On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition
This work addresses the computational difficulty of learning neural networks for researchers in machine learning theory, showing it is incremental by linking to existing tensor decomposition methods.
The paper establishes a connection between learning two-layer neural networks with polynomial activations and tensor decomposition, proving that no polynomial-time algorithm can outperform trivial prediction for certain parameter regimes under a natural data distribution and complexity-theoretic assumptions.
We establish connections between the problem of learning a two-layer neural network and tensor decomposition. We consider a model with feature vectors $\boldsymbol x \in \mathbb R^d$, $r$ hidden units with weights $\{\boldsymbol w_i\}_{1\le i \le r}$ and output $y\in \mathbb R$, i.e., $y=\sum_{i=1}^r σ( \boldsymbol w_i^{\mathsf T}\boldsymbol x)$, with activation functions given by low-degree polynomials. In particular, if $σ(x) = a_0+a_1x+a_3x^3$, we prove that no polynomial-time learning algorithm can outperform the trivial predictor that assigns to each example the response variable $\mathbb E(y)$, when $d^{3/2}\ll r\ll d^2$. Our conclusion holds for a `natural data distribution', namely standard Gaussian feature vectors $\boldsymbol x$, and output distributed according to a two-layer neural network with random isotropic weights, and under a certain complexity-theoretic assumption on tensor decomposition. Roughly speaking, we assume that no polynomial-time algorithm can substantially outperform current methods for tensor decomposition based on the sum-of-squares hierarchy. We also prove generalizations of this statement for higher degree polynomial activations, and non-random weight vectors. Remarkably, several existing algorithms for learning two-layer networks with rigorous guarantees are based on tensor decomposition. Our results support the idea that this is indeed the core computational difficulty in learning such networks, under the stated generative model for the data. As a side result, we show that under this model learning the network requires accurate learning of its weights, a property that does not hold in a more general setting.