This paper considers a network of collaborating agents for local resource allocation subject to nonlinear model constraints. In many applications, it is required (or desirable) that the solution be anytime feasible in terms of satisfying the sum-preserving global constraint. Motivated by this, sufficient conditions on the nonlinear mapping for anytime feasibility (or non-asymptotic feasibility) are addressed in this paper. For the two proposed distributed solutions, one converges over directed weight-balanced networks and the other one over undirected networks. In particular, we elaborate on uniform quantization and discuss the notion of {\epsilon}-accurate solution, which gives an estimate of how close we can get to the exact optimizer subject to different quantization levels. This work, further, handles general (possibly non-quadratic) strictly convex objective functions with application to CPU allocation among a cloud of data centers via distributed solutions. The results can be used as a coordination mechanism to optimally balance the tasks and CPU resources among a group of networked servers while addressing quantization or limited server capacity. Index Terms: multi-agent systems, sum-preserving resource allocation, distributed optimization, anytime feasibility
A novel deep neural network (DNN) architecture is proposed wherein the filtering and linear transform are realized solely with product quantization (PQ). This results in a natural implementation via content addressable memory (CAM), which transcends regular DNN layer operations and requires only simple table lookup. Two schemes are developed for the end-to-end PQ prototype training, namely, through angle- and distance-based similarities, which differ in their multiplicative and additive natures with different complexity-accuracy tradeoffs. Even more, the distance-based scheme constitutes a truly multiplier-free DNN solution. Experiments confirm the feasibility of such Product-Quantized Content Addressable Memory Network (PECAN), which has strong implication on hardware-efficient deployments especially for in-memory computing.
We introduce a method to identify speakers by computing with high-dimensional random vectors. Its strengths are simplicity and speed. With only 1.02k active parameters and a 128-minute pass through the training data we achieve Top-1 and Top-5 scores of 31% and 52% on the VoxCeleb1 dataset of 1,251 speakers. This is in contrast to CNN models requiring several million parameters and orders of magnitude higher computational complexity for only a 2$\times$ gain in discriminative power as measured in mutual information. An additional 92 seconds of training with Generalized Learning Vector Quantization (GLVQ) raises the scores to 48% and 67%. A trained classifier classifies 1 second of speech in 5.7 ms. All processing was done on standard CPU-based machines.
In this paper, a new methodology is proposed that allows for the low-complexity development of neural network (NN) based equalizers for the mitigation of impairments in high-speed coherent optical transmission systems. In this work, we provide a comprehensive description and comparison of various deep model compression approaches that have been applied to feed-forward and recurrent NN designs. Additionally, we evaluate the influence these strategies have on the performance of each NN equalizer. Quantization, weight clustering, pruning, and other cutting-edge strategies for model compression are taken into consideration. In this work, we propose and evaluate a Bayesian optimization-assisted compression, in which the hyperparameters of the compression are chosen to simultaneously reduce complexity and improve performance. In conclusion, the trade-off between the complexity of each compression approach and its performance is evaluated by utilizing both simulated and experimental data in order to complete the analysis. By utilizing optimal compression approaches, we show that it is possible to design an NN-based equalizer that is simpler to implement and has better performance than the conventional digital back-propagation (DBP) equalizer with only one step per span. This is accomplished by reducing the number of multipliers used in the NN equalizer after applying the weighted clustering and pruning algorithms. Furthermore, we demonstrate that an equalizer based on NN can also achieve superior performance while still maintaining the same degree of complexity as the full electronic chromatic dispersion compensation block. We conclude our analysis by highlighting open questions and existing challenges, as well as possible future research directions.
Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective of generative modeling. Starting with ResNet VAEs, which are originally designed for data (image) distribution modeling, we redesign their latent variable model using a quantization-aware posterior and prior, enabling easy quantization and entropy coding at test time. Along with improved neural network architecture, we present a powerful and efficient model that outperforms previous methods on natural image lossy compression. Our model compresses images in a coarse-to-fine fashion and supports parallel encoding and decoding, leading to fast execution on GPUs. Code is available at https://github.com/duanzhiihao/lossy-vae.
The application of distributed model predictive controllers (DMPC) for multi-agent systems (MASs) necessitates communication between agents, yet the consequence of communication data rates is typically overlooked. This work focuses on developing stability-guaranteed control methods for MASs with limited data rates. Initially, a distributed optimization algorithm with dynamic quantization is considered for solving the DMPC problem. Due to the limited data rate, the optimization process suffers from inexact iterations caused by quantization noise and premature termination, leading to sub-optimal solutions. In response, we propose a novel real-time DMPC framework with a quantization refinement scheme that updates the quantization parameters on-line so that both the quantization noise and the optimization sub-optimality decrease asymptotically. To facilitate the stability analysis, we treat the sub-optimally controlled MAS, the quantization refinement scheme, and the optimization process as three interconnected subsystems. The cyclic-small-gain theorem is used to derive sufficient conditions on the quantization parameters for guaranteeing the stability of the system under a limited data rate. Finally, the proposed algorithm and theoretical findings are demonstrated in a multi-AUV formation control example.
Machine learning and specifically deep-learning methods have outperformed human capabilities in many pattern recognition and data processing problems, in game playing, and now also play an increasingly important role in scientific discovery. A key application of machine learning in the molecular sciences is to learn potential energy surfaces or force fields from ab-initio solutions of the electronic Schr\"odinger equation using datasets obtained with density functional theory, coupled cluster, or other quantum chemistry methods. Here we review a recent and complementary approach: using machine learning to aid the direct solution of quantum chemistry problems from first principles. Specifically, we focus on quantum Monte Carlo (QMC) methods that use neural network ansatz functions in order to solve the electronic Schr\"odinger equation, both in first and second quantization, computing ground and excited states, and generalizing over multiple nuclear configurations. Compared to existing quantum chemistry methods, these new deep QMC methods have the potential to generate highly accurate solutions of the Schr\"odinger equation at relatively modest computational cost.
Deep convolutional neural network (CNN) training via iterative optimization has had incredible success in finding optimal parameters. However, modern CNN architectures often contain millions of parameters. Thus, any given model for a single architecture resides in a massive parameter space. Models with similar loss could have drastically different characteristics such as adversarial robustness, generalizability, and quantization robustness. For deep learning on the edge, quantization robustness is often crucial. Finding a model that is quantization-robust can sometimes require significant efforts. Recent works using Graph Hypernetworks (GHN) have shown remarkable performance predicting high-performant parameters of varying CNN architectures. Inspired by these successes, we wonder if the graph representations of GHN-2 can be leveraged to predict quantization-robust parameters as well, which we call GHN-Q. We conduct the first-ever study exploring the use of graph hypernetworks for predicting parameters of unseen quantized CNN architectures. We focus on a reduced CNN search space and find that GHN-Q can in fact predict quantization-robust parameters for various 8-bit quantized CNNs. Decent quantized accuracies are observed even with 4-bit quantization despite GHN-Q not being trained on it. Quantized finetuning of GHN-Q at lower bitwidths may bring further improvements and is currently being explored.
Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method for DNN quantization, prior research has demonstrated its suboptimal nature when applied to weight quantization. They propose optimizing weight rounding schemes by leveraging output error rather than the traditional weight quantization error. Our study reveals that similar rounding challenges also extend to activation quantization. Despite the easy generalization, the challenges lie in the dynamic nature of activation. Adaptive rounding is expected for varying activations and the method is subjected to runtime overhead. To tackle this, we propose the AQuant quantization framework with a novel perspective to reduce output error by adjusting rounding schemes of activations. Instead of using the constant rounding border 0.5 of the rounding-to-nearest operation, we make the border become a function w.r.t. the activation value to change the activation rounding by the adaptive border. To deal with the runtime overhead, we use a coarse-grained version of the border function. Finally, we introduce our framework to optimize the border function. Extensive experiments show that AQuant achieves notable improvements compared to state-of-the-art works and pushes the accuracy of ResNet-18 up to 60.31% under the 2-bit weight and activation quantization.
We consider the problem of model compression for deep neural networks (DNNs) in the challenging one-shot/post-training setting, in which we are given an accurate trained model, and must compress it without any retraining, based only on a small amount of calibration input data. This problem has become popular in view of the emerging software and hardware support for executing models compressed via pruning and/or quantization with speedup, and well-performing solutions have been proposed independently for both compression approaches. In this paper, we introduce a new compression framework which covers both weight pruning and quantization in a unified setting, is time- and space-efficient, and considerably improves upon the practical performance of existing post-training methods. At the technical level, our approach is based on an exact and efficient realization of the classical Optimal Brain Surgeon (OBS) framework of [LeCun, Denker, and Solla, 1990] extended to also cover weight quantization at the scale of modern DNNs. From the practical perspective, our experimental results show that it can improve significantly upon the compression-accuracy trade-offs of existing post-training methods, and that it can enable the accurate compound application of both pruning and quantization in a post-training setting.
Deep learning-based single image super-resolution (SISR) approaches have drawn much attention and achieved remarkable success on modern advanced GPUs. However, most state-of-the-art methods require a huge number of parameters, memories, and computational resources, which usually show inferior inference times when applying them to current mobile device CPUs/NPUs. In this paper, we propose a simple plain convolution network with a fast nearest convolution module (NCNet), which is NPU-friendly and can perform a reliable super-resolution in real-time. The proposed nearest convolution has the same performance as the nearest upsampling but is much faster and more suitable for Android NNAPI. Our model can be easily deployed on mobile devices with 8-bit quantization and is fully compatible with all major mobile AI accelerators. Moreover, we conduct comprehensive experiments on different tensor operations on a mobile device to illustrate the efficiency of our network architecture. Our NCNet is trained and validated on the DIV2K 3x dataset, and the comparison with other efficient SR methods demonstrated that the NCNet can achieve high fidelity SR results while using fewer inference times. Our codes and pretrained models are publicly available at \url{https://github.com/Algolzw/NCNet}.
Federated learning (FL) is an emerging paradigm for training machine learning models using possibly private data available at edge devices. The distributed operation of FL gives rise to challenges that are not encountered in centralized machine learning, including the need to preserve the privacy of the local datasets, and the communication load due to the repeated exchange of updated models. These challenges are often tackled individually via techniques that induce some distortion on the updated models, e.g., local differential privacy (LDP) mechanisms and lossy compression. In this work we propose a method coined joint privacy enhancement and quantization (JoPEQ), which jointly implements lossy compression and privacy enhancement in FL settings. In particular, JoPEQ utilizes vector quantization based on random lattice, a universal compression technique whose byproduct distortion is statistically equivalent to additive noise. This distortion is leveraged to enhance privacy by augmenting the model updates with dedicated multivariate privacy preserving noise. We show that JoPEQ simultaneously quantizes data according to a required bit-rate while holding a desired privacy level, without notably affecting the utility of the learned model. This is shown via analytical LDP guarantees, distortion and convergence bounds derivation, and numerical studies. Finally, we empirically assert that JoPEQ demolishes common attacks known to exploit privacy leakage.
Speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns when speech data get collected. Speaker anonymization aims to transform a speech signal to remove the source speaker's identity while leaving the spoken content unchanged. Current methods perform the transformation by relying on content/speaker disentanglement and voice conversion. Usually, an acoustic model from an automatic speech recognition system extracts the content representation while an x-vector system extracts the speaker representation. Prior work has shown that the extracted features are not perfectly disentangled. This paper tackles how to improve features disentanglement, and thus the converted anonymized speech. We propose enhancing the disentanglement by removing speaker information from the acoustic model using vector quantization. Evaluation done using the VoicePrivacy 2022 toolkit showed that vector quantization helps conceal the original speaker identity while maintaining utility for speech recognition.
Designing Deep Neural Networks (DNNs) running on edge hardware remains a challenge. Standard designs have been adopted by the community to facilitate the deployment of Neural Network models. However, not much emphasis is put on adapting the network topology to fit hardware constraints. In this paper, we adapt one of the most widely used architectures for mobile hardware platforms, MobileNetV2, and study the impact of changing its topology and applying post-training quantization. We discuss the impact of the adaptations and the deployment of the model on an embedded hardware platform for face detection.
The one-bit quanta image sensor (QIS) is a photon-counting device that captures image intensities using binary bits. Assuming that the analog voltage generated at the floating diffusion of the photodiode follows a Poisson-Gaussian distribution, the sensor produces either a ``1'' if the voltage is above a certain threshold or ``0'' if it is below the threshold. The concept of this binary sensor has been proposed for more than a decade, and physical devices have been built to realize the concept. However, what benefits does a one-bit QIS offer compared to a conventional multi-bit CMOS image sensor? Besides the known empirical results, are there theoretical proofs to support these findings? The goal of this paper is to provide new theoretical support from a signal processing perspective. In particular, it is theoretically found that the sensor can offer three benefits: (1) Low-light: One-bit QIS performs better at low-light because it has a low read noise, and its one-bit quantization can produce an error-free measurement. However, this requires the exposure time to be appropriately configured. (2) Frame rate: One-bit sensors can operate at a much higher speed because a response is generated as soon as a photon is detected. However, in the presence of read noise, there exists an optimal frame rate beyond which the performance will degrade. A Closed-form expression of the optimal frame rate is derived. (3) Dynamic range: One-bit QIS offers a higher dynamic range. The benefit is brought by two complementary characteristics of the sensor: nonlinearity and exposure bracketing. The decoupling of the two factors is theoretically proved, and closed-form expressions are derived.
Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size and can accelerate inference, but their relative benefit and combinatorial interactions have not been rigorously studied. For each of the eight possible subsets of these techniques, we compare accuracy vs. model size tradeoffs across six BERT architecture sizes and eight GLUE tasks. We find that quantization and distillation consistently provide greater benefit than pruning. Surprisingly, except for the pair of pruning and quantization, using multiple methods together rarely yields diminishing returns. Instead, we observe complementary and super-multiplicative reductions to model size. Our work quantitatively demonstrates that combining compression methods can synergistically reduce model size, and that practitioners should prioritize (1) quantization, (2) knowledge distillation, and (3) pruning to maximize accuracy vs. model size tradeoffs.
Efficiently deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. To address this issue, researchers have proposed multiplication-free neural networks, such as Power-of-Two quantization, or also known as Shift networks, which aim to reduce memory usage and simplify computation. However, existing low-bit Shift networks are not as accurate as their full-precision counterparts, typically suffering from limited weight range encoding schemes and quantization loss. In this paper, we propose the DenseShift network, which significantly improves the accuracy of Shift networks, achieving competitive performance to full-precision networks for vision and speech applications. In addition, we introduce a method to deploy an efficient DenseShift network using non-quantized floating-point activations, while obtaining 1.6X speed-up over existing methods. To achieve this, we demonstrate that zero-weight values in low-bit Shift networks do not contribute to model capacity and negatively impact inference computation. To address this issue, we propose a zero-free shifting mechanism that simplifies inference and increases model capacity. We further propose a sign-scale decomposition design to enhance training efficiency and a low-variance random initialization strategy to improve the model's transfer learning performance. Our extensive experiments on various computer vision and speech tasks demonstrate that DenseShift outperforms existing low-bit multiplication-free networks and achieves competitive performance compared to full-precision networks. Furthermore, our proposed approach exhibits strong transfer learning performance without a drop in accuracy. Our code was released on GitHub.
When quantizing neural networks for efficient inference, low-bit integers are the go-to format for efficiency. However, low-bit floating point numbers have an extra degree of freedom, assigning some bits to work on an exponential scale instead. This paper in-depth investigates this benefit of the floating point format for neural network inference. We detail the choices that can be made for the FP8 format, including the important choice of the number of bits for the mantissa and exponent, and show analytically in which settings these choices give better performance. Then we show how these findings translate to real networks, provide an efficient implementation for FP8 simulation, and a new algorithm that enables the learning of both the scale parameters and the number of exponent bits in the FP8 format. Our chief conclusion is that when doing post-training quantization for a wide range of networks, the FP8 format is better than INT8 in terms of accuracy, and the choice of the number of exponent bits is driven by the severity of outliers in the network. We also conduct experiments with quantization-aware training where the difference in formats disappears as the network is trained to reduce the effect of outliers.
The Sign Language Production (SLP) project aims to automatically translate spoken languages into sign sequences. Our approach focuses on the transformation of sign gloss sequences into their corresponding sign pose sequences (G2P). In this paper, we present a novel solution for this task by converting the continuous pose space generation problem into a discrete sequence generation problem. We introduce the Pose-VQVAE framework, which combines Variational Autoencoders (VAEs) with vector quantization to produce a discrete latent representation for continuous pose sequences. Additionally, we propose the G2P-DDM model, a discrete denoising diffusion architecture for length-varied discrete sequence data, to model the latent prior. To further enhance the quality of pose sequence generation in the discrete space, we present the CodeUnet model to leverage spatial-temporal information. Lastly, we develop a heuristic sequential clustering method to predict variable lengths of pose sequences for corresponding gloss sequences. Our results show that our model outperforms state-of-the-art G2P models on the public SLP evaluation benchmark. For more generated results, please visit our project page: \textcolor{blue}{\url{https://slpdiffusier.github.io/g2p-ddm}}
The quality of datasets plays a crucial role in the successful training and deployment of deep learning models. Especially in the medical field, where system performance may impact the health of patients, clean datasets are a safety requirement for reliable predictions. Therefore, outlier detection is an essential process when building autonomous clinical decision systems. In this work, we assess the suitability of Self-Organizing Maps for outlier detection specifically on a medical dataset containing quantitative phase images of white blood cells. We detect and evaluate outliers based on quantization errors and distance maps. Our findings confirm the suitability of Self-Organizing Maps for unsupervised Out-Of-Distribution detection on the dataset at hand. Self-Organizing Maps perform on par with a manually specified filter based on expert domain knowledge. Additionally, they show promise as a tool in the exploration and cleaning of medical datasets. As a direction for future research, we suggest a combination of Self-Organizing Maps and feature extraction based on deep learning.