English
Related papers

Related papers: Lower bounds on the performance of polynomial-time…

200 papers

We study the fundamental tradeoffs between statistical accuracy and computational tractability in the analysis of high dimensional heterogeneous data. As examples, we study sparse Gaussian mixture model, mixture of sparse linear…

Statistics Theory · Mathematics 2018-08-22 Jianqing Fan , Han Liu , Zhaoran Wang , Zhuoran Yang

In this paper, we initiate a systematic investigation of differentially private algorithms for convex empirical risk minimization. Various instantiations of this problem have been studied before. We provide new algorithms and matching lower…

Machine Learning · Computer Science 2014-10-21 Raef Bassily , Adam Smith , Abhradeep Thakurta

This paper considers estimation of sparse covariance matrices and establishes the optimal rate of convergence under a range of matrix operator norm and Bregman divergence losses. A major focus is on the derivation of a rate sharp minimax…

Statistics Theory · Mathematics 2013-02-14 T. Tony Cai , Harrison H. Zhou

The research area of algorithms with predictions has seen recent success showing how to incorporate machine learning into algorithm design to improve performance when the predictions are correct, while retaining worst-case guarantees when…

Machine Learning · Computer Science 2022-12-06 Michael Dinitz , Sungjin Im , Thomas Lavastida , Benjamin Moseley , Sergei Vassilvitskii

We consider the problem of dictionary learning under the assumption that the observed signals can be represented as sparse linear combinations of the columns of a single large dictionary matrix. In particular, we analyze the minimax risk of…

Machine Learning · Statistics 2014-06-30 Alexander Jung , Yonina C. Eldar , Norbert Görtz

Systems with stochastic time delay between the input and output present a number of unique challenges. Time domain noise leads to irregular alignments, obfuscates relationships and attenuates inferred coefficients. To handle these…

Methodology · Statistics 2021-11-15 Juan Camilo Orduz , Aaron Pickering

We consider a class of optimization problems that involve determining the maximum value that a function in a particular class can attain subject to a collection of difference constraints. We show that a particular linear programming…

Data Structures and Algorithms · Computer Science 2022-11-16 Sungjin Im , Benjamin Moseley , Hung Q. Ngo , Kirk Pruhs , Alireza Samadian

An approach to obtaining a parsimonious polynomial model from time series is proposed. An optimal minimal nonuniform time series embedding schema is used to obtain a time delay kernel. This scheme recursively optimizes an objective…

Chaotic Dynamics · Physics 2014-05-13 Chetan Nichkawde

The aim of sparse approximation is to estimate a sparse signal according to the measurement matrix and an observation vector. It is widely used in data analytics, image processing, and communication, etc. Up to now, a lot of research has…

Signal Processing · Electrical Eng. & Systems 2018-05-31 Hao Wang , Ruibin Feng , Chi-Sing Leung

Motivated by recent work on stochastic gradient descent methods, we develop two stochastic variants of greedy algorithms for possibly non-convex optimization problems with sparsity constraints. We prove linear convergence in expectation to…

Numerical Analysis · Mathematics 2014-07-02 Nam Nguyen , Deanna Needell , Tina Woolf

We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be computationally intractable in the worst-case. A major open problem is to understand the…

Machine Learning · Computer Science 2017-08-15 Surbhi Goel , Adam Klivans

Although the standard formulations of prediction problems involve fully-observed and noiseless data drawn in an i.i.d. manner, many applications involve noisy and/or missing data, possibly involving dependence, as well. We study these…

Statistics Theory · Mathematics 2015-03-19 Po-Ling Loh , Martin J. Wainwright

Traditional machine learning methods usually minimize a simple loss function to learn a predictive model, and then use a complex performance measure to measure the prediction performance. However, minimizing a simple loss function cannot…

Machine Learning · Computer Science 2015-11-19 Ning Zhang , Prathamesh Chandrasekar

Principal components analysis (PCA) is the optimal linear auto-encoder of data, and it is often used to construct features. Enforcing sparsity on the principal components can promote better generalization, while improving the…

Machine Learning · Computer Science 2015-02-25 Malik Magdon-Ismail , Christos Boutsidis

The paper considers model selection in regression under the additional structural constraints on admissible models where the number of potential predictors might be even larger than the available sample size. We develop a Bayesian formalism…

Statistics Theory · Mathematics 2013-02-19 Felix Abramovich , Vadim Grinshtein

We study the algorithmic problem of sparse mean estimation in the presence of adversarial outliers. Specifically, the algorithm observes a \emph{corrupted} set of samples from $\mathcal{N}(\mu,\mathbf{I}_d)$, where the unknown mean $\mu \in…

Data Structures and Algorithms · Computer Science 2024-03-08 Ankit Pensia

The celebrated result of Kabanets and Impagliazzo (Computational Complexity, 2004) showed that PIT algorithms imply circuit lower bounds, and vice versa. Since then it has been a major challenge to understand the precise connections between…

Computational Complexity · Computer Science 2025-08-19 Robert Andrews , Deepanshu Kush , Roei Tell

Conditions ensuring optimal parameter estimation in the presence of missing data are well established in inference, typically relying on the Missing-at-Random (MAR) assumption. In prediction, similar principles are often assumed to apply.…

Methodology · Statistics 2026-03-19 Pierre Catoire , Robin Genuer , Cecile Proust-Lima

We study minimax rates for denoising simultaneously sparse and low rank matrices in high dimensions. We show that an iterative thresholding algorithm achieves (near) optimal rates adaptively under mild conditions for a large class of loss…

Statistics Theory · Mathematics 2014-05-05 Dan Yang , Zongming Ma , Andreas Buja

The iterations of many sparse estimation algorithms are comprised of a fixed linear filter cascaded with a thresholding nonlinearity, which collectively resemble a typical neural network layer. Consequently, a lengthy sequence of algorithm…

Machine Learning · Computer Science 2016-05-11 Bo Xin , Yizhou Wang , Wen Gao , David Wipf
‹ Prev 1 4 5 6 7 8 10 Next ›