We study the problem of in-context learning (ICL) with large language mo...
We prove that there exists an online algorithm that for any sequence of
...
Generating differentially private (DP) synthetic data that closely resem...
Suppose we want to train text prediction models in email clients or word...
Large pretrained models can be privately fine-tuned to achieve performan...
Differentially private stochastic gradient descent (DP-SGD) is the workh...
Recent papers have shown that large pre-trained language models (LLMs) s...
We give an online algorithm that with high probability computes a
(e/e-1...
We give simpler, sparser, and faster algorithms for differentially priva...
Training Deep Neural Networks (DNNs) is a widely popular workload in bot...
We revisit the problem of n-gram extraction in the differential privacy
...
We show that adding differential privacy to Explainable Boosting Machine...
In the scheduling with non-uniform communication delay problem, the inpu...
We study the differentially private Empirical Risk Minimization (ERM) an...
Correlation clustering is a widely used technique in unsupervised machin...
Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its varia...
Reconfigurable optical topologies are emerging as a promising technology...
In this paper we introduce and study the online consistent k-clustering
...
We consider the classic problem of scheduling jobs with precedence
const...
We consider the classic problem of scheduling jobs with precedence
const...
In this paper we study the facility location problem in the online with
...
We study the basic operation of set union in the global model of differe...
We initiate the study of hypothesis selection under local differential
p...
We consider the problem of learning Markov Random Fields (including the
...
The problem of (vertex) (Δ+1)-coloring a graph of maximum degree
Δ has b...
Consider a unit interval [0,1] in which n points arrive one-by-one
indep...
In this paper we study the problem of dynamically maintaining graph
prop...
We study a basic private estimation problem: each of n users draws a sin...
We consider the problem of incremental cycle detection and topological
o...
We consider the classic scheduling problem of minimizing the total weigh...
Scheduling a set of jobs over a collection of machines is a fundamental
...
Differential privacy has emerged as the main definition for private data...
We consider the problem of maintaining an (approximately) minimum vertex...
The collection and analysis of telemetry data from users' devices is
rou...
We present a scheduler that improves cluster utilization and job complet...