265 citations · 441 across the 39 of their papers we have counts for
42 papers
Classification with Partially Private Features
Zeyu Shen, Anilesh Krishnaswamy, Janardhan Kulkarni +1
In this paper, we consider differentially private classification when some features are sensitive, while the rest of the features and the label are not. We adapt the definition of…
Optimal Online Discrepancy Minimization
Janardhan Kulkarni, Victor Reis, Thomas Rothvoss
We prove that there exists an online algorithm that for any sequence of vectors with , arriving one at a time, decides random si…
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni +2
Generating differentially private (DP) synthetic data that closely resembles the original private data is a scalable way to mitigate privacy concerns in the current data-driven wor…
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan Kulkarni +5
Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are…
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
Jiyan He, Xuechen Li, Da Yu +6
Differentially private deep learning has recently witnessed advances in computational efficiency and privacy-utility trade-off. We explore whether further improvements along the tw…
When Does Differentially Private Learning Not Suffer in High Dimensions?
Xuechen Li, Daogao Liu, Tatsunori Hashimoto +4
Large pretrained models can be privately fine-tuned to achieve performance approaching that of non-private models. A common theme in these results is the surprising observation tha…
Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A Inan +2
Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models…
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
Da Yu, Gautam Kamath, Janardhan Kulkarni +3
Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all d…
Online Edge Coloring via Tree Recurrences and Correlation Decay
Janardhan Kulkarni, Yang P. Liu, Ashwin Sah +2
We give an online algorithm that with high probability computes a edge coloring on a graph with maximum degree under online…
Differentially Private Fine-tuning of Language Models
Da Yu, Saurabh Naik, Arturs Backurs +9
We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus…
Synergy: Resource Sensitive DNN Scheduling in Multi-Tenant Clusters
Jayashree Mohan, Amar Phanishayee, Janardhan Kulkarni +1
Training Deep Neural Networks (DNNs) is a widely popular workload in both enterprises and cloud data centers. Existing schedulers for DNN training consider GPU as the dominant reso…
Differentially Private n-gram Extraction
Kunho Kim, Sivakanth Gopi, Janardhan Kulkarni +1
We revisit the problem of -gram extraction in the differential privacy setting. In this problem, given a corpus of private text data, the goal is to release as many -grams as…
Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
Harsha Nori, Rich Caruana, Zhiqi Bu +2
We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while prote…
On the Hardness of Scheduling With Non-Uniform Communication Delays
Sami Davies, Janardhan Kulkarni, Thomas Rothvoss +3
In the scheduling with non-uniform communication delay problem, the input is a set of jobs with precedence constraints. Associated with every precedence constraint between a pair o…
Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps
Janardhan Kulkarni, Yin Tat Lee, Daogao Liu
We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for non-smooth convex functions. We get a (nearly) optimal b…
Differentially Private Correlation Clustering
Mark Bun, Marek Eliáš, Janardhan Kulkarni
Correlation clustering is a widely used technique in unsupervised machine learning. Motivated by applications where individual privacy is a concern, we initiate the study of differ…
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan Kulkarni +3
Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requ…
Scheduling Opportunistic Links in Two-Tiered Reconfigurable Datacenters
Janardhan Kulkarni, Stefan Schmid, Paweł Schmidt
Reconfigurable optical topologies are emerging as a promising technology to improve the efficiency of datacenter networks. This paper considers the problem of scheduling opportunis…
Consistent -Median: Simpler, Better and Robust
Xiangyu Guo, Janardhan Kulkarni, Shi Li +1
In this paper we introduce and study the online consistent -clustering with outliers problem, generalizing the non-outlier version of the problem studied in [Lattanzi-Vassilvits…
Hierarchy-Based Algorithms for Minimizing Makespan under Precedence and Communication Constraints
Janardhan Kulkarni, Shi Li, Jakub Tarnawski +1
We consider the classic problem of scheduling jobs with precedence constraints on a set of identical machines to minimize the makespan objective function. Understanding the exact a…
Scheduling with Communication Delays via LP Hierarchies and Clustering
Sami Davies, Janardhan Kulkarni, Thomas Rothvoss +2
We consider the classic problem of scheduling jobs with precedence constraints on identical machines to minimize makespan, in the presence of communication delays. In this setting,…
The Power of Recourse: Better Algorithms for Facility Location in Online and Dynamic Models
Xiangyu Guo, Janardhan Kulkarni, Shi Li +1
In this paper we study the facility location problem in the online with recourse and dynamic algorithm models. In the online with recourse model, clients arrive one by one and our…
Differentially Private Set Union
Sivakanth Gopi, Pankaj Gulhane, Janardhan Kulkarni +3
We study the basic operation of set union in the global model of differential privacy. In this problem, we are given a universe of items, possibly of infinite size, and a datab…
Locally Private Hypothesis Selection
Sivakanth Gopi, Gautam Kamath, Janardhan Kulkarni +3
We initiate the study of hypothesis selection under local differential privacy. Given samples from an unknown probability distribution and a set of probability distribution…