
On the benefits of maximum likelihood estimation for Regression and Forecasting
We advocate for a practical Maximum Likelihood Estimation (MLE) approach...
read it

On the Renyi Differential Privacy of the Shuffle Model
The central question studied in this paper is Renyi Differential Privacy...
read it

CommunicationEfficient Agnostic Federated Averaging
In distributed learning settings such as federated learning, the trainin...
read it

Remember What You Want to Forget: Algorithms for Machine Unlearning
We study the problem of forgetting datapoints from a learnt model. In th...
read it

Learning with UserLevel Privacy
We propose and analyze algorithms to solve a range of learning tasks und...
read it

WynerZiv Estimators: Efficient Distributed Mean Estimation with Side Information
Communication efficient distributed mean estimation is an important prim...
read it

Robust hypothesis testing and distribution estimation in Hellinger distance
We propose a simple robust hypothesis test that has the same sample comp...
read it

MultipleSource Adaptation with Domain Classifiers
We consider the multiplesource adaptation (MSA) problem and improve a p...
read it

Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Tradeoffs
We consider a distributed empirical risk minimization (ERM) optimization...
read it

Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
Federated learning is a challenging optimization problem due to the hete...
read it

Learning discrete distributions: user vs itemlevel privacy
Much of the literature on differential privacy focuses on itemlevel pri...
read it

A Theory of MultipleSource Adaptation with Limited Target Labeled Data
We study multiplesource domain adaptation, when the learner has access ...
read it

Relative Deviation Margin Bounds
We present a series of new and more favorable marginbased learning guar...
read it

Three Approaches for Personalization with Applications to Federated Learning
The standard objective in machine learning is to train a single model fo...
read it

Convergence of Chao Unseen Species Estimator
Support size estimation and the related problem of unseen species estima...
read it

Advances and Open Problems in Federated Learning
Federated learning (FL) is a machine learning setting where many clients...
read it

Can You Really Backdoor Federated Learning?
The decentralized nature of federated learning makes detecting and defen...
read it

SCAFFOLD: Stochastic Controlled Averaging for OnDevice Federated Learning
Federated learning is a key scenario in modern largescale machine learn...
read it

Differentially private anonymized histograms
For a dataset of labelcount pairs, an anonymized histogram is the multi...
read it

Federated Learning of Ngram Language Models
We propose algorithms to train productionquality ngram language models...
read it

AdaCliP: Adaptive Clipping for Private SGD
Privacy preserving machine learning algorithms are crucial for learning ...
read it

Optimal multiclass overfitting by sequence reconstruction from Hamming queries
A primary concern of excessive reuse of test datasets in machine learnin...
read it

Sampled Softmax with Random Fourier Features
The computational cost of training with softmax cross entropy loss grows...
read it

Approximating probabilistic models as weighted finite automata
Weighted finite automata (WFA) are often used to represent probabilistic...
read it

Agnostic Federated Learning
A key learning scenario in largescale applications is that of federated...
read it

WEST: Word Encoded Sequence Transducers
Most of the parameters in large vocabulary models are used in embedding ...
read it

cpSGD: Communicationefficient and differentiallyprivate distributed SGD
Distributed stochastic gradient descent is an important subroutine in di...
read it

Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition
Recurrent neural network (RNN) language models (LMs) and Long Short Term...
read it

ModelPowered Conditional Independence Test
We consider the problem of nonparametric Conditional Independence testi...
read it

Sample complexity of population recovery
The problem of population recovery refers to estimating a distribution b...
read it

Orthogonal Random Features
We present an intriguing discovery related to Random Fourier Features: i...
read it

Estimating the number of unseen species: A bird in the hand is worth n in the bush
Estimating the number of unseen species is an important problem in many ...
read it

Nearoptimalsample estimators for spherical Gaussian mixtures
Statistical and machinelearning algorithms are frequently applied to hi...
read it
Ananda Theertha Suresh
is this you? claim profile