265 citations · 441 across the 39 of their papers we have counts for
13 papers · 1 filter
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…
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…
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…
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…
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…
Locally Private Gaussian Estimation
Matthew Joseph, Janardhan Kulkarni, Jieming Mao +1
We study a basic private estimation problem: each of users draws a single i.i.d. sample from an unknown Gaussian distribution, and the goal is to estimate the mean of this Gaus…