arXiv subjects

Chao Chen

Publications and source records attributed to Chao Chen.

At least 829 records · Page 46Linked to original sources

arXiv2021

PBBFMM3D: a parallel black-box algorithm for kernel matrix-vector multiplication

Kernel matrix-vector product is ubiquitous in many science and engineering applications. However, a naive method requires $O(N^2)$ operations, which becomes prohibitive for large-scale problems. We introduce a parallel method that provably requires $O(N)$ operations to reduce the computation cost. The distinct feature of our method is that it requires only the ability to evaluate the kernel function, offering a black-box interface to users. Our parallel approach targets multi-core shared-memory machines and is implemented using OpenMP. Numerical results demonstrate up to $19\times$ speedup on 32 cores. We also present a real-world application in geostatistics, where our parallel method was used to deliver fast principle component analysis of covariance matrices.

cs.MS↗

arXiv2021

NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering

In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data. However, the global models are often obtained via a performance tradeoff among users/items, i.e., not all users/items are perfectly fitted by the global models due to the hard non-convex optimization problems in CF algorithms. Ensemble learning can address this issue by learning multiple diverse models but usually suffer from efficiency issue on large datasets or complex algorithms. In this paper, we keep the intermediate models obtained during global model learning as the snapshot models, and then adaptively combine the snapshot models for individual user-item pairs using a memory network-based method. Empirical studies on three real-world datasets show that the proposed method can extensively and significantly improve the accuracy (up to 15.9% relatively) when applied to a variety of existing collaborative filtering methods.

cs.LG↗

arXiv2021

Strong-field response time and its implications on attosecond measurement

To measure and control the electron motion in atoms and molecules by the strong laser field on the attosecond time scale is one of the research frontiers of atomic and molecular photophysics. It involves many new phenomena and processes and raises a series of questions of concepts, theories and methods. Recent studies show that the Coulomb potential can cause the ionization time lag (about 100 attoseconds) between instants of the field maximum and the ionization-rate maximum. This lag can be understood as the response time of the electronic wave function to the strong-field-induced ionization event. It has a profound influence on the subsequent ultrafast dynamics of the ionized electron and can significantly change the time-frequency properties of electron trajectory (an important theoretical tool for attosecond measurement). Here, the research progress of response time and its implications on attosecond measurement are briefly introduced.

physics.atom-ph↗

arXiv2021

Learning with Feature-Dependent Label Noise: A Progressive Approach

Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two categories: they either assume an ideal feature-independent noise, or remain heuristic without theoretical guarantees. In this paper, we propose to target a new family of feature-dependent label noise, which is much more general than commonly used i.i.d. label noise and encompasses a broad spectrum of noise patterns. Focusing on this general noise family, we propose a progressive label correction algorithm that iteratively corrects labels and refines the model. We provide theoretical guarantees showing that for a wide variety of (unknown) noise patterns, a classifier trained with this strategy converges to be consistent with the Bayes classifier. In experiments, our method outperforms SOTA baselines and is robust to various noise types and levels.

cs.LG↗

arXiv2021

Characterizing Sub-Cycle Electron Dynamics of Polar Molecules by Asymmetry in Photoelectron Momentum Distributions

Strong-field ionization of polar molecules contains rich dynamical processes such as tunneling, excitation, and Stark shift. These processes occur on a sub-cycle time scale and are difficult to distinguish in ultrafast measurements. Here, with a developed strong-field model considering effects of both Coulomb and permanent dipole, we show that photoelectron momentum distributions (PMDs) in orthogonal two-color laser fields can be utilized to resolve these processes with attosecond-scale resolution. A feature quantity related to the asymmetry in PMDs is obtained, with which the complex electron dynamics of polar molecules in each half laser cycle is characterized and the subtle time difference when electrons escaping from different sides of the polar molecule is identified.

physics.atom-ph↗

arXiv2021

Topology-Aware Segmentation Using Discrete Morse Theory

In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern. Topological correctness, such as vessel connectivity and membrane closure, is crucial for downstream analysis tasks. In this paper, we propose a new approach to train deep image segmentation networks for better topological accuracy. In particular, leveraging the power of discrete Morse theory (DMT), we identify global structures, including 1D skeletons and 2D patches, which are important for topological accuracy. Trained with a novel loss based on these global structures, the network performance is significantly improved especially near topologically challenging locations (such as weak spots of connections and membranes). On diverse datasets, our method achieves superior performance on both the DICE score and topological metrics.

cs.CV↗

arXiv2021

Object Tracking by Least Spatiotemporal Searches

Tracking a car or a person in a city is crucial for urban safety management. How can we complete the task with minimal number of spatiotemporal searches from massive camera records? This paper proposes a strategy named IHMs (Intermediate Searching at Heuristic Moments): each step we figure out which moment is the best to search according to a heuristic indicator, then at that moment search locations one by one in descending order of predicted appearing probabilities, until a search hits; iterate this step until we get the object's current location. Five searching strategies are compared in experiments, and IHMs is validated to be most efficient, which can save up to 1/3 total costs. This result provides an evidence that "searching at intermediate moments can save cost".

cs.AI↗

arXiv2021

Near-zero Downtime Recovery from Transient-error-induced Crashes

Due to the system scaling, transient errors caused by external noises, e.g., heat fluxes and particle strikes, have become a growing concern for the current and upcoming extreme-scale high-performance-computing (HPC) systems. However, since such errors are still quite rare as compared to no-fault cases, desirable solutions call for low/no-overhead systems that do not compromise the performance under no-fault conditions and also allow very fast fault recovery to minimize downtime. In this paper, we present IterPro, a light-weight compiler-assisted resilience technique to quickly and accurately recover processes from transient-error-induced crashes. IterPro repairs the corrupted process states on-the-fly upon occurrences of errors, enabling applications to continue their executions instead of being terminated. IterPro also exploits side effects introduced by induction variable based code optimization techniques to improve its recovery capability. To this end, two new code transformation passes are introduced to expose the side effects for resilience purposes. We evaluated IterPro with 4 scientific workloads as well as the NPB benchmarks suite. During their normal execution, IterPro incurs almost zero runtime overhead and a small, fixed 27MB memory overhead. Meanwhile, IterPro can recover on an average 83.55% of crash-causing errors within dozens of milliseconds with negligible downtime. With such an effective recovery mechanism, IterPro could tremendously mitigate the overheads and resource requirements of the resilience subsystem in future extreme-scale systems.

cs.DC↗

arXiv2021

Reachability-based Trajectory Safeguard (RTS): A Safe and Fast Reinforcement Learning Safety Layer for Continuous Control

Reinforcement Learning (RL) algorithms have achieved remarkable performance in decision making and control tasks due to their ability to reason about long-term, cumulative reward using trial and error. However, during RL training, applying this trial-and-error approach to real-world robots operating in safety critical environment may lead to collisions. To address this challenge, this paper proposes a Reachability-based Trajectory Safeguard (RTS), which leverages reachability analysis to ensure safety during training and operation. Given a known (but uncertain) model of a robot, RTS precomputes a Forward Reachable Set of the robot tracking a continuum of parameterized trajectories. At runtime, the RL agent selects from this continuum in a receding-horizon way to control the robot; the FRS is used to identify if the agent's choice is safe or not, and to adjust unsafe choices. The efficacy of this method is illustrated on three nonlinear robot models, including a 12-D quadrotor drone, in simulation and in comparison with state-of-the-art safe motion planning methods.

cs.RO↗

arXiv2021

Human-in-the-loop Auditory Cueing Strategy for Gait Modification

External feedback in the form of visual, auditory and tactile cues has been used to assist patients to overcome mobility challenges. However, these cues can become less effective over time. There is limited research on adapting cues to account for inter and intra-personal variations in cue responsiveness. We propose a cue-provision framework that consists of a gait performance monitoring algorithm and an adaptive cueing strategy to improve gait performance. The proposed approach learns a model of the person's response to cues using Gaussian Process regression. The model is then used within an on-line optimization algorithm to generate cues to improve gait performance. We conduct a study with healthy participants to evaluate the ability of the adaptive cueing strategy to influence human gait, and compare its effectiveness to two other cueing approaches: the standard fixed cue approach and a proportional cue approach. The results show that adaptive cueing is more effective in changing the person's gait state once the response model is learned compared to the other methods.

cs.RO↗

arXiv2021

Stability of SGD: Tightness Analysis and Improved Bounds

Stochastic Gradient Descent (SGD) based methods have been widely used for training large-scale machine learning models that also generalize well in practice. Several explanations have been offered for this generalization performance, a prominent one being algorithmic stability [18]. However, there are no known examples of smooth loss functions for which the analysis can be shown to be tight. Furthermore, apart from the properties of the loss function, data distribution has also been shown to be an important factor in generalization performance. This raises the question: is the stability analysis of [18] tight for smooth functions, and if not, for what kind of loss functions and data distributions can the stability analysis be improved? In this paper we first settle open questions regarding tightness of bounds in the data-independent setting: we show that for general datasets, the existing analysis for convex and strongly-convex loss functions is tight, but it can be improved for non-convex loss functions. Next, we give a novel and improved data-dependent bounds: we show stability upper bounds for a large class of convex regularized loss functions, with negligible regularization parameters, and improve existing data-dependent bounds in the non-convex setting. We hope that our results will initiate further efforts to better understand the data-dependent setting under non-convex loss functions, leading to an improved understanding of the generalization abilities of deep networks.

cs.LG↗

arXiv2021

Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach

Recently, Generative Adversarial Networks (GANs) have demonstrated their potential in federated learning, i.e., learning a centralized model from data privately hosted by multiple sites. A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites. A major theoretical challenge for the federated GAN is the heterogeneity of the local data distributions. Traditional approaches cannot guarantee to learn the target distribution, which isa mixture of the highly different local distributions. This paper tackles this theoretical challenge, and for the first time, provides a provably correct framework for federated GAN. We propose a new approach called Universal Aggregation, which simulates a centralized discriminator via carefully aggregating the mixture of all private discriminators. We prove that a generator trained with this simulated centralized discriminator can learn the desired target distribution. Through synthetic and real datasets, we show that our method can learn the mixture of largely different distributions where existing federated GAN methods fail.

cs.LG↗

arXiv2021

Strain engineering of epitaxial oxide heterostructures beyond substrate limitations

The limitation of commercially available single-crystal substrates and the lack of continuous strain tunability preclude the ability to take full advantage of strain engineering for further exploring novel properties and exhaustively studying fundamental physics in complex oxides. Here we report an approach for imposing continuously tunable, large epitaxial strain in oxide heterostructures beyond substrate limitations by inserting an interface layer through tailoring its gradual strain relaxation. Taking BiFeO3 as a model system, we demonstrate that the introduction of an ultrathin interface layer allows the creation of a desired strain that can induce phase transition and stabilize a new metastable super-tetragonal phase as well as morphotropic phase boundaries overcoming substrate limitations. Furthermore, continuously tunable strain from tension to compression can be generated by precisely adjusting the thickness of the interface layer, leading to the first achievement of continuous O-R-T phase transition in BiFeO3 on a single substrate. This proposed route could be extended to other oxide heterostructures, providing a platform for creating exotic phases and emergent phenomena.

cond-mat.mtrl-sci↗

arXiv2021

Differentiable Nonparametric Belief Propagation

We present a differentiable approach to learn the probabilistic factors used for inference by a nonparametric belief propagation algorithm. Existing nonparametric belief propagation methods rely on domain-specific features encoded in the probabilistic factors of a graphical model. In this work, we replace each crafted factor with a differentiable neural network enabling the factors to be learned using an efficient optimization routine from labeled data. By combining differentiable neural networks with an efficient belief propagation algorithm, our method learns to maintain a set of marginal posterior samples using end-to-end training. We evaluate our differentiable nonparametric belief propagation (DNBP) method on a set of articulated pose tracking tasks and compare performance with a recurrent neural network. Results from this comparison demonstrate the effectiveness of using learned factors for tracking and suggest the practical advantage over hand-crafted approaches. The project webpage is available at: progress.eecs.umich.edu/projects/dnbp.

cs.RO↗

arXiv2020

Localization in the Crowd with Topological Constraints

We address the problem of crowd localization, i.e., the prediction of dots corresponding to people in a crowded scene. Due to various challenges, a localization method is prone to spatial semantic errors, i.e., predicting multiple dots within a same person or collapsing multiple dots in a cluttered region. We propose a topological approach targeting these semantic errors. We introduce a topological constraint that teaches the model to reason about the spatial arrangement of dots. To enforce this constraint, we define a persistence loss based on the theory of persistent homology. The loss compares the topographic landscape of the likelihood map and the topology of the ground truth. Topological reasoning improves the quality of the localization algorithm especially near cluttered regions. On multiple public benchmarks, our method outperforms previous localization methods. Additionally, we demonstrate the potential of our method in improving the performance in the crowd counting task.

cs.CV↗

arXiv2020

Error-Bounded Correction of Noisy Labels

To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on the noisy classifiers (i.e., models trained on the noisy training data) to determine whether a label is trustworthy. However, it remains unknown why this heuristic works well in practice. In this paper, we provide the first theoretical explanation for these methods. We prove that the prediction of a noisy classifier can indeed be a good indicator of whether the label of a training data is clean. Based on the theoretical result, we propose a novel algorithm that corrects the labels based on the noisy classifier prediction. The corrected labels are consistent with the true Bayesian optimal classifier with high probability. We incorporate our label correction algorithm into the training of deep neural networks and train models that achieve superior testing performance on multiple public datasets.

cs.CV↗

arXiv2020

Fast Approximation of the Gauss-Newton Hessian Matrix for the Multilayer Perceptron

We introduce a fast algorithm for entry-wise evaluation of the Gauss-Newton Hessian (GNH) matrix for the fully-connected feed-forward neural network. The algorithm has a precomputation step and a sampling step. While it generally requires $O(Nn)$ work to compute an entry (and the entire column) in the GNH matrix for a neural network with $N$ parameters and $n$ data points, our fast sampling algorithm reduces the cost to $O(n+d/ε^2)$ work, where $d$ is the output dimension of the network and $ε$ is a prescribed accuracy (independent of $N$). One application of our algorithm is constructing the hierarchical-matrix (H-matrix) approximation of the GNH matrix for solving linear systems and eigenvalue problems. It generally requires $O(N^2)$ memory and $O(N^3)$ work to store and factorize the GNH matrix, respectively. The H-matrix approximation requires only $O(N r_o)$ memory footprint and $O(N r_o^2)$ work to be factorized, where $r_o \ll N$ is the maximum rank of off-diagonal blocks in the GNH matrix. We demonstrate the performance of our fast algorithm and the H-matrix approximation on classification and autoencoder neural networks.

math.NA↗

arXiv2020

Deep Variational Instance Segmentation

Instance Segmentation, which seeks to obtain both class and instance labels for each pixel in the input image, is a challenging task in computer vision. State-of-the-art algorithms often employ two separate stages, the first one generating object proposals and the second one recognizing and refining the boundaries. Further, proposals are usually based on detectors such as faster R-CNN which search for boxes in the entire image exhaustively. In this paper, we propose a novel algorithm that directly utilizes a fully convolutional network (FCN) to predict instance labels. Specifically, we propose a variational relaxation of instance segmentation as minimizing an optimization functional for a piecewise-constant segmentation problem, which can be used to train an FCN end-to-end. It extends the classical Mumford-Shah variational segmentation problem to be able to handle permutation-invariant labels in the ground truth of instance segmentation. Experiments on PASCAL VOC 2012, Semantic Boundaries dataset(SBD), and the MSCOCO 2017 dataset show that the proposed approach efficiently tackle the instance segmentation task. The source code and trained models will be released with the paper.

cs.CV↗