain Protocols Revisited

The Nakamoto longest chain protocol has served Bitcoin well in its decad...

0 Xuechao Wang, et al. ∙

research

∙ 09/18/2019

Barracuda: The Power of ℓ-polling in Proof-of-Stake Blockchains

A blockchain is a database of sequential events that is maintained by a ...

0 Giulia Fanti, et al. ∙

research

∙ 09/06/2019

Privacy-Utility Tradeoffs in Routing Cryptocurrency over Payment Channel Networks

Payment channel networks (PCNs) are viewed as one of the most promising ...

0 Weizhao Tang, et al. ∙

research

∙ 08/28/2019

Optimal transport mapping via input convex neural networks

In this paper, we present a novel and principled approach to learn the o...

6 Ashok Vardhan Makkuva, et al. ∙

research

∙ 07/02/2019

Efficient Algorithms for Smooth Minimax Optimization

This paper studies first order methods for solving smooth minimax optimi...

10 Kiran Koshy Thekumparampil, et al. ∙

research

∙ 06/14/2019

InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers

Training disentangled representations with generative adversarial networ...

3 Zinan Lin, et al. ∙

research

∙ 06/09/2019

Robust conditional GANs under missing or uncertain labels

Matching the performance of conditional Generative Adversarial Networks ...

9 Kiran Koshy Thekumparampil, et al. ∙

research

∙ 06/06/2019

Learning in Gated Neural Networks

Gating is a key feature in modern neural networks including LSTMs, GRUs ...

0 Ashok Vardhan Makkuva, et al. ∙

research

∙ 05/24/2019

Minimax Rates of Estimating Approximate Differential Privacy

Differential privacy has become a widely accepted notion of privacy, lea...

0 Xiyang Liu, et al. ∙

research

∙ 03/06/2019

DeepTurbo: Deep Turbo Decoder

Present-day communication systems routinely use codes that approach the ...

0 Yihan Jiang, et al. ∙

research

∙ 12/01/2018

Number of Connected Components in a Graph: Estimation via Counting Patterns

Due to the limited resources and the scale of the graphs in modern datas...

0 Ashish Khetan, et al. ∙

Sewoong Oh

Featured Co-authors