Recurrent neural networks (RNN) such as long-short-term memory (LSTM) networks are essential in a multitude of daily live tasks such as speech, language, video, and multimodal learning. The shift from cloud to edge computation intensifies the need to contain the growth of RNN parameters. Current research on RNN shows that despite the performance obtained on convolutional neural networks (CNN), keeping a good performance in compressed RNNs is still a challenge. Most of the literature on compression focuses on CNNs using matrix product (MPO) operator tensor trains. However, matrix product state (MPS) tensor trains have more attractive features than MPOs, in terms of storage reduction and computing time at inference. We show that MPS tensor trains should be at the forefront of LSTM network compression through a theoretical analysis and practical experiments on NLP task.
Additive noise models are commonly used to infer the causal direction for a given set of observed data. Most causal models assume a single homogeneous population. However, observations may be collected under different conditions in practice. Such data often require models that can accommodate possible heterogeneity caused by different conditions under which data have been collected. We propose a clustering algorithm inspired by the $k$-means algorithm, but with unknown $k$. Using the proposed algorithm, both the labels and the number of components are estimated from the collected data. The estimated labels are used to adjust the causal direction test statistic. The adjustment significantly improves the performance of the test statistic in identifying the correct causal direction.
Implementation of quantized neural networks on computing hardware leads to considerable speed up and memory saving. However, quantized deep networks are difficult to train and batch~normalization (BatchNorm) layer plays an important role in training full-precision and quantized networks. Most studies on BatchNorm are focused on full-precision networks, and there is little research in understanding BatchNorm affect in quantized training which we address here. We show BatchNorm avoids gradient explosion which is counter-intuitive and recently observed in numerical experiments by other researchers.
Training large-scale deep neural networks is a long, time-consuming operation, often requiring many GPUs to accelerate. In large models, the time spent loading data takes a significant portion of model training time. As GPU servers are typically expensive, tricks that can save training time are valuable.Slow training is observed especially on real-world applications where exhaustive data augmentation operations are required. Data augmentation techniques include: padding, rotation, adding noise, down sampling, up sampling, etc. These additional operations increase the need to build an efficient data loading pipeline, and to explore existing tools to speed up training time. We focus on the comparison of two main tools designed for this task, namely binary data format to accelerate data reading, and NVIDIA DALI to accelerate data augmentation. Our study shows improvement on the order of 20% to 40% if such dedicated tools are used.
Uplift models provide a solution to the problem of isolating the marketing effect of a campaign. For customer churn reduction, uplift models are used to identify the customers who are likely to respond positively to a retention activity only if targeted, and to avoid wasting resources on customers that are very likely to switch to another company. We introduce a Qini-based uplift regression model to analyze a large insurance company's retention marketing campaign. Our approach is based on logistic regression models. We show that a Qini-optimized uplift model acts as a regularizing factor for uplift, much as a penalized likelihood model does for regression. This results in interpretable parsimonious models with few relevant explanatory variables. Our results show that performing Qini-based variable selection significantly improves the uplift models performance.
Binary Neural Networks (BNNs) are difficult to train, and suffer from drop of accuracy. It appears in practice that BNNs fail to train in the absence of Batch Normalization (BatchNorm) layer. We find the main role of BatchNorm is to avoid exploding gradients in the case of BNNs. This finding suggests that the common initialization methods developed for full-precision networks are irrelevant to BNNs. We build a theoretical study on the role of BatchNorm in binary training, backed up by numerical experiments.
Edge intelligence especially binary neural network (BNN) has attracted considerable attention of the artificial intelligence community recently. BNNs significantly reduce the computational cost, model size, and memory footprint. However, there is still a performance gap between the successful full-precision neural network with ReLU activation and BNNs. We argue that the accuracy drop of BNNs is due to their geometry. We analyze the behaviour of the full-precision neural network with ReLU activation and compare it with its binarized counterpart. This comparison suggests random bias initialization as a remedy to activation saturation in full-precision networks and leads us towards an improved BNN training. Our numerical experiments confirm our geometric intuition.
Neural network models are resource hungry. Low bit quantization such as binary and ternary quantization is a common approach to alleviate this resource requirements. Ternary quantization provides a more flexible model and often beats binary quantization in terms of accuracy, but doubles memory and increases computation cost. Mixed quantization depth models, on another hand, allows a trade-off between accuracy and memory footprint. In such models, quantization depth is often chosen manually (which is a tiring task), or is tuned using a separate optimization routine (which requires training a quantized network multiple times). Here, we propose Smart Ternary Quantization (STQ) in which we modify the quantization depth directly through an adaptive regularization function, so that we train a model only once. This method jumps between binary and ternary quantization while training. We show its application on image classification.
Initialization plays a crucial role in training neural models. Binary Neural Networks (BNNs) is the most extreme quantization which often suffers from drop of accuracy. Most of neural network initialization is studied in full-prevision network setting, in which the variance of the random initialization decreases with the number of parameters per layer. We show that contrary to common belief, such popular initialization schemes are meaningless to BNNs. We analyze binary networks analytically, and propose to initialize binary weights with the same variance across different layers. We perform experiments to show the accuracy gain using this straight-forward heuristic.
Pruning of neural networks is one of the well-known and promising model simplification techniques. Most neural network models are large and require expensive computations to predict new instances. It is imperative to compress the network to deploy models on low resource devices. Most compression techniques, especially pruning have been focusing on computer vision and convolution neural networks. Existing techniques are complex and require multi-stage optimization and fine-tuning to recover the state-of-the-art accuracy. We introduce a \emph{Differentiable Mask Pruning} (DMP), that simplifies the network while training, and can be used to induce sparsity on weight, filter, node or sub-network. Our method achieves competitive results on standard vision and NLP benchmarks, and is easy to integrate within the deep learning toolbox. DMP bridges the gap between neural model compression and differentiable neural architecture search.