Search Results for author:
Found 18 papers, 7 papers with code
Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm
We provide a function space characterization of the inductive bias resulting from minimizing the $\ell_2$ norm of the weights in multi-channel convolutional neural networks with linear activations and empirically test our resulting hypothesis on ReLU networks trained using gradient descent.
A Study of Performance of Optimal Transport
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
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.
Scaling up Kernel Ridge Regression via Locality Sensitive Hashing
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.
Randomized Smoothing of All Shapes and Sizes
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
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
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
In this paper, we employ adversarial training to improve the performance of randomized smoothing.
SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Search
In this paper, we introduce SANNS, a system for secure $k$-NNS that keeps client's query and the search result confidential.
Learning Space Partitions for Nearest Neighbor Search
Space partitions of $\mathbb{R}^d$ underlie a vast and important class of fast nearest neighbor search (NNS) algorithms.
Adversarial Examples from Cryptographic Pseudo-Random Generators
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.
Nonlinear Dimension Reduction via Outer Bi-Lipschitz Extensions
We introduce and study the notion of an outer bi-Lipschitz extension of a map between Euclidean spaces.
Performance of Johnson-Lindenstrauss Transform for k-Means and k-Medians Clustering
Further, the cost of every clustering is preserved within $(1+\varepsilon)$.
Approximate Nearest Neighbor Search in High Dimensions
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
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.
Practical Data-Dependent Metric Compression with Provable Guarantees
We introduce a new distance-preserving compact representation of multi-dimensional point-sets.
Approximate Near Neighbors for General Symmetric Norms
We show that every symmetric normed space admits an efficient nearest neighbor search data structure with doubly-logarithmic approximation.
On the Complexity of Inner Product Similarity Join
* New upper and lower bounds for (A)LSH-based algorithms.
Practical and Optimal LSH for Angular Distance
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.
