English
Related papers

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

200 papers

The quest for an algorithm that solves an $n\times n$ linear system in $O(n^2)$ time complexity, or $O(n^2 \text{poly}(1/\epsilon))$ when solving up to $\epsilon$ relative error, is a long-standing open problem in numerical linear algebra…

Numerical Analysis · Mathematics 2026-05-26 Michał Dereziński , Yuji Nakatsukasa , Elizaveta Rebrova

We describe an algorithm that learns two-layer residual units using rectified linear unit (ReLU) activation: suppose the input $\mathbf{x}$ is from a distribution with support space $\mathbb{R}^d$ and the ground-truth generative model is a…

Machine Learning · Computer Science 2022-12-13 Zhunxuan Wang , Linyun He , Chunchuan Lyu , Shay B. Cohen

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 develop a technique to design efficiently computable estimators for sparse linear regression in the simultaneous presence of two adversaries: oblivious and adaptive. We design several robust algorithms that outperform the state of the…

Machine Learning · Computer Science 2024-11-01 Chih-Hung Liu , Gleb Novikov

Consider a set $P$ of $n$ points picked uniformly and independently from $[0,1]^d$ for a constant dimension $d$ -- such a point set is extremely well behaved in many aspects. For example, for a fixed $r \in [0,1]$, we prove a new…

Computational Geometry · Computer Science 2023-11-01 Sariel Har-Peled , Elfarouk Harb

$k$-means++ is an important algorithm for choosing initial cluster centers for the $k$-means clustering algorithm. In this work, we present a new algorithm that can solve the $k$-means++ problem with nearly optimal running time. Given $n$…

Data Structures and Algorithms · Computer Science 2024-02-15 Jiehao Liang , Somdeb Sarkhel , Zhao Song , Chenbo Yin , Junze Yin , Danyang Zhuo

This work considers the problem of learning the Markov parameters of a linear system from observed data. Recent non-asymptotic system identification results have characterized the sample complexity of this problem in the single and…

Optimization and Control · Mathematics 2021-12-09 Han Wang , James Anderson

Learning a Gaussian mixture model (GMM) is a fundamental problem in machine learning, learning theory, and statistics. One notion of learning a GMM is proper learning: here, the goal is to find a mixture of $k$ Gaussians $\mathcal{M}$ that…

Data Structures and Algorithms · Computer Science 2015-06-04 Jerry Li , Ludwig Schmidt

For the constrained 2-means problem, we present a $O\left(dn+d({1\over\epsilon})^{O({1\over \epsilon})}\log n\right)$ time algorithm. It generates a collection $U$ of approximate center pairs $(c_1, c_2)$ such that one of pairs in $U$ can…

Computational Geometry · Computer Science 2018-08-14 Qilong Feng , Bin Fu

We revisit the problem of robust linear regression under Gaussian covariates with an unknown covariance matrix of condition number $\kappa$. For this fundamental problem, significant gaps remain in our understanding of the trade-offs among…

Data Structures and Algorithms · Computer Science 2026-05-19 Deeksha Adil , Jarosław Błasiok , Hongjie Chen , Deepak Narayanan Sridharan

We provide efficient replicable algorithms for the problem of learning large-margin halfspaces. Our results improve upon the algorithms provided by Impagliazzo, Lei, Pitassi, and Sorrell [STOC, 2022]. We design the first…

Machine Learning · Computer Science 2025-10-15 Alkis Kalavasis , Amin Karbasi , Kasper Green Larsen , Grigoris Velegkas , Felix Zhou

Clustering is a fundamental problem in unsupervised machine learning with many applications in data analysis. Popular clustering algorithms such as Lloyd's algorithm and $k$-means++ can take $\Omega(ndk)$ time when clustering $n$ points in…

Machine Learning · Computer Science 2023-10-26 Moses Charikar , Monika Henzinger , Lunjia Hu , Maxmilian Vötsch , Erik Waingarten

In a neural network with ReLU activations, the number of piecewise linear regions in the output can grow exponentially with depth. However, this is highly unlikely to happen when the initial parameters are sampled randomly, which therefore…

Machine Learning · Computer Science 2025-10-17 Max Milkert , David Hyde , Forrest Laine

Understanding when neural networks can be learned efficiently is a fundamental question in learning theory. Existing hardness results suggest that assumptions on both the input distribution and the network's weights are necessary for…

Machine Learning · Computer Science 2023-10-05 Amit Daniely , Nathan Srebro , Gal Vardi

The NP-hard problem of optimizing a shallow ReLU network can be characterized as a combinatorial search over each training example's activation pattern followed by a constrained convex problem given a fixed set of activation patterns. We…

Machine Learning · Computer Science 2022-10-04 Michael Matena , Colin Raffel

We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the…

Data Structures and Algorithms · Computer Science 2018-04-24 Surbhi Goel , Adam Klivans

We present a novel approach to finding the $k$-sink on dynamic path networks with general edge capacities. Our first algorithm runs in $O(n \log n + k^2 \log^4 n)$ time, where $n$ is the number of vertices on the given path, and our second…

Data Structures and Algorithms · Computer Science 2016-09-07 Binay Bhattacharya , Mordecai J. Golin , Yuya Higashikawa , Tsunehiko Kameda , Naoki Katoh

We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be computationally intractable in the worst-case. A major open problem is to understand the…

Machine Learning · Computer Science 2017-08-15 Surbhi Goel , Adam Klivans

We consider the dynamic of gradient descent for learning a two-layer neural network. We assume the input $x\in\mathbb{R}^d$ is drawn from a Gaussian distribution and the label of $x$ satisfies $f^{\star}(x) = a^{\top}|W^{\star}x|$, where…

Machine Learning · Computer Science 2020-07-10 Yuanzhi Li , Tengyu Ma , Hongyang R. Zhang

We prove the first superpolynomial lower bounds for learning one-layer neural networks with respect to the Gaussian distribution using gradient descent. We show that any classifier trained using gradient descent with respect to square-loss…

Machine Learning · Computer Science 2020-10-26 Surbhi Goel , Aravind Gollakota , Zhihan Jin , Sushrut Karmalkar , Adam Klivans
‹ Prev 1 3 4 5 6 7 10 Next ›