In this paper, we propose a novel strategy for a snake robot to move str...
A recent line of work has shown a surprising connection between
multical...
Membership inference attacks are designed to determine, using black box
...
We study the problem of non-disclosively collecting a sample of data tha...
We revisit the problem of differentially private squared error linear
re...
We make a connection between multicalibration and property elicitation a...
We study the connection between multicalibration and boosting for square...
A reconstruction attack on a private dataset D takes as input some publi...
We develop fast distribution-free conformal prediction algorithms for
ob...
We provide a differentially private algorithm for producing synthetic da...
We present a stylized model with feedback loops for the evolution of a
p...
We show how to take a regression function f̂ that is appropriately
“mult...
Individual probabilities refer to the probabilities of outcomes that are...
We consider an online learning problem with one-sided feedback, in which...
We give a simple, generic conformal prediction method for sequential
pre...
We introduce AdaMix, an adaptive differentially private algorithm for
tr...
Notions of fair machine learning that seek to control various kinds of e...
We introduce a simple but general online learning framework, in which at...
We study the problem of training a model that must obey demographic fair...
Data deletion algorithms aim to remove the influence of deleted data poi...
In this rejoinder, we aim to address two broad issues that cover most
co...
We propose, implement, and evaluate a new algorithm for releasing answer...
We extend the notion of minimax fairness in supervised learning problems...
We study a game theoretic model of standardized testing for college
admi...
We present a general, efficient technique for providing contextual
predi...
We consider a recently introduced framework in which fairness is measure...
Applying differential privacy at scale requires convenient ways to check...
We show how to achieve the notion of "multicalibration" from Hébert-John...
We study the data deletion problem for convex models. By leveraging
tech...
We consider a variation on the classical finance problem of optimal port...
There is increasing regulatory interest in whether machine learning
algo...
We introduce the pipeline intervention problem, defined by a layered
dir...
We propose and analyze differentially private (DP) mechanisms for call
a...
Differential privacy is an information theoretic constraint on algorithm...
We consider a fundamental dynamic allocation problem motivated by the pr...
We give a new proof of the "transfer theorem" underlying adaptive data
a...
One of the most effective algorithms for differentially private learning...
We prove a general connection between the communication complexity of
tw...
We design a general framework for answering adaptive statistical queries...
Curators of sensitive datasets sometimes need to know whether queries ag...
We revisit the notion of individual fairness first proposed by Dwork et ...
We propose a new family of fairness definitions for classification probl...
Differential privacy has seen remarkable success as a rigorous and pract...
We study the power of interactivity in local differential privacy. First...
We study an online classification problem with partial feedback in which...
We design two learning algorithms that simultaneously promise differenti...
We develop theory for using heuristics to solve computationally hard pro...
The last few years have seen an explosion of academic and popular intere...
Settings such as lending and policing can be modeled by a centralized ag...
We study a two-stage model, in which students are 1) admitted to college...