English
Related papers

Related papers: Polynomial Time and Private Learning of Unbounded …

200 papers

We study a discrete-time portfolio selection problem with partial information and maxi\-mum drawdown constraint. Drift uncertainty in the multidimensional framework is modeled by a prior probability distribution. In this Bayesian framework,…

Portfolio Management · Quantitative Finance 2020-11-02 Carmine De Franco , Johann Nicolle , Huyên Pham

We design new differentially private algorithms for the Euclidean k-means problem, both in the centralized model and in the local model of differential privacy. In both models, our algorithms achieve significantly improved error guarantees…

Data Structures and Algorithms · Computer Science 2018-07-17 Haim Kaplan , Uri Stemmer

We study the task of learning Generalized Linear models (GLMs) in the agnostic model under the Gaussian distribution. We give the first polynomial-time algorithm that achieves a constant-factor approximation for \textit{any} monotone…

Machine Learning · Computer Science 2025-08-05 Nikos Zarifis , Puqian Wang , Ilias Diakonikolas , Jelena Diakonikolas

This work introduces a novel probabilistic deep learning technique called deep Gaussian mixture ensembles (DGMEs), which enables accurate quantification of both epistemic and aleatoric uncertainty. By assuming the data generating process…

Machine Learning · Statistics 2023-06-13 Yousef El-Laham , Niccolò Dalmasso , Elizabeth Fons , Svitlana Vyetrenko

We study the problem of learning mixtures of Gaussians with censored data. Statistical learning with censored data is a classical problem, with numerous practical applications, however, finite-sample guarantees for even simple latent…

Machine Learning · Computer Science 2023-06-30 Wai Ming Tai , Bryon Aragam

This work presents a fast and scalable algorithm for incremental learning of Gaussian mixture models. By performing rank-one updates on its precision matrices and determinants, its asymptotic time complexity is of \BigO{NKD^2} for $N$ data…

Machine Learning · Computer Science 2017-01-17 Rafael Pinto , Paulo Engel

We propose PACE-GGM, a data-adaptive differentially private method for covariance estimation that concentrates its privacy budget on the most informative entries of the empirical covariance matrix, rather than perturbing all entries. This…

Machine Learning · Computer Science 2026-05-26 Cecilia Ferrando , Miguel Fuentes , Brett Mullins , Cameron Musco , Daniel Sheldon

We develop two methods for the following fundamental statistical task: given an $\epsilon$-corrupted set of $n$ samples from a $d$-dimensional sub-Gaussian distribution, return an approximate top eigenvector of the covariance matrix. Our…

Data Structures and Algorithms · Computer Science 2020-06-15 Arun Jambulapati , Jerry Li , Kevin Tian

While generative models have proved successful in many domains, they may pose a privacy leakage risk in practical deployment. To address this issue, differentially private generative model learning has emerged as a solution to train private…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Bochao Liu , Pengju Wang , Weijia Guo , Yong Li , Liansheng Zhuang , Weiping Wang , Shiming Ge

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in…

Cryptography and Security · Computer Science 2019-06-05 NhatHai Phan , Minh Vu , Yang Liu , Ruoming Jin , Dejing Dou , Xintao Wu , My T. Thai

The Gaussian mixture model is widely used in unsupervised learning, owing to its simplicity and interpretability. However, a fundamental limitation of the classical Gaussian mixture model is that it forces each observation to belong to…

Machine Learning · Statistics 2026-04-27 Huan Qing

We present a new subspace-based method to construct probabilistic models for high-dimensional data and highlight its use in anomaly detection. The approach is based on a statistical estimation of probability density using densities of…

Machine Learning · Computer Science 2021-08-16 Cetin Savkli , Catherine Schwartz

We give a polynomial-time algorithm for learning high-dimensional halfspaces with margins in $d$-dimensional space to within desired TV distance when the ambient distribution is an unknown affine transformation of the $d$-fold product of an…

Machine Learning · Computer Science 2023-11-03 Xinyuan Cao , Santosh S. Vempala

The ability to quantify distinctness of a cluster structure is fundamental for certain simulation studies, in particular for those comparing performance of different classification algorithms. The intrinsic integral measure based on the…

Statistics Theory · Mathematics 2014-07-29 Ewa Nowakowska , Jacek Koronacki , Stan Lipovetsky

We develop a near-optimal testing procedure under the framework of Gaussian differential privacy for simple as well as one- and two-sided tests under monotone likelihood ratio conditions. Our mechanism is based on a private mean estimator…

Machine Learning · Statistics 2026-01-30 Yu-Wei Chen , Raghu Pasupathy , Jordan Awan

We consider the problem of efficiently learning mixtures of a large number of spherical Gaussians, when the components of the mixture are well separated. In the most basic form of this problem, we are given samples from a uniform mixture of…

Data Structures and Algorithms · Computer Science 2017-11-01 Oded Regev , Aravindan Vijayaraghavan

We propose a method for learning constraints represented as Gaussian processes (GPs) from locally-optimal demonstrations. Our approach uses the Karush-Kuhn-Tucker (KKT) optimality conditions to determine where on the demonstrations the…

Robotics · Computer Science 2022-03-02 Glen Chou , Hao Wang , Dmitry Berenson

We study the algorithmic task of testably learning general Massart halfspaces under the Gaussian distribution. In the testable learning setting, the aim is the design of a tester-learner pair satisfying the following properties: (1) if the…

Data Structures and Algorithms · Computer Science 2026-02-27 Ilias Diakonikolas , Giannis Iakovidis , Daniel M. Kane , Sihan Liu

Through the lens of information-theoretic reductions, we examine a reductions approach to fair optimization and learning where a black-box optimizer is used to learn a fair model for classification or regression. Quantifying the complexity,…

Machine Learning · Computer Science 2021-05-25 Daniel Alabi

The question of how to determine the number of independent latent factors (topics) in mixture models such as Latent Dirichlet Allocation (LDA) is of great practical importance. In most applications, the exact number of topics is unknown,…

Machine Learning · Statistics 2014-01-23 E. D. Gutiérrez