Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement

• URL: http://arxiv.org/abs/2402.11224v2
• Date: Fri, 7 Jun 2024 10:34:32 GMT
• Title: Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement
• Authors: Chi Zhang, Jingjing Fan, Man Ho Au, Siu Ming Yiu,
• Abstract summary: replacing non-polynomial functions with their approximations is a standard practice in privacy-preserving machine learning. The resulting neural network, called approximation of neural network (PANN), is compatible with advanced cryptosystems. We provide an explanation on the effect of approximate error in PANN. We propose solutions to increase inference accuracy for PANN.
• Score: 13.406378419824003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Replacing non-polynomial functions (e.g., non-linear activation functions such as ReLU) in a neural network with their polynomial approximations is a standard practice in privacy-preserving machine learning. The resulting neural network, called polynomial approximation of neural network (PANN) in this paper, is compatible with advanced cryptosystems to enable privacy-preserving model inference. Using ``highly precise'' approximation, state-of-the-art PANN offers similar inference accuracy as the underlying backbone model. However, little is known about the effect of approximation, and existing literature often determined the required approximation precision empirically. In this paper, we initiate the investigation of PANN as a standalone object. Specifically, our contribution is two-fold. Firstly, we provide an explanation on the effect of approximate error in PANN. In particular, we discovered that (1) PANN is susceptible to some type of perturbations; and (2) weight regularisation significantly reduces PANN's accuracy. We support our explanation with experiments. Secondly, based on the insights from our investigations, we propose solutions to increase inference accuracy for PANN. Experiments showed that combination of our solutions is very effective: at the same precision, our PANN is 10% to 50% more accurate than state-of-the-arts; and at the same accuracy, our PANN only requires a precision of 2^{-9} while state-of-the-art solution requires a precision of 2^{-12} using the ResNet-20 model on CIFAR-10 dataset.

Related papers

• Guaranteed Approximation Bounds for Mixed-Precision Neural Operators [83.64404557466528]
  We build on intuition that neural operator learning inherently induces an approximation error. We show that our approach reduces GPU memory usage by up to 50% and improves throughput by 58% with little or no reduction in accuracy.
  arXiv  Detail & Related papers  (2023-07-27T17:42:06Z)
• Sparsifying Bayesian neural networks with latent binary variables and normalizing flows [10.865434331546126]
  We will consider two extensions to the latent binary Bayesian neural networks (LBBNN) method. Firstly, by using the local reparametrization trick (LRT) to sample the hidden units directly, we get a more computationally efficient algorithm. More importantly, by using normalizing flows on the variational posterior distribution of the LBBNN parameters, the network learns a more flexible variational posterior distribution than the mean field Gaussian.
  arXiv  Detail & Related papers  (2023-05-05T09:40:28Z)
• Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation [0.0]
  We present a method to learn prediction intervals for regression-based neural networks automatically. Our main contribution is the design of a novel loss function for the PI-generation network. Experiments using a synthetic dataset, eight benchmark datasets, and a real-world crop yield prediction dataset showed that our method was able to maintain a nominal probability coverage.
  arXiv  Detail & Related papers  (2022-12-13T05:03:16Z)
• Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture [77.59766598165551]
  Physics-informed neural networks (PINNs) are revolutionizing science and engineering practice by bringing together the power of deep learning to bear on scientific computation. Here, we propose Auto-PINN, which employs Neural Architecture Search (NAS) techniques to PINN design. A comprehensive set of pre-experiments using standard PDE benchmarks allows us to probe the structure-performance relationship in PINNs.
  arXiv  Detail & Related papers  (2022-05-27T03:24:31Z)
• A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness [33.09831377640498]
  We study approaches to improve uncertainty property of a single network, based on a single, deterministic representation. We propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs. On a suite of vision and language understanding benchmarks, SNGP outperforms other single-model approaches in prediction, calibration and out-of-domain detection.
  arXiv  Detail & Related papers  (2022-05-01T05:46:13Z)
• Selective Network Linearization for Efficient Private Inference [49.937470642033155]
  We propose a gradient-based algorithm that selectively linearizes ReLUs while maintaining prediction accuracy. The results demonstrate up to $4.25%$ more accuracy (iso-ReLU count at 50K) or $2.2times$ less latency (iso-accuracy at 70%) than the current state of the art.
  arXiv  Detail & Related papers  (2022-02-04T19:00:24Z)
• Multi-fidelity Bayesian Neural Networks: Algorithms and Applications [0.0]
  We propose a new class of Bayesian neural networks (BNNs) that can be trained using noisy data of variable fidelity. We apply them to learn function approximations as well as to solve inverse problems based on partial differential equations (PDEs)
  arXiv  Detail & Related papers  (2020-12-19T02:03:53Z)
• Kernel Based Progressive Distillation for Adder Neural Networks [71.731127378807]
  Adder Neural Networks (ANNs) which only contain additions bring us a new way of developing deep neural networks with low energy consumption. There is an accuracy drop when replacing all convolution filters by adder filters. We present a novel method for further improving the performance of ANNs without increasing the trainable parameters.
  arXiv  Detail & Related papers  (2020-09-28T03:29:19Z)
• Accuracy Prediction with Non-neural Model for Neural Architecture Search [185.0651567642238]
  We study an alternative approach which uses non-neural model for accuracy prediction. We leverage gradient boosting decision tree (GBDT) as the predictor for Neural architecture search (NAS) Experiments on NASBench-101 and ImageNet demonstrate the effectiveness of using GBDT as predictor for NAS.
  arXiv  Detail & Related papers  (2020-07-09T13:28:49Z)
• APQ: Joint Search for Network Architecture, Pruning and Quantization Policy [49.3037538647714]
  We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. With the same accuracy, APQ reduces the latency/energy by 2x/1.3x over MobileNetV2+HAQ.
  arXiv  Detail & Related papers  (2020-06-15T16:09:17Z)

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.