Neural Networks with Complex-Valued Weights Have No Spurious Local Minima
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.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Complex neural networks have no spurious local minima
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
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 DiscoveryGradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
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
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
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…