arXiv subjects

Lei Feng

Publications and source records attributed to Lei Feng.

At least 127 records · Page 7Linked to original sources

arXiv2024

SKA sensitivity for possible radio emission from dark matter in Omega Centauri

Omega Centauri, the largest known globular cluster in the Milky Way, is believed to be the remains of a dwarf galaxy's core. Giving its potential abundance of dark matter (DM), it is an attractive target for investigating the nature of this elusive substance in our local environment. Our study demonstrates that by observing Omega Centauri with the SKA for 1000 hours, we can detect synchrotron radio or Inverse Compton (IC) emissions from the DM annihilation products. It enables us to constrain the cross-section of DM annihilation down to $\sim {\rm 10^{-30}~cm^3~s^{-1}}$ for DM mass from several $\rm{GeV}$ to $\rm{100~GeV}$, which is much stronger compared with other observations. Additionally, we explore the axion, another well-motivated DM candidate, and provide stimulated decay calculations. It turns out that the sensitivity can reach $g_{\rm{aγγ}} \sim 10^{-10} ~\rm{GeV^{-1}}$ for $2\times 10^{-7} ~\rm{eV} < m_a < 2\times 10^{-4} ~\rm{eV}$.

astro-ph.HE↗

arXiv2024

Constraining primordial black holes as dark matter using AMS-02 data

Primordial black holes (PBHs) are the plausible candidates for the cosmological dark matter. Theoretically, PBHs with masses $M_{\rm PBH}$ in the range of $4\times10^{14}\sim 10^{17}\,{\rm g}$ can emit sub-GeV electrons and positrons through Hawking radiation. Some of these particles could undergo diffusive reacceleration during propagation in the Milky Way, potentially reaching energies up to the GeV level observed by AMS-02. In this work, we utilize AMS-02 data to constrain the PBH abundance $f_{\rm PBH}$ by employing the reacceleration mechanism. Under the assumption of a monochromatic PBH mass distribution, our findings reveal that the limit is stricter than that derived from Voyager 1 data. This difference is particularly pronounced when $M_{\rm PBH}\lesssim10^{15}\,{\rm g}$, exceeding an order of magnitude. The constraints are even more robust in a more realistic scenario involving a log-normal mass distribution of PBHs. Moreover, we explore the impact of varying propagation parameters and solar modulation potential within reasonable ranges, and find that such variations have minimal effects on the final results.

astro-ph.HE↗

arXiv2024

MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading

High-frequency trading (HFT) that executes algorithmic trading in short time scales, has recently occupied the majority of cryptocurrency market. Besides traditional quantitative trading methods, reinforcement learning (RL) has become another appealing approach for HFT due to its terrific ability of handling high-dimensional financial data and solving sophisticated sequential decision-making problems, \emph{e.g.,} hierarchical reinforcement learning (HRL) has shown its promising performance on second-level HFT by training a router to select only one sub-agent from the agent pool to execute the current transaction. However, existing RL methods for HFT still have some defects: 1) standard RL-based trading agents suffer from the overfitting issue, preventing them from making effective policy adjustments based on financial context; 2) due to the rapid changes in market conditions, investment decisions made by an individual agent are usually one-sided and highly biased, which might lead to significant loss in extreme markets. To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, \emph{a.k.a.} MacroHFT, which consists of two training phases: 1) we first train multiple types of sub-agents with the market data decomposed according to various financial indicators, specifically market trend and volatility, where each agent owns a conditional adapter to adjust its trading policy according to market conditions; 2) then we train a hyper-agent to mix the decisions from these sub-agents and output a consistently profitable meta-policy to handle rapid market fluctuations, equipped with a memory mechanism to enhance the capability of decision-making. Extensive experiments on various cryptocurrency markets demonstrate that MacroHFT can achieve state-of-the-art performance on minute-level trading tasks.

cs.LG↗

arXiv2024

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Machine learning models are susceptible to membership inference attacks (MIAs), which aim to infer whether a sample is in the training set. Existing work utilizes gradient ascent to enlarge the loss variance of training data, alleviating the privacy risk. However, optimizing toward a reverse direction may cause the model parameters to oscillate near local minima, leading to instability and suboptimal performance. In this work, we propose a novel method -- Convex-Concave Loss, which enables a high variance of training loss distribution by gradient descent. Our method is motivated by the theoretical analysis that convex losses tend to decrease the loss variance during training. Thus, our key idea behind CCL is to reduce the convexity of loss functions with a concave term. Trained with CCL, neural networks produce losses with high variance for training data, reinforcing the defense against MIAs. Extensive experiments demonstrate the superiority of CCL, achieving state-of-the-art balance in the privacy-utility trade-off.

cs.LG↗

arXiv2024

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs exhibit low zero-shot performance in downstream tasks. To alleviate this issue, we propose a Candidate Pseudolabel Learning method, termed CPL, to fine-tune VLMs with suitable candidate pseudolabels of unlabeled data in downstream tasks. The core of our method lies in the generation strategy of candidate pseudolabels, which progressively generates refined candidate pseudolabels by both intra- and inter-instance label selection, based on a confidence score matrix for all unlabeled data. This strategy can result in better performance in true label inclusion and class-balanced instance selection. In this way, we can directly apply existing loss functions to learn with generated candidate psueudolabels. Extensive experiments on nine benchmark datasets with three learning paradigms demonstrate the effectiveness of our method. Our code can be found at https://github.com/vanillaer/CPL-ICML2024.

cs.LG↗

arXiv2024

Revolutionizing Wireless Networks with Self-Supervised Learning: A Pathway to Intelligent Communications

With the rapid proliferation of mobile devices and data, next-generation wireless communication systems face stringent requirements for ultra-low latency, ultra-high reliability, and massive connectivity. Traditional AI-driven wireless network designs, while promising, often suffer from limitations such as dependency on labeled data and poor generalization. To address these challenges, we present an integration of self-supervised learning (SSL) into wireless networks. SSL leverages large volumes of unlabeled data to train models, enhancing scalability, adaptability, and generalization. This paper offers a comprehensive overview of SSL, categorizing its application scenarios in wireless network optimization and presenting a case study on its impact on semantic communication. Our findings highlight the potentials of SSL to significantly improve wireless network performance without extensive labeled data, paving the way for more intelligent and efficient communication systems.

eess.SP↗

arXiv2024

Optimal Gait Design for a Soft Quadruped Robot via Multi-fidelity Bayesian Optimization

This study focuses on the locomotion capability improvement in a tendon-driven soft quadruped robot through an online adaptive learning approach. Leveraging the inverse kinematics model of the soft quadruped robot, we employ a central pattern generator to design a parametric gait pattern, and use Bayesian optimization (BO) to find the optimal parameters. Further, to address the challenges of modeling discrepancies, we implement a multi-fidelity BO approach, combining data from both simulation and physical experiments throughout training and optimization. This strategy enables the adaptive refinement of the gait pattern and ensures a smooth transition from simulation to real-world deployment for the controller. Moreover, we integrate a computational task off-loading architecture by edge computing, which reduces the onboard computational and memory overhead, to improve real-time control performance and facilitate an effective online learning process. The proposed approach successfully achieves optimal walking gait design for physical deployment with high efficiency, effectively addressing challenges related to the reality gap in soft robotics.

cs.RO↗

arXiv2024

Optimal Gait Control for a Tendon-driven Soft Quadruped Robot by Model-based Reinforcement Learning

This study presents an innovative approach to optimal gait control for a soft quadruped robot enabled by four Compressible Tendon-driven Soft Actuators (CTSAs). Improving our previous studies of using model-free reinforcement learning for gait control, we employ model-based reinforcement learning (MBRL) to further enhance the performance of the gait controller. Compared to rigid robots, the proposed soft quadruped robot has better safety, less weight, and a simpler mechanism for fabrication and control. However, the primary challenge lies in developing sophisticated control algorithms to attain optimal gait control for fast and stable locomotion. The research employs a multi-stage methodology, including state space restriction, data-driven model training, and reinforcement learning algorithm development. Compared to benchmark methods, the proposed MBRL algorithm, combined with post-training, significantly improves the efficiency and performance of gait control policies. The developed policy is both robust and adaptable to the robot's deformable morphology. The study concludes by highlighting the practical applicability of these findings in real-world scenarios.

cs.RO↗

arXiv2024

A General Framework for Learning from Weak Supervision

Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This paper introduces a general framework for learning from weak supervision (GLWS) with a novel algorithm. Central to GLWS is an Expectation-Maximization (EM) formulation, adeptly accommodating various weak supervision sources, including instance partial labels, aggregate statistics, pairwise observations, and unlabeled data. We further present an advanced algorithm that significantly simplifies the EM computational demands using a Non-deterministic Finite Automaton (NFA) along with a forward-backward algorithm, which effectively reduces time complexity from quadratic or factorial often required in existing solutions to linear scale. The problem of learning from arbitrary weak supervision is therefore converted to the NFA modeling of them. GLWS not only enhances the scalability of machine learning models but also demonstrates superior performance and versatility across 11 weak supervision scenarios. We hope our work paves the way for further advancements and practical deployment in this field.

cs.LG↗

arXiv2024

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot performance. However, in this paper, we empirically find that the finer descriptions tend to align more effectively with local areas of the query image rather than the whole image, and then we theoretically validate this finding. Thus, we present a method called weighted visual-text cross alignment (WCA). This method begins with a localized visual prompting technique, designed to identify local visual areas within the query image. The local visual areas are then cross-aligned with the finer descriptions by creating a similarity matrix using the pre-trained VLM. To determine how well a query image aligns with each category, we develop a score function based on the weighted similarities in this matrix. Extensive experiments demonstrate that our method significantly improves zero-shot performance across various datasets, achieving results that are even comparable to few-shot learning methods.

cs.CV↗

arXiv2024

Sample-specific Masks for Visual Reprogramming-based Prompting

Visual reprogramming (VR) is a prompting technique that aims to re-purpose a pre-trained model (e.g., a classifier on ImageNet) to target tasks (e.g., medical data prediction) by learning a small-scale pattern added into input images instead of tuning considerable parameters within the model. The location of the pattern within input samples is usually determined by a pre-defined mask shared across all samples. In this paper, we show that the shared mask potentially limits VR's generalization and increases its approximation error due to the lack of sample-level adaptation. Motivated by this finding, we design a new framework for VR called sample-specific multi-channel masks (SMM). Specifically, SMM employs a lightweight ConvNet and patch-wise interpolation to generate sample-specific three-channel masks instead of a shared and pre-defined mask. Since we generate different masks for individual samples, SMM is theoretically shown to reduce approximation error for the target tasks compared with existing state-of-the-art VR methods. We also empirically demonstrate its performance gain on both ResNet and ViT. The success of SMM further highlights the broader applicability of VR in leveraging the latent knowledge of pre-trained models for various target tasks. Our code is available at https://github.com/tmlr-group/SMM.

cs.LG↗

arXiv2024

Improving Generalization of Deep Neural Networks by Optimum Shifting

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method called \emph{optimum shifting}, which changes the parameters of a neural network from a sharp minimum to a flatter one while maintaining the same training loss value. Our method is based on the observation that when the input and output of a neural network are fixed, the matrix multiplications within the network can be treated as systems of under-determined linear equations, enabling adjustment of parameters in the solution space, which can be simply accomplished by solving a constrained optimization problem. Furthermore, we introduce a practical stochastic optimum shifting technique utilizing the Neural Collapse theory to reduce computational costs and provide more degrees of freedom for optimum shifting. Extensive experiments (including classification and detection) with various deep neural network architectures on benchmark datasets demonstrate the effectiveness of our method.

cs.LG↗

arXiv2024

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning

Partial-label learning (PLL) is an important weakly supervised learning problem, which allows each training example to have a candidate label set instead of a single ground-truth label. Identification-based methods have been widely explored to tackle label ambiguity issues in PLL, which regard the true label as a latent variable to be identified. However, identifying the true labels accurately and completely remains challenging, causing noise in pseudo labels during model training. In this paper, we propose a new method called CroSel, which leverages historical predictions from the model to identify true labels for most training examples. First, we introduce a cross selection strategy, which enables two deep models to select true labels of partially labeled data for each other. Besides, we propose a novel consistency regularization term called co-mix to avoid sample waste and tiny noise caused by false selection. In this way, CroSel can pick out the true labels of most examples with high precision. Extensive experiments demonstrate the superiority of CroSel, which consistently outperforms previous state-of-the-art methods on benchmark datasets. Additionally, our method achieves over 90\% accuracy and quantity for selecting true labels on CIFAR-type datasets under various settings.

cs.LG↗

arXiv2024

Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios

Multi-view clustering (MVC) aims at exploring category structures among multi-view data in self-supervised manners. Multiple views provide more information than single views and thus existing MVC methods can achieve satisfactory performance. However, their performance might seriously degenerate when the views are noisy in practical multi-view scenarios. In this paper, we formally investigate the drawback of noisy views and then propose a theoretically grounded deep MVC method (namely MVCAN) to address this issue. Specifically, we propose a novel MVC objective that enables un-shared parameters and inconsistent clustering predictions across multiple views to reduce the side effects of noisy views. Furthermore, a two-level multi-view iterative optimization is designed to generate robust learning targets for refining individual views' representation learning. Theoretical analysis reveals that MVCAN works by achieving the multi-view consistency, complementarity, and noise robustness. Finally, experiments on extensive public datasets demonstrate that MVCAN outperforms state-of-the-art methods and is robust against the existence of noisy views.

cs.LG↗

arXiv2024

Black holes as the source of dark energy: a stringent test with high-redshift JWST AGNs

Studies have proposed that there is evidence for cosmological coupling of black holes (BHs) with an index of $k\approx 3$; hence, BHs serve as the astrophysical source of dark energy. However, the data sample is limited for the redshifts of $\leq 2.5$. In recent years, the James Webb Space Telescope (JWST) has detected many high-redshift active galactic nuclei (AGNs) and quasars. Among the JWST NIRSpec-/NIRCam-resolved AGNs, three are determined to be in early-type host galaxies with a redshift of $z\sim 4.5--7$. However, their $M_{\star}$ and $M_{\rm BH}$ are in tension with the predicted cosmological coupling of black holes with $k = 3$ at a confidence level of $\sim 2σ$, which challenges the hypothesis that BHs serve as the origin of dark energy. Future work on high-redshift AGNs using the JWST will further assess such a hypothesis by identifying more early-type host galaxies in the higher mass range.

astro-ph.CO↗

arXiv2023

keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM

Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, especially for question answering. However, in the face of problems beyond the scope of knowledge, these LLMs tend to talk nonsense with a straight face, where the potential solution could be incorporating an Information Retrieval (IR) module and generating response based on these retrieved knowledge. In this paper, we present a novel framework to assist LLMs, such as ChatGPT, to retrieve question-related structured information on the knowledge graph, and demonstrate that Knowledge-based question answering (Keqing) could be a nature Chain-of-Thought (CoT) mentor to guide the LLM to sequentially find the answer entities of a complex question through interpretable logical chains. Specifically, the workflow of Keqing will execute decomposing a complex question according to predefined templates, retrieving candidate entities on knowledge graph, reasoning answers of sub-questions, and finally generating response with reasoning paths, which greatly improves the reliability of LLM's response. The experimental results on KBQA datasets show that Keqing can achieve competitive performance and illustrate the logic of answering each question.

cs.CL↗

arXiv2023

Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examples

Partial-label learning (PLL) relies on a key assumption that the true label of each training example must be in the candidate label set. This restrictive assumption may be violated in complex real-world scenarios, and thus the true label of some collected examples could be unexpectedly outside the assigned candidate label set. In this paper, we term the examples whose true label is outside the candidate label set OOC (out-of-candidate) examples, and pioneer a new PLL study to learn with OOC examples. We consider two types of OOC examples in reality, i.e., the closed-set/open-set OOC examples whose true label is inside/outside the known label space. To solve this new PLL problem, we first calculate the wooden cross-entropy loss from candidate and non-candidate labels respectively, and dynamically differentiate the two types of OOC examples based on specially designed criteria. Then, for closed-set OOC examples, we conduct reversed label disambiguation in the non-candidate label set; for open-set OOC examples, we leverage them for training by utilizing an effective regularization strategy that dynamically assigns random candidate labels from the candidate label set. In this way, the two types of OOC examples can be differentiated and further leveraged for model training. Extensive experiments demonstrate that our proposed method outperforms state-of-the-art PLL methods.

cs.LG↗

arXiv2023

Gluon condensation: from nucleon to Galactic center

The Galactic Center Excess (GCE), one of the most remarkable discoveries by Fermi-LAT, has prompted extensive exploration over the past decade, often attributed to dark matter or millisecond pulsars. This work proposes a novel interpretation on the origin of the GCE, focusing on the observed spectral shape. Protons are accelerated at the Galactic center and collide with the neutron cluster on the surface of the non-rotating neutron stars. Due to the gluon condensation in nucleons, these collisions produce a large number of mesons, which have reached to the saturation state and subsequently generate the broken power law in the gamma ray spectra. We explained the spectral shape of GCE using the gluon condensation and an assumption of existing the non-rotating neutron stars at the Galactic center. This example of the gluon condensation mechanism not only expands the applications of the hadronic scenario in the cosmic gamma ray spectra but also provides a new evidence of the gluon condensation.

astro-ph.HE↗