
Inductive Bias of MultiChannel Linear Convolutional Networks with Bounded Weight Norm
We study the function space characterization of the inductive bias resul...
read it

A Study of Performance of Optimal Transport
We investigate the problem of efficiently computing optimal transport (O...
read it

NonAdaptive Adaptive Sampling on Turnstile Streams
Adaptive sampling is a useful algorithmic tool for data summarization pr...
read it

Scaling up Kernel Ridge Regression via Locality Sensitive Hashing
Random binning features, introduced in the seminal paper of Rahimi and R...
read it

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

Scalable Nearest Neighbor Search for Optimal Transport
The Optimal Transport (a.k.a. Wasserstein) distance is an increasingly p...
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

SANNS: Scaling Up Secure Approximate kNearest Neighbors Search
We present new secure protocols for approximate knearest neighbor searc...
read it

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

Learning SublinearTime Indexing for Nearest Neighbor Search
Most of the efficient sublineartime indexing algorithms for the highdi...
read it

Learning Space Partitions for Nearest Neighbor Search
Space partitions of R^d underlie a vast and important class of fast near...
read it

Adversarial Examples from Cryptographic PseudoRandom Generators
In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we arg...
read it

Nonlinear Dimension Reduction via Outer BiLipschitz Extensions
We introduce and study the notion of an outer biLipschitz extension of ...
read it

Performance of JohnsonLindenstrauss Transform for kMeans and kMedians Clustering
Consider an instance of Euclidean kmeans or kmedians clustering. We sh...
read it

Approximate Nearest Neighbor Search in High Dimensions
The nearest neighbor problem is defined as follows: Given a set P of n p...
read it

Adversarial examples from computational constraints
Why are classifiers in high dimension vulnerable to "adversarial" pertur...
read it

Practical DataDependent Metric Compression with Provable Guarantees
We introduce a new distancepreserving compact representation of multid...
read it
Ilya Razenshteyn
is this you? claim profile