Search Results for author: Ilya Razenshteyn

Found 18 papers, 7 papers with code

Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm

1 code implementation24 Feb 2021 Meena Jagadeesan, Ilya Razenshteyn, Suriya Gunasekar

We view this in terms of an induced regularizer in the function space given by the minimum norm of weights required to realize a linear function.

A Study of Performance of Optimal Transport

1 code implementation3 May 2020 Yihe Dong, Yu Gao, Richard Peng, Ilya Razenshteyn, Saurabh Sawlani

We investigate the problem of efficiently computing optimal transport (OT) distances, which is equivalent to the node-capacitated minimum cost maximum flow problem in a bipartite graph.

Non-Adaptive Adaptive Sampling on Turnstile Streams

no code implementations23 Apr 2020 Sepideh Mahabadi, Ilya Razenshteyn, David P. Woodruff, Samson Zhou

Adaptive sampling is a useful algorithmic tool for data summarization problems in the classical centralized setting, where the entire dataset is available to the single processor performing the computation.

Data Summarization

Scaling up Kernel Ridge Regression via Locality Sensitive Hashing

no code implementations21 Mar 2020 Michael Kapralov, Navid Nouri, Ilya Razenshteyn, Ameya Velingker, Amir Zandieh

Random binning features, introduced in the seminal paper of Rahimi and Recht (2007), are an efficient method for approximating a kernel matrix using locality sensitive hashing.

Gaussian Processes

Randomized Smoothing of All Shapes and Sizes

1 code implementation ICML 2020 Greg Yang, Tony Duan, J. Edward Hu, Hadi Salman, Ilya Razenshteyn, Jerry Li

Randomized smoothing is the current state-of-the-art defense with provable robustness against $\ell_2$ adversarial attacks.

Scalable Nearest Neighbor Search for Optimal Transport

1 code implementation ICML 2020 Arturs Backurs, Yihe Dong, Piotr Indyk, Ilya Razenshteyn, Tal Wagner

Our extensive experiments, on real-world text and image datasets, show that Flowtree improves over various baselines and existing methods in either running time or accuracy.

Data Structures and Algorithms

SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Search

no code implementations3 Apr 2019 Hao Chen, Ilaria Chillotti, Yihe Dong, Oxana Poburinnaya, Ilya Razenshteyn, M. Sadegh Riazi

In this paper, we introduce SANNS, a system for secure $k$-NNS that keeps client's query and the search result confidential.

Face Recognition Recommendation Systems

Learning Space Partitions for Nearest Neighbor Search

1 code implementation ICLR 2020 Yihe Dong, Piotr Indyk, Ilya Razenshteyn, Tal Wagner

Space partitions of $\mathbb{R}^d$ underlie a vast and important class of fast nearest neighbor search (NNS) algorithms.

General Classification graph partitioning +1

Adversarial Examples from Cryptographic Pseudo-Random Generators

no code implementations15 Nov 2018 Sébastien Bubeck, Yin Tat Lee, Eric Price, Ilya Razenshteyn

In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805. 10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem.

General Classification

Nonlinear Dimension Reduction via Outer Bi-Lipschitz Extensions

no code implementations8 Nov 2018 Sepideh Mahabadi, Konstantin Makarychev, Yury Makarychev, Ilya Razenshteyn

We introduce and study the notion of an outer bi-Lipschitz extension of a map between Euclidean spaces.

Dimensionality Reduction

Approximate Nearest Neighbor Search in High Dimensions

no code implementations26 Jun 2018 Alexandr Andoni, Piotr Indyk, Ilya Razenshteyn

The nearest neighbor problem is defined as follows: Given a set $P$ of $n$ points in some metric space $(X, D)$, build a data structure that, given any point $q$, returns a point in $P$ that is closest to $q$ (its "nearest neighbor" in $P$).

Adversarial examples from computational constraints

no code implementations25 May 2018 Sébastien Bubeck, Eric Price, Ilya Razenshteyn

First we prove that, for a broad set of classification tasks, the mere existence of a robust classifier implies that it can be found by a possibly exponential-time algorithm with relatively few training examples.

Classification General Classification

Approximate Near Neighbors for General Symmetric Norms

no code implementations18 Nov 2016 Alexandr Andoni, Huy L. Nguyen, Aleksandar Nikolov, Ilya Razenshteyn, Erik Waingarten

We show that every symmetric normed space admits an efficient nearest neighbor search data structure with doubly-logarithmic approximation.

Practical and Optimal LSH for Angular Distance

1 code implementation NeurIPS 2015 Alexandr Andoni, Piotr Indyk, Thijs Laarhoven, Ilya Razenshteyn, Ludwig Schmidt

Our lower bound implies that the above LSH family exhibits a trade-off between evaluation time and quality that is close to optimal for a natural class of LSH functions.

Cannot find the paper you are looking for? You can Submit a new open access paper.