arXiv subjects

Ling Liang

Publications and source records attributed to Ling Liang.

68 records · Page 4Linked to original sources

arXiv2022

QPPAL: A two-phase proximal augmented Lagrangian method for high dimensional convex quadratic programming problems

In this paper, we aim to solve high dimensional convex quadratic programming (QP) problems with a large number of quadratic terms, linear equality and inequality constraints. In order to solve the targeted {\bf QP} problems to a desired accuracy efficiently, we develop a two-phase {\bf P}roximal {\bf A}ugmented {\bf L}agrangian method {(QPPAL)}, with Phase I to generate a reasonably good initial point to warm start Phase II to obtain an accurate solution efficiently. More specifically, in Phase I, based on the recently developed symmetric Gauss-Seidel (sGS) decomposition technique, we design a novel sGS based semi-proximal augmented Lagrangian method for the purpose of finding a solution of low to medium accuracy. Then, in Phase II, a proximal augmented Lagrangian algorithm is proposed to obtain a more accurate solution efficiently. Extensive numerical results evaluating the performance of {QPPAL} against {existing state-of-the-art solvers Gurobi, OSQP and QPALM} are presented to demonstrate the high efficiency and robustness of our proposed algorithm for solving various classes of large-scale convex QP problems. {The MATLAB implementation of the software package QPPAL is available at: \url{https://blog.nus.edu.sg/mattohkc/softwares/qppal/}.

math.OC↗

arXiv2021

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial patch attacks work well on small images like MNIST and CIFAR-10 datasets, but achieve very poor certified accuracy on higher-resolution images like ImageNet. It is urgent to design both robust and effective defenses against such a practical and harmful attack in industry-level larger images. In this work, we propose the certified defense methodology that achieves high provable robustness for high-resolution images and largely improves the practicality for real adoption of the certified defense. The basic insight of our work is that the adversarial patch intends to leverage localized superficial important neurons (SIN) to manipulate the prediction results. Hence, we leverage the SIN-based DNN compression techniques to significantly improve the certified accuracy, by reducing the adversarial region searching overhead and filtering the prediction noises. Our experimental results show that the certified accuracy is increased from 36.3% (the state-of-the-art certified detection) to 60.4% on the ImageNet dataset, largely pushing the certified defenses for practical use.

cs.CV↗

arXiv2021

An Inexact Projected Gradient Method with Rounding and Lifting by Nonlinear Programming for Solving Rank-One Semidefinite Relaxation of Polynomial Optimization

We consider solving high-order semidefinite programming (SDP) relaxations of nonconvex polynomial optimization problems (POPs) that often admit degenerate rank-one optimal solutions. Instead of solving the SDP alone, we propose a new algorithmic framework that blends local search using the nonconvex POP into global descent using the convex SDP. In particular, we first design a globally convergent inexact projected gradient method (iPGM) for solving the SDP that serves as the backbone of our framework. We then accelerate iPGM by taking long, but safeguarded, rank-one steps generated by fast nonlinear programming algorithms. We prove that the new framework is still globally convergent for solving the SDP. To solve the iPGM subproblem of projecting a given point onto the feasible set of the SDP, we design a two-phase algorithm with phase one using a symmetric Gauss-Seidel based accelerated proximal gradient method (sGS-APG) to generate a good initial point, and phase two using a modified limited-memory BFGS (L-BFGS) method to obtain an accurate solution. We analyze the convergence for both phases and establish a novel global convergence result for the modified L-BFGS that does not require the objective function to be twice continuously differentiable. We conduct numerical experiments for solving second-order SDP relaxations arising from a diverse set of POPs. Our framework demonstrates state-of-the-art efficiency, scalability, and robustness in solving degenerate rank-one SDPs to high accuracy, even in the presence of millions of equality constraints.

math.OC↗

arXiv2021

An Inexact Augmented Lagrangian Method for Second-order Cone Programming with Applications

In this paper, we adopt the augmented Lagrangian method (ALM) to solve convex quadratic second-order cone programming problems (SOCPs). Fruitful results on the efficiency of the ALM have been established in the literature. Recently, it has been shown in [Cui, Sun, and Toh, {\em Math. Program.}, 178 (2019), pp. 381--415] that if the quadratic growth condition holds at an optimal solution for the dual problem, then the KKT residual converges to zero R-superlinearly when the ALM is applied to the primal problem. Moreover, Cui, Ding, and Zhao [{\em SIAM J. Optim.}, 27 (2017), pp. 2332-2355] provided sufficient conditions for the quadratic growth condition to hold under the metric subregularity and bounded linear regularity conditions for solving composite matrix optimization problems involving spectral functions. Here, we adopt these recent ideas to analyze the convergence properties of the ALM when applied to SOCPs. To the best of our knowledge, no similar work has been done for SOCPs so far. In our paper, we first provide sufficient conditions to ensure the quadratic growth condition for SOCPs. With these elegant theoretical guarantees, we then design an SOCP solver and apply it to solve various classes of SOCPs, such as minimal enclosing ball problems, classical trust-region subproblems, square-root Lasso problems, and DIMACS Challenge problems. Numerical results show that the proposed ALM based solver is efficient and robust compared to the existing highly developed solvers, such as Mosek and SDPT3.

math.OC↗

arXiv2021

On Degenerate Doubly Nonnegative Projection Problems

The doubly nonnegative (DNN) cone, being the set of all positive semidefinite matrices whose elements are nonnegative, is a popular approximation of the computationally intractable completely positive cone. The major difficulty for implementing a Newton-type method to compute the projection of a given large scale matrix onto the DNN cone lies in the possible failure of the constraint nondegeneracy, a generalization of the linear independence constraint qualification for nonlinear programming. Such a failure results in the singularity of the Jacobian of the nonsmooth equation representing the Karush-Kuhn-Tucker optimality condition that prevents the semismooth Newton-CG method from solving it with a desirable convergence rate. In this paper, we overcome the aforementioned difficulty by solving a sequence of better conditioned nonsmooth equations generated by the augmented Lagrangian method (ALM) instead of solving one above mentioned singular equation. By leveraging on the metric subregularity of the normal cone associated with the positive semidefinite cone, we derive sufficient conditions to ensure the dual quadratic growth condition of the underlying problem, which further leads to the asymptotically superlinear convergence of the proposed ALM. Numerical results on difficult randomly generated instances and from the semidefinite programming library are presented to demonstrate the efficiency of the algorithm for computing the DNN projection to a very high accuracy.

math.OC↗

arXiv2021

H2Learn: High-Efficiency Learning Accelerator for High-Accuracy Spiking Neural Networks

Although spiking neural networks (SNNs) take benefits from the bio-plausible neural modeling, the low accuracy under the common local synaptic plasticity learning rules limits their application in many practical tasks. Recently, an emerging SNN supervised learning algorithm inspired by backpropagation through time (BPTT) from the domain of artificial neural networks (ANNs) has successfully boosted the accuracy of SNNs and helped improve the practicability of SNNs. However, current general-purpose processors suffer from low efficiency when performing BPTT for SNNs due to the ANN-tailored optimization. On the other hand, current neuromorphic chips cannot support BPTT because they mainly adopt local synaptic plasticity rules for simplified implementation. In this work, we propose H2Learn, a novel architecture that can achieve high efficiency for BPTT-based SNN learning which ensures high accuracy of SNNs. At the beginning, we characterized the behaviors of BPTT-based SNN learning. Benefited from the binary spike-based computation in the forward pass and the weight update, we first design lookup table (LUT) based processing elements in Forward Engine and Weight Update Engine to make accumulations implicit and to fuse the computations of multiple input points. Second, benefited from the rich sparsity in the backward pass, we design a dual-sparsity-aware Backward Engine which exploits both input and output sparsity. Finally, we apply a pipeline optimization between different engines to build an end-to-end solution for the BPTT-based SNN learning. Compared with the modern NVIDIA V100 GPU, H2Learn achieves 7.38x area saving, 5.74-10.20x speedup, and 5.25-7.12x energy saving on several benchmark datasets.

cs.NE↗

arXiv2020

Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient

Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps. We propose two approaches to address the challenges of gradient input incompatibility and gradient vanishing. Specifically, we design a gradient to spike converter to convert continuous gradients to ternary ones compatible with spike inputs. Then, we design a gradient trigger to construct ternary gradients that can randomly flip the spike inputs with a controllable turnover rate, when meeting all zero gradients. Putting these methods together, we build an adversarial attack methodology for SNNs trained by supervised algorithms. Moreover, we analyze the influence of the training loss function and the firing threshold of the penultimate layer, which indicates a "trap" region under the cross-entropy loss that can be escaped by threshold tuning. Extensive experiments are conducted to validate the effectiveness of our solution. Besides the quantitative analysis of the influence factors, we evidence that SNNs are more robust against adversarial attack than ANNs. This work can help reveal what happens in SNN attack and might stimulate more research on the security of SNN models and neuromorphic devices.

cs.NE↗

arXiv2020

Rubik: A Hierarchical Architecture for Efficient Graph Learning

Graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce, social networks, and knowledge graphs. However, learning from graphs is non-trivial because of its mixed computation model involving both graph analytics and neural network computing. To this end, we decompose the GCN learning into two hierarchical paradigms: graph-level and node-level computing. Such a hierarchical paradigm facilitates the software and hardware accelerations for GCN learning. We propose a lightweight graph reordering methodology, incorporated with a GCN accelerator architecture that equips a customized cache design to fully utilize the graph-level data reuse. We also propose a mapping methodology aware of data reuse and task-level parallelism to handle various graphs inputs effectively. Results show that Rubik accelerator design improves energy efficiency by 26.3x to 1375.2x than GPU platforms across different datasets and GCN models.

cs.AR↗

arXiv2020

Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization

As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency. Model compression has been proposed as a promising technique to improve the running efficiency via parameter and operation reduction. Whereas, this technique is mainly practiced in ANNs rather than SNNs. It is interesting to answer how much an SNN model can be compressed without compromising its functionality, where two challenges should be addressed: i) the accuracy of SNNs is usually sensitive to model compression, which requires an accurate compression methodology; ii) the computation of SNNs is event-driven rather than static, which produces an extra compression dimension on dynamic spikes. To this end, we realize a comprehensive SNN compression through three steps. First, we formulate the connection pruning and weight quantization as a constrained optimization problem. Second, we combine spatio-temporal backpropagation (STBP) and alternating direction method of multipliers (ADMM) to solve the problem with minimum accuracy loss. Third, we further propose activity regularization to reduce the spike events for fewer active operations. These methods can be applied in either a single way for moderate compression or a joint way for aggressive compression. We define several quantitative metrics to evaluation the compression performance for SNNs. Our methodology is validated in pattern recognition tasks over MNIST, N-MNIST, CIFAR10, and CIFAR100 datasets, where extensive comparisons, analyses, and insights are provided. To our best knowledge, this is the first work that studies SNN compression in a comprehensive manner by exploiting all compressible components and achieves better results.

cs.NE↗

arXiv2020

SEALing Neural Network Models in Secure Deep Learning Accelerators

Deep learning (DL) accelerators are increasingly deployed on edge devices to support fast local inferences. However, they suffer from a new security problem, i.e., being vulnerable to physical access based attacks. An adversary can easily obtain the entire neural network (NN) model by physically snooping the GDDR memory bus that connects the accelerator chip with DRAM memory. Therefore, memory encryption becomes important for DL accelerators on edge devices to improve the security of NN models. Nevertheless, we observe that traditional memory encryption solutions that have been efficiently used in CPU systems cause significant performance degradation when directly used in DL accelerators. The main reason comes from the big bandwidth gap between the GDDR memory bus and the encryption engine. To address this problem, our paper proposes SEAL, a Secure and Efficient Accelerator scheme for deep Learning. SEAL enhances the performance of the encrypted DL accelerator from two aspects, i.e., improving the data access bandwidth and the efficiency of memory encryption. Specifically, to improve the data access bandwidth, SEAL leverages a criticality-aware smart encryption scheme which identifies partial data that have no impact on the security of NN models and allows them to bypass the encryption engine, thus reducing the amount of data to be encrypted. To improve the efficiency of memory encryption, SEAL leverages a colocation mode encryption scheme to eliminate memory accesses from counters used for encryption by co-locating data and their counters. Our experimental results demonstrate that, compared with traditional memory encryption solutions, SEAL achieves 1.4 ~ 1.6 times IPC improvement and reduces the inference latency by 39% ~ 60%. Compared with a baseline accelerator without memory encryption, SEAL compromises only 5% ~ 7% IPC for significant security improvement.

cs.AR↗

arXiv2020

HyGCN: A GCN Accelerator with Hybrid Architecture

In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU. Guided by the characterization, we design a GCN accelerator, HyGCN, using a hybrid architecture to efficiently perform GCNs. Specifically, first, we build a new programming model to exploit the fine-grained parallelism for our hardware design. Second, we propose a hardware design with two efficient processing engines to alleviate the irregularity of Aggregation phase and leverage the regularity of Combination phase. Besides, these engines can exploit various parallelism and reuse highly reusable data efficiently. Third, we optimize the overall system via inter-engine pipeline for inter-phase fusion and priority-based off-chip memory access coordination to improve off-chip bandwidth utilization. Compared to the state-of-the-art software framework running on Intel Xeon CPU and NVIDIA V100 GPU, our work achieves on average 1509$\times$ speedup with 2500$\times$ energy reduction and average 6.5$\times$ speedup with 10$\times$ energy reduction, respectively.

cs.DC↗

arXiv2019

Multi-View Fuzzy Clustering with The Alternative Learning between Shared Hidden Space and Partition

As the multi-view data grows in the real world, multi-view clus-tering has become a prominent technique in data mining, pattern recognition, and machine learning. How to exploit the relation-ship between different views effectively using the characteristic of multi-view data has become a crucial challenge. Aiming at this, a hidden space sharing multi-view fuzzy clustering (HSS-MVFC) method is proposed in the present study. This method is based on the classical fuzzy c-means clustering model, and obtains associ-ated information between different views by introducing shared hidden space. Especially, the shared hidden space and the fuzzy partition can be learned alternatively and contribute to each other. Meanwhile, the proposed method uses maximum entropy strategy to control the weights of different views while learning the shared hidden space. The experimental result shows that the proposed multi-view clustering method has better performance than many related clustering methods.

cs.LG↗

arXiv2019

Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints

As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject. Even those that deploy neural networks embedded in physical devices may wish to keep the inner working of their designs hidden -- either to protect their intellectual property or as a form of protection from adversarial inputs. The specific problem we address is how, through heavy system stack, given noisy and imperfect memory traces, one might reconstruct the neural network architecture including the set of layers employed, their connectivity, and their respective dimension sizes. Considering both the intra-layer architecture features and the inter-layer temporal association information introduced by the DNN design empirical experience, we draw upon ideas from speech recognition to solve this problem. We show that off-chip memory address traces and PCIe events provide ample information to reconstruct such neural network architectures accurately. We are the first to propose such accurate model extraction techniques and demonstrate an end-to-end attack experimentally in the context of an off-the-shelf Nvidia GPU platform with full system stack. Results show that the proposed techniques achieve a high reverse engineering accuracy and improve the one's ability to conduct targeted adversarial attack with success rate from 14.6\%$\sim$25.5\% (without network architecture knowledge) to 75.9\% (with extracted network architecture).

cs.CR↗

arXiv2018

Crossbar-aware neural network pruning

Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations. However, in the case of convolutional neural networks (CNNs), the efficiency is compromised dramatically due to the large amounts of data reuse. Although some mapping methods have been designed to achieve a balance between the execution throughput and resource overhead, the resource consumption cost is still huge while maintaining the throughput. Network pruning is a promising and widely studied leverage to shrink the model size. Whereas, previous work didn`t consider the crossbar architecture and the corresponding mapping method, which cannot be directly utilized by crossbar-based neural network accelerators. Tightly combining the crossbar structure and its mapping, this paper proposes a crossbar-aware pruning framework based on a formulated L0-norm constrained optimization problem. Specifically, we design an L0-norm constrained gradient descent (LGD) with relaxant probabilistic projection (RPP) to solve this problem. Two grains of sparsity are successfully achieved: i) intuitive crossbar-grain sparsity and ii) column-grain sparsity with output recombination, based on which we further propose an input feature maps (FMs) reorder method to improve the model accuracy. We evaluate our crossbar-aware pruning framework on median-scale CIFAR10 dataset and large-scale ImageNet dataset with VGG and ResNet models. Our method is able to reduce the crossbar overhead by 44%-72% with little accuracy degradation. This work greatly saves the resource and the related energy cost, which provides a new co-design solution for mapping CNNs onto various crossbar devices with significantly higher efficiency.

cs.CV↗