
Statistical Query Algorithms and LowDegree Tests Are Almost Equivalent
Researchers currently use a number of approaches to predict and substant...
read it

Aligning AI With Shared Human Values
We show how to assess a language model's knowledge of basic concepts of ...
read it

WellConditioned Methods for IllConditioned Systems: Linear Regression with SemiRandom Noise
Classical iterative algorithms for linear system solving and regression ...
read it

Robust and HeavyTailed Mean Estimation Made Simple, via Regret Minimization
We study the problem of estimating the mean of a distribution in high di...
read it

Security and Machine Learning in the Real World
Machine learning (ML) models deployed in many safety and businesscriti...
read it

RL Unplugged: Benchmarks for Offline Reinforcement Learning
Offline methods for reinforcement learning have the potential to help br...
read it

Robust Gaussian Covariance Estimation in NearlyMatrix Multiplication Time
Robust covariance estimation is the following, wellstudied problem in h...
read it

Robust SubGaussian Principal Component Analysis and WidthIndependent Schatten Packing
We develop two methods for the following fundamental statistical task: g...
read it

Entanglement is Necessary for Optimal Quantum Property Testing
There has been a surge of progress in recent years in developing algorit...
read it

Efficient Algorithms for Multidimensional Segmented Regression
We study the fundamental problem of fixed design multidimensional segme...
read it

An empirical investigation of the challenges of realworld reinforcement learning
Reinforcement learning (RL) has proven its worth in a series of artifici...
read it

Learning Structured Distributions From Untrusted Batches: Faster and Simpler
We revisit the problem of learning from untrusted batches introduced by ...
read it

Randomized Smoothing of All Shapes and Sizes
Randomized smoothing is a recently proposed defense against adversarial ...
read it

Positive Semidefinite Programming: Mixed, Parallel, and WidthIndependent
We give the first approximation algorithm for mixed packing and covering...
read it

Finding the Mode of a Kernel Density Estimate
Given points p_1, ..., p_n in R^d, how do we find a point x which maximi...
read it

Learning Mixtures of Linear Regressions in Subexponential Time via Fourier Moments
We consider the problem of learning a mixture of linear regressions (MLR...
read it

LowRank Toeplitz Matrix Estimation via Random UltraSparse Rulers
We study how to estimate a nearly lowrank Toeplitz covariance matrix T ...
read it

Efficiently Learning Structured Distributions from Untrusted Batches
We study the problem, introduced by Qiao and Valiant, of learning from u...
read it

Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection
We study two problems in highdimensional robust statistics: robust mean...
read it

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Recent works have shown the effectiveness of randomized smoothing as a s...
read it

Sample Efficient Toeplitz Covariance Estimation
We study the query complexity of estimating the covariance matrix T of a...
read it

How Hard Is Robust Mean Estimation?
Robust mean estimation is the problem of estimating the mean μ∈R^d of a ...
read it

On Mean Estimation for General Norms with Statistical Queries
We study the problem of mean estimation for highdimensional distributio...
read it

Spectral Signatures in Backdoor Attacks
A recent line of work has uncovered a new form of data poisoning: socal...
read it

TwinGAN  Unpaired CrossDomain Image Translation with WeightSharing GANs
We present a framework for translating unlabeled images from one domain ...
read it

Privately Learning HighDimensional Distributions
We design nearly optimal differentially private algorithms for learning ...
read it

Byzantine Stochastic Gradient Descent
This paper studies the problem of distributed stochastic optimization in...
read it

Sever: A Robust MetaAlgorithm for Stochastic Optimization
In high dimensions, most machine learning methods are brittle to even a ...
read it

Fast and Sample NearOptimal Algorithms for Learning Multidimensional Histograms
We study the problem of robustly learning multidimensional histograms. ...
read it

Mixture Models, Robustness, and Sum of Squares Proofs
We use the Sum of Squares method to develop new efficient algorithms for...
read it

Robustly Learning a Gaussian: Getting Optimal Error, Efficiently
We study the fundamental problem of learning the parameters of a highdi...
read it

Being Robust (in High Dimensions) Can Be Practical
Robust estimation is much more challenging in high dimensions than it is...
read it

The ZipML Framework for Training Models with EndtoEnd Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning
Recently there has been significant interest in training machinelearnin...
read it

Robust Estimators in High Dimensions without the Computational Intractability
We study highdimensional distribution learning in an agnostic setting w...
read it

Lower Bounds for Exact Model Counting and Applications in Probabilistic Databases
The best current methods for exactly computing the number of satisfying ...
read it
Jerry Li
is this you? claim profile