paper-with-me

Papers

Neural Networks with Complex-Valued Weights Have No Spurious Local Minima

2021-01-31 · Xingtu Liu

We study the benefits of complex-valued weights for neural networks. We prove that shallow complex neural networks with quadratic activations have no spurious local minima. In contrast, shallow real neural networks with quadratic activations have infinitely many spurious local minima under the same conditions. In addition, we provide specific examples to demonstrate that complex-valued weights turn poor local minima into saddle points.

📄 PDF Abstract BibTeX arXiv:2103.07287

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
CReLU 설명 없음

Similar Papers 제목 키워드 기반

Complex neural networks have no spurious local minima

2021-01-01 · Xingtu Liu

Most non-linear neural networks are known to have poor local minima (Yun et al. (2019)) and it is shown that training a neural network is NP-hard (Blum & Rivest (1988)). A line of work has studied the global optimality o…

Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery

2024-05-27 · Anand Gopalakrishnan, Aleksandar Stanić, Jürgen Schmidhuber, Michael Curtis Mozer

Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures. We argue for the computational advantages of a rec…

ObjectObject Discovery

Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima

2017-12-03 · ICML 2018 7 · Simon S. Du, Jason D. Lee, Yuandong Tian, Barnabas Poczos 외

We consider the problem of learning a one-hidden-layer neural network with non-overlapping convolutional layer and ReLU activation, i.e., $f(\mathbf{Z}, \mathbf{w}, \mathbf{a}) = \sum_j a_j\sigma(\mathbf{w}^T\mathbf{Z}_j…

Quantitative approximation results for complex-valued neural networks

2021-02-25 · A. Caragea, D. G. Lee, J. Maly, G. Pfander 외

Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior …

Complex Markov Logic Networks: Expressivity and Liftability

2020-02-24 · Ondrej Kuzelka

We study expressivity of Markov logic networks (MLNs). We introduce complex MLNs, which use complex-valued weights, and we show that, unlike standard MLNs with real-valued weights, complex MLNs are fully expressive. We t…