English
Related papers

Related papers: A faster and simpler algorithm for learning shallo…

200 papers

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. We consider the problem of learning a one hidden layer convolutional neural network with ReLU activation…

Optimization and Control · Mathematics 2020-02-26 Thu Dinh , Jack Xin

The classical work of (Arora et al., 1999) provides a scheme that gives, for any $\epsilon>0$, a polynomial time $1-\epsilon$ approximation algorithm for dense instances of a family of $\mathcal{NP}$-hard problems, such as Max-CUT and…

Data Structures and Algorithms · Computer Science 2024-05-24 Evripidis Bampis , Bruno Escoffier , Michalis Xefteris

We present an algorithm which computes the $D^{th}$ term of a sequence satisfying a linear recurrence relation of order $d$ over a field $K$ in $O( \mathsf{M}(\bar d)\log(D) + \mathsf{M}(d)\log(d))$ operations in $K$, where $\bar d \leq d$…

Symbolic Computation · Computer Science 2018-06-12 Seung Gyu Hyun , Stephen Melczer , Catherine St-Pierre

The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden layer for node information convolution is provided in this paper. Two types of GNNs are investigated, depending on whether labels are attached…

Machine Learning · Computer Science 2020-12-08 Qunwei Li , Shaofeng Zou , Wenliang Zhong

We resolve one of the major outstanding problems in robust statistics. In particular, if $X$ is an evenly weighted mixture of two arbitrary $d$-dimensional Gaussians, we devise a polynomial time algorithm that given access to samples from…

Data Structures and Algorithms · Computer Science 2020-07-14 Daniel M. Kane

Network reconstruction consists in determining the unobserved pairwise couplings between $N$ nodes given only observational data on the resulting behavior that is conditioned on those couplings -- typically a time-series or independent…

Data Structures and Algorithms · Computer Science 2024-05-08 Tiago P. Peixoto

We consider the problem of learning unions of rectangles over the domain $[b]^n$, in the uniform distribution membership query learning setting, where both b and n are "large". We obtain poly$(n, \log b)$-time algorithms for the following…

Machine Learning · Computer Science 2008-09-12 Alp Atici , Rocco A. Servedio

In the area of parameterized complexity, to cope with NP-Hard problems, we introduce a parameter k besides the input size n, and we aim to design algorithms (called FPT algorithms) that run in O(f(k)n^d) time for some function f(k) and…

Data Structures and Algorithms · Computer Science 2013-07-19 Yoichi Iwata , Keigo Oka , Yuichi Yoshida

A graph $G$ is said to be a $(k,\ell)$-graph if its vertex set can be partitioned into $k$ independent sets and $\ell$ cliques. It is well established that the recognition problem for $(k,\ell)$-graphs is NP-complete whenever $k \geq 3$ or…

Discrete Mathematics · Computer Science 2025-10-21 Flavia Bonomo-Braberman , Min Chih Lin , Ignacio Maqueda

Robust mean estimation is one of the most important problems in statistics: given a set of samples in $\mathbb{R}^d$ where an $\alpha$ fraction are drawn from some distribution $D$ and the rest are adversarially corrupted, we aim to…

Machine Learning · Computer Science 2022-12-07 Shiwei Zeng , Jie Shen

$\renewcommand{\Re}{\mathbb{R}} \newcommand{\eps}{\varepsilon} \newcommand{\Net}{S} \newcommand{\tldO}{{\widetilde{O}}} \newcommand{\body}{C} $ We revisit an algorithm of Clarkson etal [CEMST96], that computes (roughly) a…

Computational Geometry · Computer Science 2019-03-01 Sariel Har-Peled , Mitchell Jones

Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints. Instead, in many real-world applications, the constraints are derived from side information, such as…

Machine Learning · Computer Science 2012-03-19 Kaizhu Huang , Rong Jin , Zenglin Xu , Cheng-Lin Liu

We study the sample complexity of learning one-hidden-layer convolutional neural networks (CNNs) with non-overlapping filters. We propose a novel algorithm called approximate gradient descent for training CNNs, and show that, with high…

Machine Learning · Computer Science 2019-11-13 Yuan Cao , Quanquan Gu

Offline reinforcement learning (RL) leverages previously collected data for policy optimization without any further active exploration. Despite the recent interest in this problem, its theoretical results in neural network function…

Machine Learning · Statistics 2022-12-15 Thanh Nguyen-Tang , Sunil Gupta , Hung Tran-The , Svetha Venkatesh

The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights. This observation has prompted the development of…

Machine Learning · Computer Science 2017-08-03 Hao He , Bo Xin , David Wipf

Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We…

We are interested in a framework of online learning with kernels for low-dimensional but large-scale and potentially adversarial datasets. We study the computational and theoretical performance of online variations of kernel Ridge…

Machine Learning · Statistics 2019-05-30 Rémi Jézéquel , Pierre Gaillard , Alessandro Rudi

We study the problem of propagating the mean and covariance of a general multivariate Gaussian distribution through a deep (residual) neural network using layer-by-layer moment matching. We close a longstanding gap by deriving exact moment…

Machine Learning · Computer Science 2026-05-11 Simon Kuang , Xinfan Lin

Nonlinear differential equations exhibit rich phenomena in many fields but are notoriously challenging to solve. Recently, Liu et al. [1] demonstrated the first efficient quantum algorithm for dissipative quadratic differential equations…

Quantum Physics · Physics 2023-11-08 Dong An , Di Fang , Stephen Jordan , Jin-Peng Liu , Guang Hao Low , Jiasu Wang

We present the first $m\,\text{polylog}(n)$ work, $\text{polylog}(n)$ time algorithm in the PRAM model that computes $(1+\epsilon)$-approximate single-source shortest paths on weighted, undirected graphs. This improves upon the breakthrough…

Data Structures and Algorithms · Computer Science 2022-06-02 Jason Li