中文
相关论文

相关论文: Statistical Query Lower Bounds for Robust Estimati…

200 篇论文

We study the complexity of learning mixtures of separated Gaussians with common unknown bounded covariance matrix. Specifically, we focus on learning Gaussian mixture models (GMMs) on $\mathbb{R}^d$ of the form $P= \sum_{i=1}^k w_i…

机器学习 · 计算机科学 2023-06-23 Ilias Diakonikolas , Daniel M. Kane , Thanasis Pittas , Nikos Zarifis

We study the complexity of smoothed agnostic learning, recently introduced by~\cite{CKKMS24}, in which the learner competes with the best classifier in a target class under slight Gaussian perturbations of the inputs. Specifically, we focus…

机器学习 · 计算机科学 2026-02-25 Ilias Diakonikolas , Daniel M. Kane

We study the problem of learning mixtures of linear classifiers under Gaussian covariates. Given sample access to a mixture of $r$ distributions on $\mathbb{R}^n$ of the form $(\mathbf{x},y_{\ell})$, $\ell\in [r]$, where…

机器学习 · 计算机科学 2023-10-19 Ilias Diakonikolas , Daniel M. Kane , Yuxin Sun

We study the problem of estimating the mean of an identity covariance Gaussian in the truncated setting, in the regime when the truncation set comes from a low-complexity family $\mathcal{C}$ of sets. Specifically, for a fixed but unknown…

数据结构与算法 · 计算机科学 2024-03-05 Ilias Diakonikolas , Daniel M. Kane , Thanasis Pittas , Nikos Zarifis

We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces with Random Classification Noise under the Gaussian distribution. We establish nearly-matching algorithmic and Statistical Query (SQ) lower bound…

机器学习 · 计算机科学 2023-07-18 Ilias Diakonikolas , Jelena Diakonikolas , Daniel M. Kane , Puqian Wang , Nikos Zarifis

We consider the well-studied problem of learning intersections of halfspaces under the Gaussian distribution in the challenging \emph{agnostic learning} model. Recent work of Diakonikolas et al. (2021) shows that any Statistical Query (SQ)…

机器学习 · 计算机科学 2022-02-11 Daniel Hsu , Clayton Sanford , Rocco Servedio , Emmanouil-Vasileios Vlatakis-Gkaragkounis

Efficiently learning mixture of Gaussians is a fundamental problem in statistics and learning theory. Given samples coming from a random one out of k Gaussian distributions in Rn, the learning problem asks to estimate the means and the…

机器学习 · 计算机科学 2015-03-11 Rong Ge , Qingqing Huang , Sham M. Kakade

We study the problem of high-dimensional linear regression in a robust model where an $\epsilon$-fraction of the samples can be adversarially corrupted. We focus on the fundamental setting where the covariates of the uncorrupted samples are…

机器学习 · 计算机科学 2018-06-04 Ilias Diakonikolas , Weihao Kong , Alistair Stewart

We study the complexity of learning $k$-mixtures of Gaussians ($k$-GMMs) on $\mathbb{R}^d$. This task is known to have complexity $d^{\Omega(k)}$ in full generality. To circumvent this exponential lower bound on the number of components,…

机器学习 · 计算机科学 2025-04-22 Ilias Diakonikolas , Daniel M. Kane , Sushrut Karmalkar , Jasper C. H. Lee , Thanasis Pittas

In this paper, we study the problem of learning one-dimensional Gaussian mixture models (GMMs) with a specific focus on estimating both the model order and the mixing distribution from independent and identically distributed (i.i.d.)…

机器学习 · 统计学 2026-02-24 Xinyu Liu , Hai Zhang

In this paper, we study the problem of learning multi-dimensional Gaussian Mixture Models (GMMs), with a specific focus on model order selection and efficient mixing distribution estimation. We first establish an information-theoretic lower…

机器学习 · 统计学 2026-03-23 Xinyu Liu , Hai Zhang

We study the fundamental problems of agnostically learning halfspaces and ReLUs under Gaussian marginals. In the former problem, given labeled examples $(\mathbf{x}, y)$ from an unknown distribution on $\mathbb{R}^d \times \{ \pm 1\}$,…

机器学习 · 计算机科学 2020-06-30 Ilias Diakonikolas , Daniel M. Kane , Nikos Zarifis

We establish optimal Statistical Query (SQ) lower bounds for robustly learning certain families of discrete high-dimensional distributions. In particular, we show that no efficient SQ algorithm with access to an $\epsilon$-corrupted binary…

数据结构与算法 · 计算机科学 2022-06-10 Ilias Diakonikolas , Daniel M. Kane , Yuxin Sun

Given data drawn from a mixture of multivariate Gaussians, a basic problem is to accurately estimate the mixture parameters. We give an algorithm for this problem that has a running time, and data requirement polynomial in the dimension and…

机器学习 · 计算机科学 2010-04-27 Ankur Moitra , Gregory Valiant

We use the Sum of Squares method to develop new efficient algorithms for learning well-separated mixtures of Gaussians and robust mean estimation, both in high dimensions, that substantially improve upon the statistical guarantees achieved…

数据结构与算法 · 计算机科学 2017-11-21 Samuel B. Hopkins , Jerry Li

We study the complexity of Non-Gaussian Component Analysis (NGCA) in the Statistical Query (SQ) model. Prior work developed a general methodology to prove SQ lower bounds for this task that have been applicable to a wide range of contexts.…

机器学习 · 计算机科学 2024-03-08 Ilias Diakonikolas , Daniel Kane , Lisheng Ren , Yuxin Sun

This work represents a natural coalescence of two important lines of work: learning mixtures of Gaussians and algorithmic robust statistics. In particular we give the first provably robust algorithm for learning mixtures of any constant…

数据结构与算法 · 计算机科学 2021-07-27 Allen Liu , Ankur Moitra

This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and…

计算复杂性 · 计算机科学 2020-05-20 Matthew Brennan , Guy Bresler

While several papers have investigated computationally and statistically efficient methods for learning Gaussian mixtures, precise minimax bounds for their statistical performance as well as fundamental limits in high-dimensional settings…

机器学习 · 统计学 2013-06-11 Martin Azizyan , Aarti Singh , Larry Wasserman

We study the efficient learnability of high-dimensional Gaussian mixtures in the outlier-robust setting, where a small constant fraction of the data is adversarially corrupted. We resolve the polynomial learnability of this problem when the…

数据结构与算法 · 计算机科学 2020-05-14 Ilias Diakonikolas , Samuel B. Hopkins , Daniel Kane , Sushrut Karmalkar
‹ 上一页 1 2 3 10 下一页 ›