paper-with-me

Papers

A Strongly Polynomial Algorithm for Approximate Forster Transforms and its Application to Halfspace Learning

2022-12-06 · Ilias Diakonikolas, Christos Tzamos, Daniel M. Kane

The Forster transform is a method of regularizing a dataset by placing it in {\em radial isotropic position} while maintaining some of its essential properties. Forster transforms have played a key role in a diverse range of settings spanning computer science and functional analysis. Prior work had given {\em weakly} polynomial time algorithms for computing Forster transforms, when they exist. Our main result is the first {\em strongly polynomial time} algorithm to compute an approximate Forster transform of a given dataset or certify that no such transformation exists. By leveraging our strongly polynomial Forster algorithm, we obtain the first strongly polynomial time algorithm for {\em distribution-free} PAC learning of halfspaces. This learning result is surprising because {\em proper} PAC learning of halfspaces is {\em equivalent} to linear programming. Our learning approach extends to give a strongly polynomial halfspace learner in the presence of random classification noise and, more generally, Massart noise.

📄 PDF Abstract BibTeX arXiv:2212.03008

Code (0)

등록된 구현이 없습니다.

Tasks

PAC learning

Similar Papers 제목 키워드 기반

Forster Decomposition and Learning Halfspaces with Noise

2021-07-12 · NeurIPS 2021 12 · Ilias Diakonikolas, Daniel M. Kane, Christos Tzamos

A Forster transform is an operation that turns a distribution into one with good anti-concentration properties. While a Forster transform does not always exist, we show that any distribution can be efficiently decomposed…

PAC learning

Strongly polynomial efficient approximation scheme for segmentation

2018-05-28 · Nikolaj Tatti

Partitioning a sequence of length $n$ into $k$ coherent segments (Seg) is one of the classic optimization problems. As long as the optimization criterion is additive, Seg can be solved exactly in $O(n^2k)$ time using a c…

2kSegmentation

Strongly Polynomial Time Complexity of Policy Iteration for $L_\infty$ Robust MDPs

2026-01-30 · Ali Asadi, Krishnendu Chatterjee, Ehsan Goharshady, Mehrdad Karrabi 외 arxiv

Markov decision processes (MDPs) are a fundamental model in sequential decision making. Robust MDPs (RMDPs) extend this framework by allowing uncertainty in transition probabilities and optimizing against the worst-case …

Decision Making

Discrete Optimal Transport with Independent Marginals is #P-Hard

2022-03-02 · Bahar Taşkesen, Soroosh Shafieezadeh-Abadeh, Daniel Kuhn, Karthik Natarajan

We study the computational complexity of the optimal transport problem that evaluates the Wasserstein distance between the distributions of two K-dimensional discrete random vectors. The best known algorithms for this pr…

Optimizing Over All Sequences of Orthogonal Polynomials

2021-01-01 · Shiva Kaul

Every length-$(n+1)$ sequence of orthogonal polynomials is uniquely represented by two length-$(n+1)$ sequences of coefficients $\alpha$ and $\beta$. We make this representation learnable by gradient-based methods. Ortho…

AllComputational Efficiency