
Private Stochastic Convex Optimization: Optimal Rates in ℓ_1 Geometry
Stochastic convex optimization over an ℓ_1bounded domain is ubiquitous ...
read it

Lossless Compression of Efficient Private Local Randomizers
Locally Differentially Private (LDP) Reports are commonly used for colle...
read it

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling
Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Th...
read it

When is Memorization of Irrelevant Training Data Necessary for HighAccuracy Learning?
Modern machine learning models are complex and frequently encode surpris...
read it

Individual Privacy Accounting via a Renyi Filter
We consider a sequential setting in which a single dataset of individual...
read it

What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation
Deep learning algorithms are wellknown to have a propensity for fitting...
read it

Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
Uniform stability is a notion of algorithmic stability that bounds the w...
read it

Private Stochastic Convex Optimization: Optimal Rates in Linear Time
We study differentially private (DP) algorithms for stochastic convex op...
read it

PAC learning with stable and private predictions
We study binary classification algorithms for which the prediction on an...
read it

Interaction is necessary for distributed learning with privacy or communication constraints
Local differential privacy (LDP) is a model where users send privatized ...
read it

Private Stochastic Convex Optimization with Optimal Rates
We study differentially private (DP) algorithms for stochastic convex op...
read it

Does Learning Require Memorization? A Short Tale about a Long Tail
Stateoftheart results on image recognition tasks are achieved using o...
read it

The advantages of multiple classes for reducing overfitting from test set reuse
Excessive reuse of holdout data can lead to overfitting. However, there ...
read it

High probability generalization bounds for uniformly stable algorithms with nearly optimal rate
Algorithmic stability is a classical approach to understanding and analy...
read it

Generalization Bounds for Uniformly Stable Algorithms
Uniform stability of a learning algorithm is a classical notion of algor...
read it

Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity
Sensitive statistics are often collected across sets of users, with repe...
read it

Learning without Interaction Requires Separation
One of the key resources in largescale learning systems is the number o...
read it

Privacy Amplification by Iteration
Many commonly used learning algorithms work by iteratively updating an i...
read it

Privacypreserving Prediction
Ensuring differential privacy of models learned from sensitive user data...
read it

The Everlasting Database: Statistical Validity at a Fair Price
The problem of handling adaptivity in data analysis, intentional or not,...
read it

Calibrating Noise to Variance in Adaptive Data Analysis
Datasets are often used multiple times and each successive analysis may ...
read it

Generalization for Adaptivelychosen Estimators via Stable Median
Datasets are often reused to perform multiple statistical analyses in an...
read it

Dealing with Range Anxiety in Mean Estimation via Statistical Queries
We give algorithms for estimating the expectation of a given realvalued...
read it

Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back
In stochastic convex optimization the goal is to minimize a convex funct...
read it

A General Characterization of the Statistical Query Complexity
Statistical query (SQ) algorithms are algorithms that have access to an ...
read it

Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy
We describe a framework for designing efficient active learning algorith...
read it

Learning using Local Membership Queries
We introduce a new model of membership query (MQ) learning, where the le...
read it

DistributionIndependent Evolvability of Linear Threshold Functions
Valiant's (2007) model of evolvability models the evolutionary process o...
read it

Agnostic Learning of Monomials by Halfspaces is Hard
We prove the following strong hardness result for learning: Given a dist...
read it
Vitaly Feldman
is this you? claim profile
ML/TCS Researcher, Research Scientist at Google since 2017, Research Scientist at IBM Almaden Research Center from 20072017, Postdoctoral fellow at Harvard University 2007