Sliding down the stairs: how correlated latent variables accelerate learning with neural networks

• URL: http://arxiv.org/abs/2404.08602v2
• Date: Tue, 4 Jun 2024 09:43:45 GMT
• Title: Sliding down the stairs: how correlated latent variables accelerate learning with neural networks
• Authors: Lorenzo Bardone, Sebastian Goldt,
• Abstract summary: We show that correlations between latent variables along directions encoded in different input cumulants speed up learning from higher-order correlations. Our results are confirmed in simulations of two-layer neural networks.
• Score: 8.107431208836426
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks extract features from data using stochastic gradient descent (SGD). In particular, higher-order input cumulants (HOCs) are crucial for their performance. However, extracting information from the $p$th cumulant of $d$-dimensional inputs is computationally hard: the number of samples required to recover a single direction from an order-$p$ tensor (tensor PCA) using online SGD grows as $d^{p-1}$, which is prohibitive for high-dimensional inputs. This result raises the question of how neural networks extract relevant directions from the HOCs of their inputs efficiently. Here, we show that correlations between latent variables along the directions encoded in different input cumulants speed up learning from higher-order correlations. We show this effect analytically by deriving nearly sharp thresholds for the number of samples required by a single neuron to weakly-recover these directions using online SGD from a random start in high dimensions. Our analytical results are confirmed in simulations of two-layer neural networks and unveil a new mechanism for hierarchical learning in neural networks.

Related papers

• Generative Kaleidoscopic Networks [2.321684718906739]
  We utilize this property of neural networks to design a dataset kaleidoscope, termed as Generative Kaleidoscopic Networks' We observed this phenomenon to various degrees for the other deep learning architectures like CNNs, Transformers & U-Nets.
  arXiv  Detail & Related papers  (2024-02-19T02:48:40Z)
• Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks [7.503293567983987]
  We study how efficient are neural networks at extracting features from higher-order cumulants. We show that neural networks do indeed learn to distinguish the two distributions with quadratic sample complexity. Our results show that neural networks extract information from higher-ordercorrelations in the spiked cumulant model efficiently.
  arXiv  Detail & Related papers  (2023-12-22T18:55:25Z)
• SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem [1.3597551064547502]
  We consider the optimization process of minibatch descent gradient (SGD) on a 2-layer neural network with data separated by a quadratic ground truth function. We prove that with data drawn from the $d$-dimensional Boolean hypercube labeled by the quadratic XOR'' function $y = -x_ix_j$, it is possible to train to a population error $o(1)$ with $d :textpolylog(d)$ samples.
  arXiv  Detail & Related papers  (2023-09-26T17:57:44Z)
• Sampling weights of deep neural networks [1.2370077627846041]
  We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of internal network parameters are needed. We prove that sampled networks are universal approximators.
  arXiv  Detail & Related papers  (2023-06-29T10:13:36Z)
• Correlation Functions in Random Fully Connected Neural Networks at Finite Width [17.51364577113718]
  This article considers fully connected neural networks with Gaussian random weights and biases and $L$ hidden layers. For bounded non-linearities we give sharp recursion estimates in powers of $1/n$ for the joint correlation functions of the network output and its derivatives. We find in both cases that the depth-to-width ratio $L/n$ plays the role of an effective network depth, controlling both the scale of fluctuations at individual neurons and the size of inter-neuron correlations.
  arXiv  Detail & Related papers  (2022-04-03T11:57:18Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Differentially private training of neural networks with Langevin dynamics forcalibrated predictive uncertainty [58.730520380312676]
  We show that differentially private gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models. This represents a serious issue for safety-critical applications, e.g. in medical diagnosis.
  arXiv  Detail & Related papers  (2021-07-09T08:14:45Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)
• Towards Understanding Hierarchical Learning: Benefits of Neural Representations [160.33479656108926]
  In this work, we demonstrate that intermediate neural representations add more flexibility to neural networks. We show that neural representation can achieve improved sample complexities compared with the raw input. Our results characterize when neural representations are beneficial, and may provide a new perspective on why depth is important in deep learning.
  arXiv  Detail & Related papers  (2020-06-24T02:44:54Z)
• Measuring Model Complexity of Neural Networks with Curve Activation Functions [100.98319505253797]
  We propose the linear approximation neural network (LANN) to approximate a given deep model with curve activation function. We experimentally explore the training process of neural networks and detect overfitting. We find that the $L1$ and $L2$ regularizations suppress the increase of model complexity.
  arXiv  Detail & Related papers  (2020-06-16T07:38:06Z)

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.