arXiv subjects

Feng Chen

Publications and source records attributed to Feng Chen.

At least 253 records · Page 14Linked to original sources

arXiv2023

Solar coronal magnetic field measurements using spectral lines available in Hinode/EIS observations: Strong and weak field techniques and temperature diagnostics

Recently, it has been proposed that the magnetic-field-induced transition (MIT) in Fe X can be used to measure coronal magnetic field strengths. Several techniques, the direct line ratio technique and the weak and strong magnetic field techniques, are developed to apply the MIT theory to spectroscopic observations taken by EUV Imaging Spectrometer (EIS) onboard Hinode. However, the suitability of coronal magnetic field measurements based on the weak and strong magnetic field techniques has not been evaluated. Besides, temperature diagnostics is also important for measuring coronal magnetic field based on the MIT theory, but how to determine the accurate formation temperature of the Fe X lines from EIS observations still needs investigation. In this study, we synthesized emissions of several spectral lines from a 3D radiation magnetohydrodynamic model of a solar active region, and then derived magnetic field strengths using different methods. We first compared the magnetic field strengths derived from the weak and strong magnetic field techniques to the values in the model. Our study suggests that both weak and strong magnetic field techniques underestimate the coronal magnetic field strength. Then we developed two methods to calculate the formation temperature of the Fe X lines. One is based on differential emission measure analyses, and the other is deriving temperature from the Fe IX and Fe XI line pairs. However, neither of the two methods can provide temperature determination for accurate coronal magnetic field measurements as those derived from the Fe X 174/175 and 184/345 Å line ratios. More efforts are still needed for accurate coronal magnetic field measurements using EIS observations.

astro-ph.SR↗

arXiv2023

Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning

Utilizing messages from teammates can improve coordination in cooperative Multi-agent Reinforcement Learning (MARL). Previous works typically combine raw messages of teammates with local information as inputs for policy. However, neglecting message aggregation poses significant inefficiency for policy learning. Motivated by recent advances in representation learning, we argue that efficient message aggregation is essential for good coordination in cooperative MARL. In this paper, we propose Multi-Agent communication via Self-supervised Information Aggregation (MASIA), where agents can aggregate the received messages into compact representations with high relevance to augment the local policy. Specifically, we design a permutation invariant message encoder to generate common information-aggregated representation from messages and optimize it via reconstructing and shooting future information in a self-supervised manner. Hence, each agent would utilize the most relevant parts of the aggregated representation for decision-making by a novel message extraction mechanism. Furthermore, considering the potential of offline learning for real-world applications, we build offline benchmarks for multi-agent communication, which is the first as we know. Empirical results demonstrate the superiority of our method in both online and offline settings. We also release the built offline benchmarks in this paper as a testbed for communication ability validation to facilitate further future research.

cs.LG↗

arXiv2023

Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information

Due to various and serious adverse impacts of spreading fake news, it is often known that only people with malicious intent would propagate fake news. However, it is not necessarily true based on social science studies. Distinguishing the types of fake news spreaders based on their intent is critical because it will effectively guide how to intervene to mitigate the spread of fake news with different approaches. To this end, we propose an intent classification framework that can best identify the correct intent of fake news. We will leverage deep reinforcement learning (DRL) that can optimize the structural representation of each tweet by removing noisy words from the input sequence when appending an actor to the long short-term memory (LSTM) intent classifier. Policy gradient DRL model (e.g., REINFORCE) can lead the actor to a higher delayed reward. We also devise a new uncertainty-aware immediate reward using a subjective opinion that can explicitly deal with multidimensional uncertainty for effective decision-making. Via 600K training episodes from a fake news tweets dataset with an annotated intent class, we evaluate the performance of uncertainty-aware reward in DRL. Evaluation results demonstrate that our proposed framework efficiently reduces the number of selected words to maintain a high 95\% multi-class accuracy.

cs.CL↗

arXiv2023

How Out-of-Distribution Data Hurts Semi-Supervised Learning

Recent semi-supervised learning algorithms have demonstrated greater success with higher overall performance due to better-unlabeled data representations. Nonetheless, recent research suggests that the performance of the SSL algorithm can be degraded when the unlabeled set contains out-of-distribution examples (OODs). This work addresses the following question: How do out-of-distribution (OOD) data adversely affect semi-supervised learning algorithms? To answer this question, we investigate the critical causes of OOD's negative effect on SSL algorithms. In particular, we found that 1) certain kinds of OOD data instances that are close to the decision boundary have a more significant impact on performance than those that are further away, and 2) Batch Normalization (BN), a popular module, may degrade rather than improve performance when the unlabeled set contains OODs. In this context, we developed a unified weighted robust SSL framework that can be easily extended to many existing SSL algorithms and improve their robustness against OODs. More specifically, we developed an efficient bi-level optimization algorithm that could accommodate high-order approximations of the objective and scale to multiple inner optimization steps to learn a massive number of weight parameters while outperforming existing low-order approximations of bi-level optimization. Further, we conduct a theoretical study of the impact of faraway OODs in the BN step and propose a weighted batch normalization (WBN) procedure for improved performance. Finally, we discuss the connection between our approach and low-order approximation techniques. Our experiments on synthetic and real-world datasets demonstrate that our proposed approach significantly enhances the robustness of four representative SSL algorithms against OODs compared to four state-of-the-art robust SSL strategies.

cs.LG↗

arXiv2022

Quantum enhanced sensing by echoing spin-nematic squeezing in atomic Bose-Einstein condensate

Quantum entanglement can provide enhanced precision beyond standard quantum limit (SQL), the highest precision achievable with classical means. It remains challenging, however, to observe large enhancement limited by the experimental abilities to prepare, maintain, manipulate and detect entanglement. Here, we present nonlinear interferometry protocols based on echoing spin-nematic squeezing to achieve record high enhancement factors in atomic Bose-Einstein condensate. The echo is realized by a state-flip of the spin-nematic squeezed vacuum, which serves as the probe state and is refocused back to the vicinity of the unsqueezed initial state while carrying out near noiseless amplification of a signal encoded. A sensitivity of $21.6\pm0.5$ decibels (dB) for a small-angle Rabi rotation beyond the two-mode SQL of 26400 atoms as well as $16.6\pm1.3$ dB for phase sensing in a Ramsey interferometer are observed. The absolute phase sensitivity for the latter extrapolates to $103~\rm{pT/\sqrt{Hz}}$ at a probe volume of $18~μ\rm{m}^3$ for near-resonant microwave field sensing. Our work highlights the excellent many-body coherence of spin-nematic squeezing and suggests its possible quantum metrological applications in atomic magnetometer, atomic optical clock, and fundamental testing of Lorentz symmetry violation, etc.

cond-mat.quant-gas↗

arXiv2022

PPO-UE: Proximal Policy Optimization via Uncertainty-Aware Exploration

Proximal Policy Optimization (PPO) is a highly popular policy-based deep reinforcement learning (DRL) approach. However, we observe that the homogeneous exploration process in PPO could cause an unexpected stability issue in the training phase. To address this issue, we propose PPO-UE, a PPO variant equipped with self-adaptive uncertainty-aware explorations (UEs) based on a ratio uncertainty level. The proposed PPO-UE is designed to improve convergence speed and performance with an optimized ratio uncertainty level. Through extensive sensitivity analysis by varying the ratio uncertainty level, our proposed PPO-UE considerably outperforms the baseline PPO in Roboschool continuous control tasks.

cs.LG↗

arXiv2022

Neural network quantum state with proximal optimization: a ground-state searching scheme based on variational Monte Carlo

Neural network quantum states (NQS), incorporating with variational Monte Carlo (VMC) method, are shown to be a promising way to investigate quantum many-body physics. Whereas vanilla VMC methods perform one gradient update per sample, we introduce a novel objective function with proximal optimization (PO) that enables multiple updates via reusing the mismatched samples. Our VMC-PO method keeps the advantage of the previous importance sampling gradient optimization algorithm [L. Yang, {\it et al}, Phys. Rev. Research {\bf 2}, 012039(R)(2020)] that efficiently uses sampled states. PO mitigates the numerical instabilities during network updates, which is similar to stochastic reconfiguration (SR) methods, but achieves an alternative and simpler implement with lower computational complexity. We investigate the performance of our VMC-PO algorithm for ground-state searching with a 1-dimensional transverse-field Ising model and 2-dimensional Heisenberg antiferromagnet on a square lattice, and demonstrate that the reached ground-state energies are comparable to state-of-the-art results.

cond-mat.dis-nn↗

arXiv2022

Discrete Boltzmann modeling of detonation: based on the Shakhov model

A Discrete Boltzmann Model(DBM) based on the Shakhov model for detonation is proposed. Compared with the DBM based on the Bhatnagar-Gross-Krook (BGK) model, the current model has a flexible Prandtl numbers and consequently can be applied to a much wider range of detonation phenomena. Besides the Hydrodynamic Non-Equilibrium (HNE) behaviors usually investigated by the Navier-Stokes model, the most relevant Thermodynamic Non-Equilibrium (TNE) effects can be probed by the current model. The model is validated by some well-known benchmarks,and some steady and unsteady detonation processes are investigated. As for the von Neumann peak relative to the wave front, it is found that (i) (within the range of numerical experiments) the peak heights of pressure, density and flow velocity increase exponentially with the Prandtl number, the maximum stress increases parabolically with the Prandtl number, and the maximum heat flux decreases exponentially with the Prandtl number; (ii) the peak heights of pressure, density, temperature and flow velocity and the maximum stress within the peak are parabolically increase with the Mach number, the maximum heat flux decreases exponentially with the Mach number.

physics.flu-dyn↗

arXiv2022

Block-Structured Optimization for Subgraph Detection in Interdependent Networks

We propose a generalized framework for block-structured nonconvex optimization, which can be applied to structured subgraph detection in interdependent networks, such as multi-layer networks, temporal networks, networks of networks, and many others. Specifically, we design an effective, efficient, and parallelizable projection algorithm, namely Graph Block-structured Gradient Projection (GBGP), to optimize a general non-linear function subject to graph-structured constraints. We prove that our algorithm: 1) runs in nearly-linear time on the network size; 2) enjoys a theoretical approximation guarantee. Moreover, we demonstrate how our framework can be applied to two very practical applications and conduct comprehensive experiments to show the effectiveness and efficiency of our proposed algorithm.

cs.LG↗

arXiv2022

Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?

Modern deep learning involves training costly, highly overparameterized networks, thus motivating the search for sparser networks that can still be trained to the same accuracy as the full network (i.e. matching). Iterative magnitude pruning (IMP) is a state of the art algorithm that can find such highly sparse matching subnetworks, known as winning tickets. IMP operates by iterative cycles of training, masking smallest magnitude weights, rewinding back to an early training point, and repeating. Despite its simplicity, the underlying principles for when and how IMP finds winning tickets remain elusive. In particular, what useful information does an IMP mask found at the end of training convey to a rewound network near the beginning of training? How does SGD allow the network to extract this information? And why is iterative pruning needed? We develop answers in terms of the geometry of the error landscape. First, we find that$\unicode{x2014}$at higher sparsities$\unicode{x2014}$pairs of pruned networks at successive pruning iterations are connected by a linear path with zero error barrier if and only if they are matching. This indicates that masks found at the end of training convey the identity of an axial subspace that intersects a desired linearly connected mode of a matching sublevel set. Second, we show SGD can exploit this information due to a strong form of robustness: it can return to this mode despite strong perturbations early in training. Third, we show how the flatness of the error landscape at the end of training determines a limit on the fraction of weights that can be pruned at each iteration of IMP. Finally, we show that the role of retraining in IMP is to find a network with new small weights to prune. Overall, these results make progress toward demystifying the existence of winning tickets by revealing the fundamental role of error landscape geometry.

cs.LG↗

arXiv2022

A Comprehensive Radiative Magnetohydrodynamics Simulation of Active Region Scale Flux Emergence from the Convection Zone to the Corona

We present a comprehensive radiative magnetohydrodynamic simulation of the quiet Sun and large solar active regions. The 197 Mm wide simulation domain spans from 18 (10) Mm beneath the photosphere to 113 Mm in the solar corona. Radiative transfer assuming local thermal equilibrium, optically-thin radiative losses, and anisotropic conduction transport provide the necessary realism for synthesizing observables to compare with remote sensing observations of the photosphere and corona. This model self-consistently reproduces observed features of the quiet Sun, emerging and developed active regions, and solar flares up to M class. Here, we report an overview of the first results. The surface magnetoconvection yields an upward Poynting flux that is dissipated in the corona and heats the plasma to over one million K. The quiescent corona also presents ubiquitous propagating waves, jets, and bright points with sizes down to 2 Mm. Magnetic flux bundles emerge into the photosphere and give rise to strong and complex active regions with over $10^{23}$ Mx magnetic flux. The coronal free magnetic energy, which is approximately 18\% of the total magnetic energy, accumulates to approximately $10^{33}$ erg. The coronal magnetic field is clearly non-force-free, as the Lorentz force needs to balance the pressure force and viscous stress as well as drive magnetic field evolution. The emission measure from $\log_{10}T{=}4.5$ to $\log_{10}T{>}7$ provides a comprehensive view of the active region corona, such as coronal loops of various lengths and temperatures, mass circulation by evaporation and condensation, and eruptions from jets to large-scale mass ejections.

astro-ph.SR↗

arXiv2022

Adjacency constraint for efficient hierarchical reinforcement learning

Goal-conditioned Hierarchical Reinforcement Learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is large. Searching in a large goal space poses difficulty for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a $k$-step adjacent region of the current state using an adjacency constraint. We theoretically prove that in a deterministic Markov Decision Process (MDP), the proposed adjacency constraint preserves the optimal hierarchical policy, while in a stochastic MDP the adjacency constraint induces a bounded state-value suboptimality determined by the MDP's transition structure. We further show that this constraint can be practically implemented by training an adjacency network that can discriminate between adjacent and non-adjacent subgoals. Experimental results on discrete and continuous control tasks including challenging simulated robot locomotion and manipulation tasks show that incorporating the adjacency constraint significantly boosts the performance of state-of-the-art goal-conditioned HRL approaches.

cs.LG↗

arXiv2022

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information

Few-shot classification (FSC) requires training models using a few (typically one to five) data points per class. Meta learning has proven to be able to learn a parametrized model for FSC by training on various other classification tasks. In this work, we propose PLATINUM (semi-suPervised modeL Agnostic meTa-learnIng usiNg sUbmodular Mutual information), a novel semi-supervised model agnostic meta-learning framework that uses the submodular mutual information (SMI) functions to boost the performance of FSC. PLATINUM leverages unlabeled data in the inner and outer loop using SMI functions during meta-training and obtains richer meta-learned parameterizations for meta-test. We study the performance of PLATINUM in two scenarios - 1) where the unlabeled data points belong to the same set of classes as the labeled set of a certain episode, and 2) where there exist out-of-distribution classes that do not belong to the labeled set. We evaluate our method on various settings on the miniImageNet, tieredImageNet and Fewshot-CIFAR100 datasets. Our experiments show that PLATINUM outperforms MAML and semi-supervised approaches like pseduo-labeling for semi-supervised FSC, especially for small ratio of labeled examples per class.

cs.LG↗

arXiv2022

Stochastic declustering of earthquakes with the spatiotemporal RETAS model

Epidemic-Type Aftershock Sequence (ETAS) models are point processes that have found prominence in seismological modeling. Its success has led to the development of a number of different versions of the ETAS model. Among these extensions is the RETAS model which has shown potential to improve the modeling capabilities of the ETAS class of models. The RETAS model endows the main-shock arrival process with a renewal process which serves as an alternative to the homogeneous Poisson process. Model fitting is performed using likelihood-based estimation by directly optimizing the exact likelihood. However, inferring the branching structure from the fitted RETAS model remains a challenging task since the declustering algorithm that is currently available for the ETAS model is not directly applicable. This article solves this problem by developing an iterative algorithm to calculate the smoothed main and aftershock probabilities conditional on all available information contained in the catalog. Consequently, an objective estimate of the spatial intensity function can be obtained and an iterative semi-parametric approach is implemented to estimate model parameters with information criteria used for tuning the smoothing parameters. The methods proposed herein are illustrated on simulated data and a New Zealand earthquake catalog.

stat.AP↗

arXiv2022

Framing Algorithmic Recourse for Anomaly Detection

The problem of algorithmic recourse has been explored for supervised machine learning models, to provide more interpretable, transparent and robust outcomes from decision support systems. An unexplored area is that of algorithmic recourse for anomaly detection, specifically for tabular data with only discrete feature values. Here the problem is to present a set of counterfactuals that are deemed normal by the underlying anomaly detection model so that applications can utilize this information for explanation purposes or to recommend countermeasures. We present an approach -- Context preserving Algorithmic Recourse for Anomalies in Tabular data (CARAT), that is effective, scalable, and agnostic to the underlying anomaly detection model. CARAT uses a transformer based encoder-decoder model to explain an anomaly by finding features with low likelihood. Subsequently semantically coherent counterfactuals are generated by modifying the highlighted features, using the overall context of features in the anomalous instance(s). Extensive experiments help demonstrate the efficacy of CARAT.

cs.LG↗

arXiv2022

Radiative Magnetohydrodynamic Simulation of the Confined Eruption of a Magnetic Flux Rope: Magnetic Structure and Plasma Thermodynamics

It is widely believed that magnetic flux ropes are the key structure of solar eruptions; however, their observable counterparts are not clear yet. We study a flare associated with flux rope eruption in a comprehensive radiative magnetohydrodynamic simulation of flare-productive active regions, especially focusing on the thermodynamic properties of the plasma involved in the eruption and their relation to the magnetic flux rope. The pre-existing flux rope, which carries cold and dense plasma, rises quasi-statically before the eruption onsets. During this stage, the flux rope does not show obvious signatures in extreme ultraviolet (EUV) emission. After the flare onset, a thin `current shell' is generated around the erupting flux rope. Moreover, a current sheet is formed under the flux rope, where two groups of magnetic arcades reconnect and create a group of post-flare loops. The plasma within the `current shell', current sheet, and post-flare loops are heated to more than 10 MK. The post-flare loops give rise to abundant soft X-ray emission. Meanwhile a majority of the plasma hosted in the flux rope is heated to around 1 MK, and the main body of the flux rope is manifested as a bright arch in cooler EUV passbands such as AIA 171 Å~channel.

astro-ph.SR↗

arXiv2022

Calibrated Nonparametric Scan Statistics for Anomalous Pattern Detection in Graphs

We propose a new approach, the calibrated nonparametric scan statistic (CNSS), for more accurate detection of anomalous patterns in large-scale, real-world graphs. Scan statistics identify connected subgraphs that are interesting or unexpected through maximization of a likelihood ratio statistic; in particular, nonparametric scan statistics (NPSSs) identify subgraphs with a higher than expected proportion of individually significant nodes. However, we show that recently proposed NPSS methods are miscalibrated, failing to account for the maximization of the statistic over the multiplicity of subgraphs. This results in both reduced detection power for subtle signals, and low precision of the detected subgraph even for stronger signals. Thus we develop a new statistical approach to recalibrate NPSSs, correctly adjusting for multiple hypothesis testing and taking the underlying graph structure into account. While the recalibration, based on randomization testing, is computationally expensive, we propose both an efficient (approximate) algorithm and new, closed-form lower bounds (on the expected maximum proportion of significant nodes for subgraphs of a given size, under the null hypothesis of no anomalous patterns). These advances, along with the integration of recent core-tree decomposition methods, enable CNSS to scale to large real-world graphs, with substantial improvement in the accuracy of detected subgraphs. Extensive experiments on both semi-synthetic and real-world datasets are demonstrated to validate the effectiveness of our proposed methods, in comparison with state-of-the-art counterparts.

stat.ME↗

arXiv2022

A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning

An in-depth understanding of uncertainty is the first step to making effective decisions under uncertainty. Deep/machine learning (ML/DL) has been hugely leveraged to solve complex problems involved with processing high-dimensional data. However, reasoning and quantifying different types of uncertainties to achieve effective decision-making have been much less explored in ML/DL than in other Artificial Intelligence (AI) domains. In particular, belief/evidence theories have been studied in KRR since the 1960s to reason and measure uncertainties to enhance decision-making effectiveness. We found that only a few studies have leveraged the mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty. In this survey paper, we discuss several popular belief theories and their core ideas dealing with uncertainty causes and types and quantifying them, along with the discussions of their applicability in ML/DL. In addition, we discuss three main approaches that leverage belief theories in Deep Neural Networks (DNNs), including Evidential DNNs, Fuzzy DNNs, and Rough DNNs, in terms of their uncertainty causes, types, and quantification methods along with their applicability in diverse problem domains. Based on our in-depth survey, we discuss insights, lessons learned, limitations of the current state-of-the-art bridging belief theories and ML/DL, and finally, future research directions.

cs.AI↗