A faster and simpler algorithm for learning shallow networks
- URL: http://arxiv.org/abs/2307.12496v1
- Date: Mon, 24 Jul 2023 03:04:10 GMT
- Title: A faster and simpler algorithm for learning shallow networks
- Authors: Sitan Chen, Shyam Narayanan
- Abstract summary: We revisit the well-studied problem of learning a linear combination of $k$ ReLU activations given labeled examples.
Here we show that a simpler one-stage version of their algorithm suffices, and moreover its runtime is only $(d/varepsilon)O(k2)$.
- Score: 10.595936992218856
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We revisit the well-studied problem of learning a linear combination of $k$
ReLU activations given labeled examples drawn from the standard $d$-dimensional
Gaussian measure. Chen et al. [CDG+23] recently gave the first algorithm for
this problem to run in $\text{poly}(d,1/\varepsilon)$ time when $k = O(1)$,
where $\varepsilon$ is the target error. More precisely, their algorithm runs
in time $(d/\varepsilon)^{\mathrm{quasipoly}(k)}$ and learns over multiple
stages. Here we show that a much simpler one-stage version of their algorithm
suffices, and moreover its runtime is only $(d/\varepsilon)^{O(k^2)}$.
Related papers
- Mini-Batch Kernel $k$-means [4.604003661048267]
A single iteration of our algorithm takes $widetildeO(kb2)$ time, significantly faster than the $O(n2)$ time required by the full batch kernel $k$-means.
Experiments demonstrate that our algorithm consistently achieves a 10-100x speedup with minimal loss in quality.
arXiv Detail & Related papers (2024-10-08T10:59:14Z) - Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians [7.04316974339151]
We study the estimation of distributional parameters when samples are shown only if they fall in some unknown set.
We develop tools that may be of independent interest, including a reduction from PAC learning with positive and unlabeled samples to PAC learning with positive and negative samples.
arXiv Detail & Related papers (2024-10-02T15:21:07Z) - A Scalable Algorithm for Individually Fair K-means Clustering [77.93955971520549]
We present a scalable algorithm for the individually fair ($p$, $k$)-clustering problem introduced by Jung et al. and Mahabadi et al.
A clustering is then called individually fair if it has centers within distance $delta(x)$ of $x$ for each $xin P$.
We show empirically that not only is our algorithm much faster than prior work, but it also produces lower-cost solutions.
arXiv Detail & Related papers (2024-02-09T19:01:48Z) - Efficiently Learning One-Hidden-Layer ReLU Networks via Schur
Polynomials [50.90125395570797]
We study the problem of PAC learning a linear combination of $k$ ReLU activations under the standard Gaussian distribution on $mathbbRd$ with respect to the square loss.
Our main result is an efficient algorithm for this learning task with sample and computational complexity $(dk/epsilon)O(k)$, whereepsilon>0$ is the target accuracy.
arXiv Detail & Related papers (2023-07-24T14:37:22Z) - Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix
Factorization [54.29685789885059]
We introduce efficient $(1+varepsilon)$-approximation algorithms for the binary matrix factorization (BMF) problem.
The goal is to approximate $mathbfA$ as a product of low-rank factors.
Our techniques generalize to other common variants of the BMF problem.
arXiv Detail & Related papers (2023-06-02T18:55:27Z) - Most Neural Networks Are Almost Learnable [52.40331776572531]
We show that for any fixed $epsilon>0$ and depth $i$, there is a poly-time algorithm that learns random Xavier networks of depth $i$.
The algorithm runs in time and sample complexity of $(bard)mathrmpoly(epsilon-1)$, where $bar d$ is the size of the network.
For some cases of sigmoid and ReLU-like activations the bound can be improved to $(bard)mathrmpolylog(eps
arXiv Detail & Related papers (2023-05-25T22:27:42Z) - Sketching Algorithms and Lower Bounds for Ridge Regression [65.0720777731368]
We give a sketching-based iterative algorithm that computes $1+varepsilon$ approximate solutions for the ridge regression problem.
We also show that this algorithm can be used to give faster algorithms for kernel ridge regression.
arXiv Detail & Related papers (2022-04-13T22:18:47Z) - On Efficient Low Distortion Ultrametric Embedding [18.227854382422112]
A widely-used method to preserve the underlying hierarchical structure of the data is to find an embedding of the data into a tree or an ultrametric.
In this paper, we provide a new algorithm which takes as input a set of points isometric in $mathbbRd2 (for universal constant $rho>1$) to output an ultrametric $Delta.
We show that the output of our algorithm is comparable to the output of the linkage algorithms while achieving a much faster running time.
arXiv Detail & Related papers (2020-08-15T11:06:45Z) - Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample
Complexity [59.34067736545355]
Given an MDP with $S$ states, $A$ actions, the discount factor $gamma in (0,1)$, and an approximation threshold $epsilon > 0$, we provide a model-free algorithm to learn an $epsilon$-optimal policy.
For small enough $epsilon$, we show an improved algorithm with sample complexity.
arXiv Detail & Related papers (2020-06-06T13:34:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.