arXiv subjects

Fei He

Publications and source records attributed to Fei He.

At least 55 records · Page 3Linked to original sources

arXiv2023

Leveraging Datapath Propagation in IC3 for Hardware Model Checking

IC3 is a famous bit-level framework for safety verification. By incorporating datapath abstraction, a notable enhancement in the efficiency of hardware verification can be achieved. However, datapath abstraction entails a coarse level of abstraction where all datapath operations are approximated as uninterpreted functions. This level of abstraction, albeit useful, can lead to an increased computational burden during the verification process as it necessitates extensive exploration of redundant abstract state space. In this paper, we introduce a novel approach called datapath propagation. Our method involves leveraging concrete constant values to iteratively compute the outcomes of relevant datapath operations and their associated uninterpreted functions. Meanwhile, we generate potentially useful datapath propagation lemmas in abstract state space and tighten the datapath abstraction. With this technique, the abstract state space can be reduced, and the verification efficiency is significantly improved. We implemented the proposed approach and conducted extensive experiments. The results show promising improvements of our approach compared to the state-of-the-art verifiers.

cs.LO↗

arXiv2023

Model-Free Market Risk Hedging Using Crowding Networks

Crowding is widely regarded as one of the most important risk factors in designing portfolio strategies. In this paper, we analyze stock crowding using network analysis of fund holdings, which is used to compute crowding scores for stocks. These scores are used to construct costless long-short portfolios, computed in a distribution-free (model-free) way and without using any numerical optimization, with desirable properties of hedge portfolios. More specifically, these long-short portfolios provide protection for both small and large market price fluctuations, due to their negative correlation with the market and positive convexity as a function of market returns. By adding our long-short portfolio to a baseline portfolio such as a traditional 60/40 portfolio, our method provides an alternative way to hedge portfolio risk including tail risk, which does not require costly option-based strategies or complex numerical optimization. The total cost of such hedging amounts to the total cost of rebalancing the hedge portfolio.

q-fin.PM↗

arXiv2023

InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation

Video instance segmentation (VIS) aims at segmenting and tracking objects in videos. Prior methods typically generate frame-level or clip-level object instances first and then associate them by either additional tracking heads or complex instance matching algorithms. This explicit instance association approach increases system complexity and fails to fully exploit temporal cues in videos. In this paper, we design a simple, fast and yet effective query-based framework for online VIS. Relying on an instance query and proposal propagation mechanism with several specially developed components, this framework can perform accurate instance association implicitly. Specifically, we generate frame-level object instances based on a set of instance query-proposal pairs propagated from previous frames. This instance query-proposal pair is learned to bind with one specific object across frames through conscientiously developed strategies. When using such a pair to predict an object instance on the current frame, not only the generated instance is automatically associated with its precursors on previous frames, but the model gets a good prior for predicting the same object. In this way, we naturally achieve implicit instance association in parallel with segmentation and elegantly take advantage of temporal clues in videos. To show the effectiveness of our method InsPro, we evaluate it on two popular VIS benchmarks, i.e., YouTube-VIS 2019 and YouTube-VIS 2021. Without bells-and-whistles, our InsPro with ResNet-50 backbone achieves 43.2 AP and 37.6 AP on these two benchmarks respectively, outperforming all other online VIS methods.

cs.CV↗

arXiv2022

Learning Disentangled Label Representations for Multi-label Classification

Although various methods have been proposed for multi-label classification, most approaches still follow the feature learning mechanism of the single-label (multi-class) classification, namely, learning a shared image feature to classify multiple labels. However, we find this One-shared-Feature-for-Multiple-Labels (OFML) mechanism is not conducive to learning discriminative label features and makes the model non-robustness. For the first time, we mathematically prove that the inferiority of the OFML mechanism is that the optimal learned image feature cannot maintain high similarities with multiple classifiers simultaneously in the context of minimizing cross-entropy loss. To address the limitations of the OFML mechanism, we introduce the One-specific-Feature-for-One-Label (OFOL) mechanism and propose a novel disentangled label feature learning (DLFL) framework to learn a disentangled representation for each label. The specificity of the framework lies in a feature disentangle module, which contains learnable semantic queries and a Semantic Spatial Cross-Attention (SSCA) module. Specifically, learnable semantic queries maintain semantic consistency between different images of the same label. The SSCA module localizes the label-related spatial regions and aggregates located region features into the corresponding label feature to achieve feature disentanglement. We achieve state-of-the-art performance on eight datasets of three tasks, \ie, multi-label classification, pedestrian attribute recognition, and continual multi-label learning.

cs.CV↗

arXiv2022

EqFix: Fixing LaTeX Equation Errors by Examples

LaTeX is a widely-used document preparation system. Its powerful ability in mathematical equation editing is perhaps the main reason for its popularity in academia. Sometimes, however, even an expert user may spend much time fixing an erroneous equation. In this paper, we present EqFix, a synthesis-based repairing system for LaTeX equations. It employs a set of fixing rules and can suggest possible repairs for common errors in LaTeX equations. A domain-specific language is proposed for formally expressing the fixing rules. The fixing rules can be automatically synthesized from a set of input-output examples. An extension of relaxers is also introduced to enhance the practicality of EqFix. We evaluate EqFix on real-world examples and find that it can synthesize rules with high generalization ability. Compared with a state-of-the-art string transformation synthesizer, EqFix solved 37% more cases and spent less than half of their synthesis time.

cs.PL↗

arXiv2022

QueryProp: Object Query Propagation for High-Performance Video Object Detection

Video object detection has been an important yet challenging topic in computer vision. Traditional methods mainly focus on designing the image-level or box-level feature propagation strategies to exploit temporal information. This paper argues that with a more effective and efficient feature propagation framework, video object detectors can gain improvement in terms of both accuracy and speed. For this purpose, this paper studies object-level feature propagation, and proposes an object query propagation (QueryProp) framework for high-performance video object detection. The proposed QueryProp contains two propagation strategies: 1) query propagation is performed from sparse key frames to dense non-key frames to reduce the redundant computation on non-key frames; 2) query propagation is performed from previous key frames to the current key frame to improve feature representation by temporal context modeling. To further facilitate query propagation, an adaptive propagation gate is designed to achieve flexible key frame selection. We conduct extensive experiments on the ImageNet VID dataset. QueryProp achieves comparable accuracy with state-of-the-art methods and strikes a decent accuracy/speed trade-off. Code is available at https://github.com/hf1995/QueryProp.

cs.CV↗

arXiv2022

Bispectrum-based Cross-frequency Functional Connectivity: Classification of Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative disease known to affect brain functional connectivity (FC). Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals such as electroencephalography (EEG) recordings into discrete frequency bands and analysing them in isolation. We address this limitation by quantifying cross-frequency FC in addition to the traditional within-band approach. Cross-bispectrum, a higher-order spectral analysis, is used to measure the nonlinear FC and is compared with the cross-spectrum, which only measures the linear FC within bands. Each frequency coupling is then used to construct an FC network, which is in turn vectorised and used to train a classifier. We show that fusing features from networks improves classification accuracy. Although both within-frequency and cross-frequency networks can be used to predict AD with high accuracy, our results show that bispectrum-based FC outperforms cross-spectrum suggesting an important role of cross-frequency FC.

q-bio.NC↗

arXiv2022

PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation

This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior works address this problem by simply adding a dense depth regression head to panoptic segmentation (PS) networks, resulting in two independent task branches. This neglects the mutually-beneficial relations between these two tasks, thus failing to exploit handy instance-level semantic cues to boost depth accuracy while also producing sub-optimal depth maps. To overcome these limitations, we propose a unified framework for the DPS task by applying a dynamic convolution technique to both the PS and depth prediction tasks. Specifically, instead of predicting depth for all pixels at a time, we generate instance-specific kernels to predict depth and segmentation masks for each instance. Moreover, leveraging the instance-wise depth estimation scheme, we add additional instance-level depth cues to assist with supervising the depth learning via a new depth loss. Extensive experiments on Cityscapes-DPS and SemKITTI-DPS show the effectiveness and promise of our method. We hope our unified solution to DPS can lead a new paradigm in this area. Code is available at https://github.com/NaiyuGao/PanopticDepth.

cs.CV↗

arXiv2022

Lay-it-out: Interactive Design of Layout-Sensitive Grammars

Layout-sensitive grammars have been adopted in many modern programming languages. However, tool support for this kind of grammars still remains limited and immature. In this paper, we present Lay-it-out, an interactive framework for layout-sensitive grammar design. Beginning with a user-defined ambiguous grammar, our framework refines it by synthesizing layout constraints through user interaction. For ease of interaction, a shortest nonempty ambiguous sentence (if exists) is automatically generated by our bounded ambiguity checker via SMT solving. The soundness and completeness of our SMT encoding are mechanized in the Coq proof assistant. Case studies on real grammars, including a full grammar, demonstrate the practicality and scalability of our approach.

cs.PL↗

arXiv2022

On the biharmonic heat equation on complete Riemannian manifolds

We study entire solutions of the biharmonic heat equation on complete Riemannian manifolds without boundary. We provide exponential decay estimates for the biharmonic heat kernel under assumptions on the lower bound of Ricci curvature and noncollapsing of unit balls. And we prove a uniqueness criteria for the Cauchy problem. As corollaries we prove the conservation law for the biharmonic heat kernel and a uniform L-infinite estimate for entire solutions starting with bounded initial data.

math.DG↗

arXiv2022

ProbTA: A sound and complete proof rule for probabilistic verification

We propose a sound and complete proof rule ProbTA for quantitative analysis of violation probability of probabilistic programs. Our approach extends the technique of trace abstraction with probability in the control-flow randomness style, in contrast to previous work of combining trace abstraction and probabilisitic verification which adopts the data randomness style. In our method, a program specification is proved or disproved by decomposing the program into different modules of traces. Precise quantitative analysis is enabled by novel models proposed to bridge program verification and probability theory. Based on the proof rule, we propose a new automated algorithm via CEGAR involving multiple technical issues unprecedented in non-probabilistic trace abstraction and data randomness-based approach.

cs.PL↗

arXiv2022

Multi-Phase Locking Value: A Generalized Method for Determining Instantaneous Multi-frequency Phase Coupling

Many physical, biological and neural systems behave as coupled oscillators, with characteristic phase coupling across different frequencies. Methods such as $n:m$ phase locking value and bi-phase locking value have previously been proposed to quantify phase coupling between two resonant frequencies (e.g. $f$, $2f/3$) and across three frequencies (e.g. $f_1$, $f_2$, $f_1+f_2$), respectively. However, the existing phase coupling metrics have their limitations and limited applications. They cannot be used to detect or quantify phase coupling across multiple frequencies (e.g. $f_1$, $f_2$, $f_3$, $f_4$, $f_1+f_2+f_3-f_4$), or coupling that involves non-integer multiples of the frequencies (e.g. $f_1$, $f_2$, $2f_1/3+f_2/3$). To address the gap, this paper proposes a generalized approach, named multi-phase locking value (M-PLV), for the quantification of various types of instantaneous multi-frequency phase coupling. Different from most instantaneous phase coupling metrics that measure the simultaneous phase coupling, the proposed M-PLV method also allows the detection of delayed phase coupling and the associated time lag between coupled oscillators. The M-PLV has been tested on cases where synthetic coupled signals are generated using white Gaussian signals, and a system comprised of multiple coupled Rössler oscillators. Results indicate that the M-PLV can provide a reliable estimation of the time window and frequency combination where the phase coupling is significant, as well as a precise determination of time lag in the case of delayed coupling. This method has the potential to become a powerful new tool for exploring phase coupling in complex nonlinear dynamic systems.

q-bio.NC↗

arXiv2021

Characterising Alzheimer's Disease with EEG-based Energy Landscape Analysis

Alzheimer's disease (AD) is one of the most common neurodegenerative diseases, with around 50 million patients worldwide. Accessible and non-invasive methods of diagnosing and characterising AD are therefore urgently required. Electroencephalography (EEG) fulfils these criteria and is often used when studying AD. Several features derived from EEG were shown to predict AD with high accuracy, e.g. signal complexity and synchronisation. However, the dynamics of how the brain transitions between stable states have not been properly studied in the case of AD and EEG data. Energy landscape analysis is a method that can be used to quantify these dynamics. This work presents the first application of this method to both AD and EEG. Energy landscape assigns energy value to each possible state, i.e. pattern of activations across brain regions. The energy is inversely proportional to the probability of occurrence. By studying the features of energy landscapes of 20 AD patients and 20 healthy age-matched counterparts, significant differences were found. The dynamics of AD patients' brain networks were shown to be more constrained - with more local minima, less variation in basin size, and smaller basins. We show that energy landscapes can predict AD with high accuracy, performing significantly better than baseline models.

q-bio.NC↗

arXiv2021

Measurement of Neutron Lifetime and Purcell Effect

Purcell effect predicts that spontaneous radiation is not an intrinsic property of matter, but is affected by the environment in which it is located, and is the result of the interaction of matter and field. Purcell effect can be inferred from Fermi Gold rule through strict quantum electrodynamics (QED), and through it can achieve the enhancement or suppression of radiation. We suggest that, in principle, the Purcell effect can be detected at the percentage level of neutron decay in experiments with trapped ultra-cold neutrons. As a test of our claim, we propose a currently achievable experimental protocol that can detect whether Purcell effect has occurred in an trapped ultra-cold neutron lifetime measurement experiment. Finally, we discuss the discrepancy in current methods of measuring neutron lifetime, which may be caused by different experimental setups.

nucl-th↗

arXiv2021

Automatic Detection and Resolution of Software Merge Conflicts: Are We There Yet?

Developers create software branches for tentative feature addition and bug fixing, and periodically merge branches to release software with new features or repairing patches. When the program edits from different branches textually overlap (i.e., textual conflicts), or the co-application of those edits lead to compilation or runtime errors (i.e., compiling or dynamic conflicts), it is challenging and time-consuming for developers to eliminate merge conflicts. Prior studies examined %the popularity of merge conflicts and how conflicts were related to code smells or software development process; tools were built to find and solve conflicts. However, some fundamental research questions are still not comprehensively explored, including (1) how conflicts were introduced, (2) how developers manually resolved conflicts, and (3) what conflicts cannot be handled by current tools. For this paper, we took a hybrid approach that combines automatic detection with manual inspection to reveal 204 merge conflicts and their resolutions in 15 open-source repositories. %in the version history of 15 open-source projects. Our data analysis reveals three phenomena. First, compiling and dynamic conflicts are harder to detect, although current tools mainly focus on textual conflicts. Second, in the same merging context, developers usually resolved similar textual conflicts with similar strategies. Third, developers manually fixed most of the inspected compiling and dynamic conflicts by similarly editing the merged version as what they did for one of the branches. Our research reveals the challenges and opportunities for automatic detection and resolution of merge conflicts; it also sheds light on related areas like systematic program editing and change recommendation.

cs.SE↗

arXiv2021

Machine Learning Percolation Model

Recent advances in machine learning have become increasingly popular in the applications of phase transitions and critical phenomena. By machine learning approaches, we try to identify the physical characteristics in the two-dimensional percolation model. To achieve this, we adopt Monte Carlo simulation to generate dataset at first, and then we employ several approaches to analyze the dataset. Four kinds of convolutional neural networks (CNNs), one variational autoencoder (VAE), one convolutional VAE (cVAE), one principal component analysis (PCA), and one $k$-means are used for identifying order parameter, the permeability, and the critical transition point. The former three kinds of CNNs can simulate the two order parameters and the permeability with high accuracy, and good extrapolating performance. The former two kinds of CNNs have high anti-noise ability. To validate the robustness of the former three kinds of CNNs, we also use the VAE and the cVAE to generate new percolating configurations to add perturbations into the raw configurations. We find that there is no difference by using the raw or the perturbed configurations to identify the physical characteristics, under the prerequisite of corresponding labels. In the case of lacking labels, we use unsupervised learning to detect the physical characteristics. The PCA, a classical unsupervised learning, performs well when identifying the permeability but fails to deduce order parameter. Hence, we apply the fourth kinds of CNNs with different preset thresholds, and identify a new order parameter and the critical transition point. Our findings indicate that the effectiveness of machine learning still needs to be evaluated in the applications of phase transitions and critical phenomena.

cond-mat.dis-nn↗

arXiv2020

Google Crowdsourced Speech Corpora and Related Open-Source Resources for Low-Resource Languages and Dialects: An Overview

This paper presents an overview of a program designed to address the growing need for developing freely available speech resources for under-represented languages. At present we have released 38 datasets for building text-to-speech and automatic speech recognition applications for languages and dialects of South and Southeast Asia, Africa, Europe and South America. The paper describes the methodology used for developing such corpora and presents some of our findings that could benefit under-represented language communities.

cs.CL↗

arXiv2020

On distributionally robust extreme value analysis

We study distributional robustness in the context of Extreme Value Theory (EVT). We provide a data-driven method for estimating extreme quantiles in a manner that is robust against incorrect model assumptions underlying the application of the standard Extremal Types Theorem. Typical studies in distributional robustness involve computing worst case estimates over a model uncertainty region expressed in terms of the Kullback-Leibler discrepancy. We go beyond standard distributional robustness in that we investigate different forms of discrepancies, and prove rigorous results which are helpful for understanding the role of a putative model uncertainty region in the context of extreme quantile estimation. Finally, we illustrate our data-driven method in various settings, including examples showing how standard EVT can significantly underestimate quantiles of interest.

math.ST↗