Search Results for author: Cyrus Rashtchian

Found 14 papers, 6 papers with code

Explainable k-Means and k-Medians Clustering

no code implementations ICML 2020 Michal Moshkovitz, Sanjoy Dasgupta, Cyrus Rashtchian, Nave Frost

In terms of negative results, we show that popular top-down decision tree algorithms may lead to clusterings with arbitrarily large cost, and we prove that any explainable clustering must incur an \Omega(\log k) approximation compared to the optimal clustering.

Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians

no code implementations2 Sep 2021 Sami Davies, Arya Mazumdar, Soumyabrata Pal, Cyrus Rashtchian

Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory.

Learning Theory

Average-Case Communication Complexity of Statistical Problems

no code implementations3 Jul 2021 Cyrus Rashtchian, David P. Woodruff, Peng Ye, Hanlin Zhu

Our motivation is to understand the statistical-computational trade-offs in streaming, sketching, and query-based models.

Approximate Trace Reconstruction

no code implementations12 Dec 2020 Sami Davies, Miklos Z. Racz, Cyrus Rashtchian, Benjamin G. Schiffer

In the usual trace reconstruction problem, the goal is to exactly reconstruct an unknown string of length $n$ after it passes through a deletion channel many times independently, producing a set of traces (i. e., random subsequences of the string).

Robustness and Generalization to Nearest Categories

1 code implementation17 Nov 2020 Yao-Yuan Yang, Cyrus Rashtchian, Ruslan Salakhutdinov, Kamalika Chaudhuri

Prior work shows that robust networks perform well in some out-of-distribution generalization tasks, such as transfer learning and outlier detection.

Adversarial Robustness Classification +6

Unsupervised Embedding of Hierarchical Structure in Euclidean Space

1 code implementation30 Oct 2020 Jinyu Zhao, Yi Hao, Cyrus Rashtchian

To learn the embedding, we revisit using a variational autoencoder with a Gaussian mixture prior, and we show that rescaling the latent space embedding and then applying Ward's linkage-based algorithm leads to improved results for both dendrogram purity and the Moseley-Wang cost function.

Hierarchical structure

Trace Reconstruction Problems in Computational Biology

no code implementations12 Oct 2020 Vinnu Bhardwaj, Pavel A. Pevzner, Cyrus Rashtchian, Yana Safonova

The problem of reconstructing a string from its error-prone copies, the trace reconstruction problem, was introduced by Vladimir Levenshtein two decades ago.

Vector-Matrix-Vector Queries for Solving Linear Algebra, Statistics, and Graph Problems

no code implementations24 Jun 2020 Cyrus Rashtchian, David P. Woodruff, Hanlin Zhu

We consider the general problem of learning about a matrix through vector-matrix-vector queries.

ExKMC: Expanding Explainable $k$-Means Clustering

2 code implementations3 Jun 2020 Nave Frost, Michal Moshkovitz, Cyrus Rashtchian

To allow flexibility, we develop a new explainable $k$-means clustering algorithm, ExKMC, that takes an additional parameter $k' \geq k$ and outputs a decision tree with $k'$ leaves.

LSF-Join: Locality Sensitive Filtering for Distributed All-Pairs Set Similarity Under Skew

no code implementations6 Mar 2020 Cyrus Rashtchian, Aneesh Sharma, David P. Woodruff

Theoretically, we show that LSF-Join efficiently finds most close pairs, even for small similarity thresholds and for skewed input sets.

Recommendation Systems

A Closer Look at Accuracy vs. Robustness

1 code implementation NeurIPS 2020 Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Ruslan Salakhutdinov, Kamalika Chaudhuri

Current methods for training robust networks lead to a drop in test accuracy, which has led prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning.

Explainable $k$-Means and $k$-Medians Clustering

3 code implementations28 Feb 2020 Sanjoy Dasgupta, Nave Frost, Michal Moshkovitz, Cyrus Rashtchian

In terms of negative results, we show, first, that popular top-down decision tree algorithms may lead to clusterings with arbitrarily large cost, and second, that any tree-induced clustering must in general incur an $\Omega(\log k)$ approximation factor compared to the optimal clustering.

Clustering Billions of Reads for DNA Data Storage

no code implementations NeurIPS 2017 Cyrus Rashtchian, Konstantin Makarychev, Miklos Racz, Siena Ang, Djordje Jevdjic, Sergey Yekhanin, Luis Ceze, Karin Strauss

We provide empirical justification of the accuracy, scalability, and convergence of our algorithm on real and synthetic data.

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