Searcharxiv⌕ Search

arXiv subjects

Kai Zhao

Publications and source records attributed to Kai Zhao.

At least 199 records · Page 11Linked to original sources
arXiv2021

Viscosity subsoltions of Hamilton-Jacobi equations and Invariant sets of contact Hamilton systems

The objective of this paper is to present some results about viscosity subsolutions of the contact Hamiltonian-Jacobi equations on connected, closed manifold $M$ $$ H(x,\partial_x u,u)= 0, \quad x\in M. $$ Based on implicit variational principles introduced in [12,14], we focus on the monotonicity of the solution semigroups on viscosity subsolutions and the positive invariance of the epigraph for viscosity subsolutions. Besides, we show a similar consequence for strict viscosity subsolutions on $M$.

math.DS↗
arXiv2021

Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle

Recent advances in convolutional neural networks(CNNs) usually come with the expense of excessive computational overhead and memory footprint. Network compression aims to alleviate this issue by training compact models with comparable performance. However, existing compression techniques either entail dedicated expert design or compromise with a moderate performance drop. In this paper, we propose a novel structured sparsification method for efficient network compression. The proposed method automatically induces structured sparsity on the convolutional weights, thereby facilitating the implementation of the compressed model with the highly-optimized group convolution. We further address the problem of inter-group communication with a learnable channel shuffle mechanism. The proposed approach can be easily applied to compress many network architectures with a negligible performance drop. Extensive experimental results and analysis demonstrate that our approach gives a competitive performance against the recent network compression counterparts with a sound accuracy-complexity trade-off.

cs.CV↗
arXiv2021

Deep Hough Transform for Semantic Line Detection

We focus on a fundamental task of detecting meaningful line structures, a.k.a. semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. To better exploit the property of lines, in this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e. non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features eg features along lines close to a specific line, that are critical for accurate line detection. In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives.

cs.CV↗
arXiv2021

Multi-objective Herglotz' variational principle and cooperative Hamilton-Jacobi systems

We study a multi-objective variational problem of Herglotz' type with cooperative linear coupling. We established the associated Euler-Lagrange equations and the characteristic system for cooperative weakly coupled systems of Hamilton-Jacobi equations. We also established the relation of the value functions of this variational problem with the viscosity solutions of cooperative weakly coupled systems of Hamilton-Jacobi equations. Comparing to the previous work in stochastic frame, this approach affords a pure deterministic explanation of this problem under more general conditions. We also showed this approach is valid for general linearly coupling matrix for short time.

math.AP↗
arXiv2021

FT-BLAS: A High Performance BLAS Implementation With Online Fault Tolerance

Basic Linear Algebra Subprograms (BLAS) is a core library in scientific computing and machine learning. This paper presents FT-BLAS, a new implementation of BLAS routines that not only tolerates soft errors on the fly, but also provides comparable performance to modern state-of-the-art BLAS libraries on widely-used processors such as Intel Skylake and Cascade Lake. To accommodate the features of BLAS, which contains both memory-bound and computing-bound routines, we propose a hybrid strategy to incorporate fault tolerance into our brand-new BLAS implementation: duplicating computing instructions for memory-bound Level-1 and Level-2 BLAS routines and incorporating an Algorithm-Based Fault Tolerance mechanism for computing-bound Level-3 BLAS routines. Our high performance and low overhead are obtained from delicate assembly-level optimization and a kernel-fusion approach to the computing kernels. Experimental results demonstrate that FT-BLAS offers high reliability and high performance -- faster than Intel MKL, OpenBLAS, and BLIS by up to 3.50%, 22.14% and 21.70%, respectively, for routines spanning all three levels of BLAS we benchmarked, even under hundreds of errors injected per minute.

cs.DC↗
arXiv2021

The localization of quantum random walks on sierpinski gaskets

We consider the discrete time quantum random walks on a Sierpinski gasket. We study the hitting probability as the level of fractal goes to infinity in terms of their localization exponents $β_w$ , total variation exponents $δ_w$ and relative entropy exponents $η_w$ . We define and solve the amplitude Green functions recursively when the level of the fractal graph goes to infinity. We obtain exact recursive formulas for the amplitude Green functions, based on which the hitting probabilities and expectation of the first-passage time are calculated. Using the recursive formula with the aid of Monte Carlo integration, we evaluate their numerical values. We also show that when the level of the fractal graph goes to infinity, with probability 1, the quantum random walks will return to origin, i.e., the quantum walks on Sierpinski gasket are recurrent.

quant-ph↗
arXiv2021

Res2Net: A New Multi-scale Backbone Architecture

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.

cs.CV↗
arXiv2021

SDRBench: Scientific Data Reduction Benchmark for Lossy Compressors

Efficient error-controlled lossy compressors are becoming critical to the success of today's large-scale scientific applications because of the ever-increasing volume of data produced by the applications. In the past decade, many lossless and lossy compressors have been developed with distinct design principles for different scientific datasets in largely diverse scientific domains. In order to support researchers and users assessing and comparing compressors in a fair and convenient way, we establish a standard compression assessment benchmark -- Scientific Data Reduction Benchmark (SDRBench). SDRBench contains a vast variety of real-world scientific datasets across different domains, summarizes several critical compression quality evaluation metrics, and integrates many state-of-the-art lossy and lossless compressors. We demonstrate evaluation results using SDRBench and summarize six valuable takeaways that are helpful to the in-depth understanding of lossy compressors.

cs.DC↗
arXiv2020

SDC Resilient Error-bounded Lossy Compressor

Lossy compression is one of the most important strategies to resolve the big science data issue, however, little work was done to make it resilient against silent data corruptions (SDC). In fact, SDC is becoming non-negligible because of exa-scale computing demand on complex scientific simulations with vast volume of data being produced or in some particular instruments/devices (such as interplanetary space probe) that need to transfer large amount of data in an error-prone environment. In this paper, we propose an SDC resilient error-bounded lossy compressor upon the SZ compression framework. Specifically, we adopt a new independent-block-wise model that decomposes the entire dataset into many independent sub-blocks to compress. Then, we design and implement a series of error detection/correction strategies based on SZ. We are the first to extend algorithm-based fault tolerance (ABFT) to lossy compression. Our proposed solution incurs negligible execution overhead without soft errors. It keeps the correctness of decompressed data still bounded within user's requirement with a very limited degradation of compression ratios upon soft errors.

cs.DC↗
arXiv2020

cuSZ: An Efficient GPU-Based Error-Bounded Lossy Compression Framework for Scientific Data

Error-bounded lossy compression is a state-of-the-art data reduction technique for HPC applications because it not only significantly reduces storage overhead but also can retain high fidelity for postanalysis. Because supercomputers and HPC applications are becoming heterogeneous using accelerator-based architectures, in particular GPUs, several development teams have recently released GPU versions of their lossy compressors. However, existing state-of-the-art GPU-based lossy compressors suffer from either low compression and decompression throughput or low compression quality. In this paper, we present an optimized GPU version, cuSZ, for one of the best error-bounded lossy compressors-SZ. To the best of our knowledge, cuSZ is the first error-bounded lossy compressor on GPUs for scientific data. Our contributions are fourfold. (1) We propose a dual-quantization scheme to entirely remove the data dependency in the prediction step of SZ such that this step can be performed very efficiently on GPUs. (2) We develop an efficient customized Huffman coding for the SZ compressor on GPUs. (3) We implement cuSZ using CUDA and optimize its performance by improving the utilization of GPU memory bandwidth. (4) We evaluate our cuSZ on five real-world HPC application datasets from the Scientific Data Reduction Benchmarks and compare it with other state-of-the-art methods on both CPUs and GPUs. Experiments show that our cuSZ improves SZ's compression throughput by up to 370.1x and 13.1x, respectively, over the production version running on single and multiple CPU cores, respectively, while getting the same quality of reconstructed data. It also improves the compression ratio by up to 3.48x on the tested data compared with another state-of-the-art GPU supported lossy compressor.

cs.DC↗
arXiv2020

FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks

Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deployed in safety-critical systems, which may suffer from soft errors caused by high-energy particles, high temperature, or abnormal voltage. Of critical importance is ensuring the stability of the CNN inference process against soft errors. Traditional fault tolerance methods are not suitable for CNN inference because error-correcting code is unable to protect computational components, instruction duplication techniques incur high overhead, and existing algorithm-based fault tolerance (ABFT) techniques cannot protect all convolution implementations. In this paper, we focus on how to protect the CNN inference process against soft errors as efficiently as possible, with the following three contributions. (1) We propose several systematic ABFT schemes based on checksum techniques and analyze their fault protection ability and runtime thoroughly.Unlike traditional ABFT based on matrix-matrix multiplication, our schemes support any convolution implementations. (2) We design a novel workflow integrating all the proposed schemes to obtain a high detection/correction ability with limited total runtime overhead. (3) We perform our evaluation using ImageNet with well-known CNN models including AlexNet, VGG-19, ResNet-18, and YOLOv2. Experimental results demonstrate that our implementation can handle soft errors with very limited runtime overhead (4%~8% in both error-free and error-injected situations).

cs.DC↗
arXiv2020

Progress of Quantum Molecular Dynamics model and its applications in Heavy Ion Collisions

In this review article, we first briefly introduce the transport theory and quantum molecular dynamics model applied in the study of the heavy ion collisions from low to intermediate energies. The developments of improved quantum molecular dynamics model (ImQMD) and ultra-relativistic quantum molecular dynamics model (UrQMD), are reviewed. The reaction mechanism and phenomena related to the fusion, multinucleon transfer, fragmentation, collective flow and particle production are reviewed and discussed within the framework of the two models. The constraints on the isospin asymmetric nuclear equation of state and in-medium nucleon-nucleon cross sections by comparing the heavy ion collision data with transport models calculations in last decades are also discussed, and the uncertainties of these constraints are analyzed as well. Finally, we discuss the future direction of the development of the transport models for improving the understanding of the reaction mechanism, the descriptions of various observables, the constraint on the nuclear equation of state, as well as for the constraint on in-medium nucleon-nucleon cross sections.

nucl-th↗
arXiv2020

Dependency Aware Filter Pruning

Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference. Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. For this purpose, identifying unimportant convolutional filters is the key to effective filter pruning. Previous work prunes filters according to either their weight norms or the corresponding batch-norm scaling factors, while neglecting the sequential dependency between adjacent layers. In this paper, we further develop the norm-based importance estimation by taking the dependency between the adjacent layers into consideration. Besides, we propose a novel mechanism to dynamically control the sparsity-inducing regularization so as to achieve the desired sparsity. In this way, we can identify unimportant filters and search for the optimal network architecture within certain resource budgets in a more principled manner. Comprehensive experimental results demonstrate the proposed method performs favorably against the existing strong baseline on the CIFAR, SVHN, and ImageNet datasets. The training sources will be publicly available after the review process.

cs.CV↗
arXiv2019

LinearFold: linear-time approximate RNA folding by 5'-to-3' dynamic programming and beam search

Motivation: Predicting the secondary structure of an RNA sequence is useful in many applications. Existing algorithms (based on dynamic programming) suffer from a major limitation: their runtimes scale cubically with the RNA length, and this slowness limits their use in genome-wide applications. Results: We present a novel alternative $O(n^3)$-time dynamic programming algorithm for RNA folding that is amenable to heuristics that make it run in $O(n)$ time and $O(n)$ space, while producing a high-quality approximation to the optimal solution. Inspired by incremental parsing for context-free grammars in computational linguistics, our alternative dynamic programming algorithm scans the sequence in a left-to-right (5'-to-3') direction rather than in a bottom-up fashion, which allows us to employ the effective beam pruning heuristic. Our work, though inexact, is the first RNA folding algorithm to achieve linear runtime (and linear space) without imposing constraints on the output structure. Surprisingly, our approximate search results in even higher overall accuracy on a diverse database of sequences with known structures. More interestingly, it leads to significantly more accurate predictions on the longest sequence families in that database (16S and 23S Ribosomal RNAs), as well as improved accuracies for long-range base pairs (500+ nucleotides apart), both of which are well known to be challenging for the current models. Availability: Our source code is available at https://github.com/LinearFold/LinearFold, and our webserver is at http://linearfold.org (sequence limit: 100,000nt).

q-bio.BM↗
arXiv2019

Deep Differentiable Random Forests for Age Estimation

Age estimation from facial images is typically cast as a label distribution learning or regression problem, since aging is a gradual progress. Its main challenge is the facial feature space w.r.t. ages is inhomogeneous, due to the large variation in facial appearance across different persons of the same age and the non-stationary property of aging. In this paper, we propose two Deep Differentiable Random Forests methods, Deep Label Distribution Learning Forest (DLDLF) and Deep Regression Forest (DRF), for age estimation. Both of them connect split nodes to the top layer of convolutional neural networks (CNNs) and deal with inhomogeneous data by jointly learning input-dependent data partitions at the split nodes and age distributions at the leaf nodes. This joint learning follows an alternating strategy: (1) Fixing the leaf nodes and optimizing the split nodes and the CNN parameters by Back-propagation; (2) Fixing the split nodes and optimizing the leaf nodes by Variational Bounding. Two Deterministic Annealing processes are introduced into the learning of the split and leaf nodes, respectively, to avoid poor local optima and obtain better estimates of tree parameters free of initial values. Experimental results show that DLDLF and DRF achieve state-of-the-art performance on three age estimation datasets.

cs.CV↗
arXiv2019

Optimizing the F-measure for Threshold-free Salient Object Detection

Current CNN-based solutions to salient object detection (SOD) mainly rely on the optimization of cross-entropy loss (CELoss). Then the quality of detected saliency maps is often evaluated in terms of F-measure. In this paper, we investigate an interesting issue: can we consistently use the F-measure formulation in both training and evaluation for SOD? By reformulating the standard F-measure we propose the relaxed F-measure which is differentiable w.r.t the posterior and can be easily appended to the back of CNNs as the loss function. Compared to the conventional cross-entropy loss of which the gradients decrease dramatically in the saturated area, our loss function, named FLoss, holds considerable gradients even when the activation approaches the target. Consequently, the FLoss can continuously force the network to produce polarized activations. Comprehensive benchmarks on several popular datasets show that FLoss outperforms the state-of-the-art with a considerable margin. More specifically, due to the polarized predictions, our method is able to obtain high-quality saliency maps without carefully tuning the optimal threshold, showing significant advantages in real-world applications.

cs.CV↗