Search Results for author:
Found 20 papers, 2 papers with code
Uniqueness of Tensor Decompositions with Applications to Polynomial Identifiability
We give a robust version of the celebrated result of Kruskal on the uniqueness of tensor decompositions: we prove that given a tensor whose decomposition satisfies a robust form of Kruskal's rank condition, it is possible to approximately recover the decomposition if the tensor is known up to a sufficiently small (inverse polynomial) error.
Smoothed Analysis of Tensor Decompositions
We introduce a smoothed analysis model for studying these questions and develop an efficient algorithm for tensor decomposition in the highly overcomplete case (rank polynomial in the dimension).
Relax, no need to round: integrality of clustering formulations
Under the same distributional model, the $k$-means LP relaxation fails to recover such clusters at separation as large as $\Delta = 4$.
Label optimal regret bounds for online local learning
We resolve an open question from (Christiano, 2014b) posed in COLT'14 regarding the optimal dependency of the regret achievable for online local learning on the size of the label set.
Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction
We consider a crowdsourcing model in which $n$ workers are asked to rate the quality of $n$ items previously generated by other workers.
Learning from Untrusted Data
For example, given a dataset of $n$ points for which an unknown subset of $\alpha n$ points are drawn from a distribution of interest, and no assumptions are made about the remaining $(1-\alpha)n$ points, is it possible to return a list of $\operatorname{poly}(1/\alpha)$ answers, one of which is correct?
A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics
We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization.
Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers
We introduce a criterion, resilience, which allows properties of a dataset (such as its mean or best low rank approximation) to be robustly computed, even in the presence of a large fraction of arbitrary additional data.
Hierarchical Clustering with Structural Constraints
For many real-world applications, we would like to exploit prior information about the data that imposes constraints on the clustering hierarchy, and is not captured by the set of features available to the algorithm.
Hierarchical Clustering better than Average-Linkage
Hierarchical Clustering (HC) is a widely studied problem in exploratory data analysis, usually tackled by simple agglomerative procedures like average-linkage, single-linkage or complete-linkage.
A sampling framework for counting temporal motifs
However, there are no algorithms for fast estimation of temporal motifs counts; moreover, we show that even counting simple temporal star motifs is NP-complete.
Social and Information Networks Data Structures and Algorithms
Recovery Guarantees for Quadratic Tensors with Sparse Observations
We consider the tensor completion problem of predicting the missing entries of a tensor.
Efficient Profile Maximum Likelihood for Universal Symmetric Property Estimation
Generalizing work of Acharya et al. 2016 on the utility of approximate PML we show that our algorithm provides a nearly linear time universal plug-in estimator for all symmetric functions up to accuracy $\epsilon = \Omega(n^{-0. 166})$.
A General Framework for Symmetric Property Estimation
In this paper we provide a general framework for estimating symmetric properties of distributions from i. i. d.
The Bethe and Sinkhorn Permanents of Low Rank Matrices and Implications for Profile Maximum Likelihood
For each problem we provide polynomial time algorithms that given $n$ i. i. d.\ samples from a discrete distribution, achieve an approximation factor of $\exp\left(-O(\sqrt{n} \log n) \right)$, improving upon the previous best-known bound achievable in polynomial time of $\exp(-O(n^{2/3} \log n))$ (Charikar, Shiragur and Sidford, 2019).
Instance Based Approximations to Profile Maximum Likelihood
In this paper we provide a new efficient algorithm for approximately computing the profile maximum likelihood (PML) distribution, a prominent quantity in symmetric property estimation.
Near-Optimal Explainable $k$-Means for All Dimensions
Given $d$-dimensional data points, we show an efficient algorithm that finds an explainable clustering whose $k$-means cost is at most $k^{1 - 2/d}\,\mathrm{poly}(d\log k)$ times the minimum cost achievable by a clustering without the explainability constraint, assuming $k, d\ge 2$.
On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood
We provide an efficient unified plug-in approach for estimating symmetric properties of distributions given $n$ independent samples.
A Characterization of List Learnability
In this work we consider list PAC learning where the goal is to output a list of $k$ predictions.
Breaking the Metric Voting Distortion Barrier
To do so we study a handful of voting rules that are new to the problem.
