We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width. Taylorized training involves training the $k$-th order Taylor expansion of the neural network at initialization, and is a principled extension of linearized training---a recently proposed theory for understanding the success of deep learning. We experiment with Taylorized training on modern neural network architectures, and show that Taylorized training (1) agrees with full neural network training increasingly better as we increase $k$, and (2) can significantly close the performance gap between linearized and full training. Compared with linearized training, higher-order training works in more realistic settings such as standard parameterization and large (initial) learning rate. We complement our experiments with theoretical results showing that the approximation error of $k$-th order Taylorized models decay exponentially over $k$ in wide neural networks.

Classical results on the statistical complexity of linear models have commonly identified the norm of the weights $\|w\|$ as a fundamental capacity measure. Generalizations of this measure to the setting of deep networks have been varied, though a frequently identified quantity is the product of weight norms of each layer. In this work, we show that for a large class of networks possessing a positive homogeneity property, similar bounds may be obtained instead in terms of the norm of the product of weights. Our proof technique generalizes a recently proposed sampling argument, which allows us to demonstrate the existence of sparse approximants of positive homogeneous networks. This yields covering number bounds, which can be converted to generalization bounds for multi-class classification that are comparable to, and in certain cases improve upon, existing results in the literature. Finally, we investigate our sampling procedure empirically, which yields results consistent with our theory.

Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where the trajectory distribution can be decomposed using the reparametrization trick. For this problem class, estimating the expected return is efficient and the trajectory can be computed deterministically given peripheral random variables, which enables us to study reparametrizable RL using supervised learning and transfer learning theory. Through these relationships, we derive guarantees on the gap between the expected and empirical return for both intrinsic and external errors, based on Rademacher complexity as well as the PAC-Bayes bound. Our bound suggests the generalization capability of reparameterizable RL is related to multiple factors including "smoothness" of the environment transition, reward and agent policy function class. We also empirically verify the relationship between the generalization gap and these factors through simulations.

In recent years, three-dimensional convolutional neural network (3D CNN) is intensively applied in video analysis and receives good performance. However, 3D CNN leads to massive computation and storage consumption, which hinders its deployment on mobile and embedded devices. In this paper, we propose a three-dimensional regularization-based pruning method to assign different regularization parameters to different weight groups based on their importance to the network. Experiments show that the proposed method outperforms other popular methods in this area.

While it has not yet been proven, empirical evidence suggests that model generalization is related to local properties of the optima which can be described via the Hessian. We connect model generalization with the local property of a solution under the PAC-Bayes paradigm. In particular, we prove that model generalization ability is related to the Hessian, the higher-order "smoothness" terms characterized by the Lipschitz constant of the Hessian, and the scales of the parameters. Guided by the proof, we propose a metric to score the generalization capability of the model, as well as an algorithm that optimizes the perturbed model accordingly.

Convolutional Neural Networks (CNN's) are restricted by their massive computation and high storage. Parameter pruning is a promising approach for CNN compression and acceleration, which aims at eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter pruning methods usually assign a fixed regularization parameter to all weights, which neglects the fact that different weights may have different importance to CNN. To solve this problem, we propose a theoretically sound regularization-based pruning method to incrementally assign different regularization parameters to different weights based on their importance to the network. On AlexNet and VGG-16, our method can achieve 4x theoretical speedup with similar accuracies compared with the baselines. For ResNet-50, the proposed method also achieves 2x acceleration and only suffers 0.1% top-5 accuracy loss.

Although deep Convolutional Neural Network (CNN) has shown better performance in various computer vision tasks, its application is restricted by a significant increase in storage and computation. Among CNN simplification techniques, parameter pruning is a promising approach which aims at reducing the number of weights of various layers without intensively reducing the original accuracy. In this paper, we propose a novel progressive parameter pruning method, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Specifically, unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria for the training process. Experiments show that, with 4x speedup, SPP can accelerate AlexNet with only 0.3% loss of top-5 accuracy and VGG-16 with 0.8% loss of top-5 accuracy in ImageNet classification. Moreover, SPP can be directly applied to accelerate multi-branch CNN networks, such as ResNet, without specific adaptations. Our 2x speedup ResNet-50 only suffers 0.8% loss of top-5 accuracy on ImageNet. We further prove the effectiveness of our method on transfer learning task on Flower-102 dataset with AlexNet.