14 papers
Is Randomness Necessary for Adaptive Data Analysis?
Edith Cohen, Haim Kaplan, Yishay Mansour +2
The Adaptive Data Analysis (ADA) problem formalizes the challenge of preventing false discovery and overfitting when a dataset is repeatedly reused. Formally, our input is a datase…
Load Balancing under Adaptive Bin Deletions
Haim Kaplan, Shay Sapir, Uri Stemmer
We analyze a balls-and-bins game against an adaptive adversary that sequentially deletes bins. Starting with balls distributed across bins, the adversary deletes a bin in e…
Protecting the Undeleted in Machine Unlearning
Aloni Cohen, Refael Kohen, Kobbi Nissim +1
Machine unlearning aims to remove specific data points from a trained model, often striving to emulate "perfect retraining", i.e., producing the model that would have been obtained…
Adaptively Robust Resettable Streaming
Edith Cohen, Elena Gribelyuk, Jelani Nelson +1
We study algorithms in the resettable streaming model, where the value of each key can either be increased or reset to zero. The model is suitable for applications such as active r…
Tight Bounds for Answering Adaptively Chosen Concentrated Queries
Emma Rapoport, Edith Cohen, Uri Stemmer
Most work on adaptive data analysis assumes that samples in the dataset are independent. When correlations are allowed, even the non-adaptive setting can become intractable, unless…
Hot PATE: Private Aggregation of Distributions for Diverse Task
Edith Cohen, Benjamin Cohen-Wang, Xin Lyu +3
The Private Aggregation of Teacher Ensembles (PATE) framework enables privacy-preserving machine learning by aggregating responses from disjoint subsets of sensitive data. Adaptati…