paper-with-me

홈 › Papers

Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity

2026-06-25 · Haitong Liu, Deepak Narayanan Sridharan, David Steurer, Manuel Wiedmer arxiv

We study the fundamental problem of learning a high-dimensional Gaussian truncated to an unknown halfspace. Lee, Mehrotra and Zampetakis (FOCS'24) recently obtained the first polynomial time algorithm for this problem, but their resulting sample and time complexity bounds are not optimal. Under non-trivial truncation, for any target accuracy $\varepsilon > 0$ and dimension $d$ we give an efficient algorithm that uses $n = \tilde{O}(d^2/\varepsilon^2)$ samples and learns the underlying Gaussian to error $\varepsilon$ in total variation distance. Our algorithm is also fast: its runtime is dominated by the cost of computing the empirical covariance matrix. Both our sample and time complexity are optimal in terms of $d$ and $\varepsilon$ even without truncation: in this regard, we can learn a Gaussian under halfspace truncation for free. The key ingredient behind our result is a novel reinterpretation of the low-degree moments of the truncated Gaussian in terms of a relative truncation parameter. This relative truncation parameter uniquely determines the parameters of the untruncated Gaussian and enables direct parameter recovery. This reinterpretation allows us to circumvent the time intensive projected stochastic gradient descent procedure that is widely used in learning under truncation.

📄 PDF Abstract BibTeX arXiv:2606.27298

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time

2023-11-02 · NeurIPS 2023 11

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…

Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians

2024-10-02 · Jane H. Lee, Anay Mehrotra, Manolis Zampetakis

We study the estimation of distributional parameters when samples are shown only if they fall in some unknown set $S \subseteq \mathbb{R}^d$. Kontonis, Tzamos, and Zampetakis (FOCS'19) gave a $d^{\mathrm{poly}(1/\varepsi…

PAC learning

Efficient Truncated Statistics with Unknown Truncation

2019-08-02 · Vasilis Kontonis, Christos Tzamos, Manolis Zampetakis

We study the problem of estimating the parameters of a Gaussian distribution when samples are only shown if they fall in some (unknown) subset $S \subseteq \R^d$. This core problem in truncated statistics has long histor…

Learning General Halfspaces with General Massart Noise under the Gaussian Distribution

2021-08-19 · Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis, Christos Tzamos 외

We study the problem of PAC learning halfspaces on $\mathbb{R}^d$ with Massart noise under the Gaussian distribution. In the Massart model, an adversary is allowed to flip the label of each point $\mathbf{x}$ with unknow…

PAC learning

Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals

2023-02-13 · Ilias Diakonikolas, Daniel M. Kane, Lisheng Ren

We study the task of agnostically learning halfspaces under the Gaussian distribution. Specifically, given labeled examples $(\mathbf{x},y)$ from an unknown distribution on $\mathbb{R}^n \times \{ \pm 1\}$, whose margina…

regression