TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Quantum advantage for learning shallow NNs with natural data distributions

1 点作者 westurner大约 1 个月前

1 comment

westurner大约 1 个月前
ScholarlyArticle: &quot;Quantum advantage for learning shallow neural networks with natural data distributions&quot; (2025) <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2503.20879" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2503.20879</a><p>NewsArticle: &quot;Google Researchers Say Quantum Theory Suggests a Shortcut for Learning Certain Neural Networks&quot; (2025) <a href="https:&#x2F;&#x2F;thequantuminsider.com&#x2F;2025&#x2F;03&#x2F;31&#x2F;google-researchers-say-quantum-theory-suggests-a-shortcut-for-learning-certain-neural-networks&#x2F;" rel="nofollow">https:&#x2F;&#x2F;thequantuminsider.com&#x2F;2025&#x2F;03&#x2F;31&#x2F;google-researchers-...</a> :<p>&gt; <i>Using this model,</i> [Quantum Statistical Query (QSQ) learning,] <i>the authors design a two-part algorithm. First, the quantum algorithm finds the hidden period in the function using a modified form of quantum Fourier transform — a core capability of quantum computers. This step identifies the unknown weight vector that defines the periodic neuron. In the second part, it applies classical gradient descent to learn the remaining parameters of the cosine combination. The algorithm is shown to require only a polynomial number of steps, compared to the exponential cost for classical learners.</i> [...]<p>&gt; <i>The researchers carefully address several technical challenges. For one, real-valued data must be discretized into digital form to use in a quantum computer.</i><p>Quantum embedding:<p>&gt; <i>Another way to put this: real-world numbers must be converted into digital chunks so a quantum computer can process them. But naive discretization can lose the periodic structure, making it impossible to detect the right signal. The authors solve this by designing a</i> pseudoperiodic discretization. <i>This approximates the period well enough for quantum algorithms to detect it.</i><p>&gt; <i>They also adapt an algorithm from quantum number theory called</i> Hallgren’s algorithm <i>to detect non-integer periods in the data. While Hallgren’s method originally worked only for uniform distributions, the authors generalize it to work with “sufficiently flat” non-uniform distributions like Gaussians and logistics, as long as the variance is large enough.</i>
评论 #43537871 未加载