Search Results for author:
Found 18 papers, 0 papers with code
Learning across Data Owners with Joint Differential Privacy
In this paper, we study the setting in which data owners train machine learning models collaboratively under a privacy notion called joint differential privacy [Kearns et al., 2018].
Regret Minimization with Noisy Observations
In our model, the task is to pick the highest one out of $n$ values.
Shuffle Private Stochastic Convex Optimization
In shuffle privacy, each user sends a collection of randomized messages to a trusted shuffler, the shuffler randomly permutes these messages, and the resulting shuffled collection of messages must satisfy differential privacy.
Smoothly Bounding User Contributions in Differential Privacy
But at the same time, more noise might need to be added to the algorithm in order to keep the algorithm differentially private and this might hurt the algorithm’s performance.
Connecting Robust Shuffle Privacy and Pan-Privacy
First, we give robustly shuffle private protocols and upper bounds for counting distinct elements and uniformity testing.
Pan-Private Uniformity Testing
We show that the sample complexity of pure pan-private uniformity testing is $\Theta(k^{2/3})$.
Exponential Separations in Local Differential Privacy
We prove a general connection between the communication complexity of two-player games and the sample complexity of their multi-player locally private analogues.
Sorted Top-k in Rounds
When the comparisons are noiseless, we characterize how the optimal sample complexity depends on the number of rounds (up to a polylogarithmic factor for general $r$ and up to a constant factor for $r=1$ or 2).
The Role of Interactivity in Local Differential Privacy
Next, we show that our reduction is tight by exhibiting a family of problems such that for any $k$, there is a fully interactive $k$-compositional protocol which solves the problem, while no sequentially interactive protocol can solve the problem without at least an $\tilde \Omega(k)$ factor more examples.
Bayesian Exploration with Heterogeneous Agents
We consider Bayesian Exploration: a simple model in which the recommendation system (the "principal") controls the information flow to the users (the "agents") and strives to incentivize exploration via information asymmetry.
Differentially Private Fair Learning
This algorithm is appealingly simple, but must be able to use protected group membership explicitly at test time, which can be viewed as a form of 'disparate treatment'.
Contextual Pricing for Lipschitz Buyers
For the symmetric loss $\ell(f(x_t), y_t) = \vert f(x_t) - y_t \vert$, we provide an algorithm for this problem achieving total loss $O(\log T)$ when $d=1$ and $O(T^{(d-1)/d})$ when $d>1$, and show that both bounds are tight (up to a factor of $\sqrt{\log T}$).
Locally Private Gaussian Estimation
We study a basic private estimation problem: each of $n$ users draws a single i. i. d.
Incentivizing Exploration with Selective Data Disclosure
We propose and design recommendation systems that incentivize efficient exploration.
Selling to a No-Regret Buyer
- There exists a learning algorithm $\mathcal{A}$ such that if the buyer bids according to $\mathcal{A}$ then the optimal strategy for the seller is simply to post the Myerson reserve for $D$ every round.
A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model
We study the active learning problem of top-$k$ ranking from multi-wise comparisons under the popular multinomial logit model.
Multi-armed Bandit Problems with Strategic Arms
We study a strategic version of the multi-armed bandit problem, where each arm is an individual strategic agent and we, the principal, pull one arm each round.
Competitive analysis of the top-K ranking problem
In particular, we present a linear time algorithm for the top-$K$ problem which has a competitive ratio of $\tilde{O}(\sqrt{n})$; i. e. to solve any instance of top-$K$, our algorithm needs at most $\tilde{O}(\sqrt{n})$ times as many samples needed as the best possible algorithm for that instance (in contrast, all previous known algorithms for the top-$K$ problem have competitive ratios of $\tilde{\Omega}(n)$ or worse).
