Search Results for author:
Found 29 papers, 8 papers with code
Training Text-to-Text Transformers with Privacy Guarantees
We focus on T5 and show that by using recent advances in JAX and XLA we can train models with DP that do not suffer a large drop in pre-training utility, nor in training speed, and can still be fine-tuned to high accuracies on downstream tasks (e. g.
Scaling Laws for Downstream Task Performance of Large Language Models
With sufficient alignment, both downstream cross-entropy and BLEU score improve monotonically with more pretraining data.
Measuring Re-identification Risk
In this work, we present a new theoretical framework to measure re-identification risk in such user representations.
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
However, while some adoption of DP has happened in industry, attempts to apply DP to real world complex ML models are still few and far between.
Algorithms with Prediction Portfolios
For each of these problems we introduce new algorithms that take advantage of multiple predictors, and prove bounds on the resulting performance.
Learning-Augmented Private Algorithms for Multiple Quantile Release
When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors.
Easy Differentially Private Linear Regression
In this paper, we study an algorithm which uses the exponential mechanism to select a model with high Tukey depth from a collection of non-private regression models.
Smooth Anonymity for Sparse Binary Matrices
When working with user data providing well-defined privacy guarantees is paramount.
Scalable Differentially Private Clustering via Hierarchically Separated Trees
We study the private $k$-median and $k$-means clustering problem in $d$ dimensional Euclidean space.
Learning Predictions for Algorithms with Predictions
A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms can take advantage of a possibly-imperfect prediction of some aspect of the problem.
Robust Online Correlation Clustering
In correlation clustering we are given a set of points along with recommendations whether each pair of points should be placed in the same cluster or into separate clusters.
On the Pitfalls of Label Differential Privacy
We complement the negative results with a non-parametric estimator for the true privacy loss, and apply our techniques on large-scale benchmark data to demonstrate how to achieve a desired privacy protection.
Label differential privacy via clustering
We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set.
Faster Matchings via Learned Duals
Second, once the duals are feasible, they may not be optimal, so we show that they can be used to quickly find an optimal solution.
Private Optimization Without Constraint Violations
We also prove a lower bound demonstrating that the difference between the objective value of our algorithm's solution and the optimal solution is tight up to logarithmic factors among all differentially private algorithms.
Fair Hierarchical Clustering
As machine learning has become more prevalent, researchers have begun to recognize the necessity of ensuring machine learning systems are fair.
Sliding Window Algorithms for k-Clustering Problems
The sliding window model of computation captures scenarios in which data is arriving continuously, but only the latest $w$ elements should be used for analysis.
Data Structures and Algorithms
Differentially Private Covariance Estimation
The covariance matrix of a dataset is a fundamental statistic that can be used for calculating optimum regression weights as well as in many other learning and data analysis settings.
Maximizing Induced Cardinality Under a Determinantal Point Process
In this paper we advocate an alternative framework for applying DPPs to recommender systems.
Fair Clustering Through Fairlets
We show that any fair clustering problem can be decomposed into first finding good fairlets, and then using existing machinery for traditional clustering algorithms.
Competitive caching with machine learned advice
Traditional online algorithms encapsulate decision making under uncertainty, and give ways to hedge against all possible future events, while guaranteeing a nearly optimal solution as compared to an offline optimum.
Online Learning for Non-Stationary A/B Tests
The rollout of new versions of a feature in modern applications is a manual multi-stage process, as the feature is released to ever larger groups of users, while its performance is carefully monitored.
Consistent k-Clustering
The study of online algorithms and competitive analysis provides a solid foundation for studying the quality of irrevocable decision making when the data arrives in an online manner.
Revenue Optimization with Approximate Bid Predictions
In the context of advertising auctions, finding good reserve prices is a notoriously challenging learning problem.
Statistical Cost Sharing
We first show that when cost functions come from the family of submodular functions with bounded curvature, $\kappa$, the Shapley value can be approximated from samples up to a $\sqrt{1 - \kappa}$ factor, and that the bound is tight.
On Mixtures of Markov Chains
We study the problem of reconstructing a mixture of Markov chains from the trajectories generated by random walks through the state space.
Scalable K-Means++
The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution.
Databases
Ad Serving Using a Compact Allocation Plan
A large fraction of online display advertising is sold via guaranteed contracts: a publisher guarantees to the advertiser a certain number of user visits satisfying the targeting predicates of the contract.
Data Structures and Algorithms
SHALE: An Efficient Algorithm for Allocation of Guaranteed Display Advertising
Motivated by the problem of optimizing allocation in guaranteed display advertising, we develop an efficient, lightweight method of generating a compact {\em allocation plan} that can be used to guide ad server decisions.
Data Structures and Algorithms
