arXiv subjects

Lei Huang

Publications and source records attributed to Lei Huang.

At least 145 records · Page 8Linked to original sources

arXiv2024

The white-light superflares from cool stars in GWAC triggers

M-type stars are the ones that flare most frequently, but how big their maximum flare energy can reach is still unknown. We present 163 flares from 162 individual M2 through L1-type stars that triggered the GWAC, with flare energies ranging from $10^{32.2}$ to $10^{36.4}$ erg . The flare amplitudes range from $\triangle G = 0.84$ to $\sim 10$ mag. Flare energy increases with stellar surface temperature ($T_{\rm eff}$) but both $\triangle G$ and equivalent duration $\log_{10}(ED)$ seem to be independent of $T_{\rm eff}$. Combining periods detected from light curves of TESS and K2, spectra from LAMOST, SDSS and the 2.16 m Telescope, and the Gaia DR3 data, we found that these GWAC flare stars are young. For the stars that have spectra, we found that these stars are in or very near to the saturation region, and $\log_{10}(L_{\rm Hα}/L_{\rm bol})$ is lower for M7-L1 stars than for M2-M6 stars. We also studied the relation between GWAC flare bolometric energy $E_{\rm bol}$ and stellar hemispherical area $S$, and found that $\log_{10}E_{\rm bol}$ (in erg) increases with increasing $S$ (in cm$^2$), and the maximum flare energy $\log_{10}E_{\rm bol, max} \geqslant \log_{10}S + 14.25$. For M7-L1 stars, there seem to be other factors limiting their maximum flare energies in addition to stellar hemispherical area.

astro-ph.SR↗

arXiv2024

Finite convergence of Moment-SOS relaxations with non-real radical ideals

We consider the linear conic optimization problem with the cone of nonnegative polynomials. Its dual optimization problem is the generalized moment problem. Moment-SOS relaxations are powerful for solving them. This paper studies finite convergence of the Moment-SOS hierarchy when the constraining set is defined by equations whose ideal may not be real radical. Under the archimedeanness, we show that the Moment-SOS hierarchy has finite convergence if some classical optimality conditions hold at every minimizer of the optimal nonnegative polynomial for the linear conic optimization problem. When the archimedeanness fails (this is the case for unbounded sets), we propose a homogenized Moment-SOS hierarchy and prove its finite convergence under similar assumptions. Furthermore, we also prove the finite convergence of the Moment-SOS hierarchy with denominators. In particular, this paper resolves a conjecture posed in the earlier work.

math.OC↗

arXiv2024

Intelligent Reflecting Surface-Assisted NLOS Sensing With OFDM Signals

This work addresses the problem of intelligent reflecting surface (IRS) assisted target sensing in a non-line-of-sight (NLOS) scenario, where an IRS is employed to facilitate the radar/access point (AP) to sense the targets when the line-of-sight (LOS) path between the AP and the target is blocked by obstacles. To sense the targets, the AP transmits a train of uniformly-spaced orthogonal frequency division multiplexing (OFDM) pulses, and then perceives the targets based on the echoes from the AP-IRS-targets-IRS-AP channel. To resolve an inherent scaling ambiguity associated with IRS-assisted NLOS sensing, we propose a two-phase sensing scheme by exploiting the diversity in the illumination pattern of the IRS across two different phases. Specifically, the received echo signals from the two phases are formulated as third-order tensors. Then a canonical polyadic (CP) decomposition-based method is developed to estimate each target's parameters including the direction of arrival (DOA), Doppler shift and time delay. Our analysis reveals that the proposed method achieves reliable NLOS sensing using a modest quantity of pulse/subcarrier resources. Simulation results are provided to show the effectiveness of the proposed method under the challenging scenario where the degrees-of-freedom provided by the AP-IRS channel are not enough for resolving the scaling ambiguity.

eess.SP↗

arXiv2024

ADSNet: Cross-Domain LTV Prediction with an Adaptive Siamese Network in Advertising

Advertising platforms have evolved in estimating Lifetime Value (LTV) to better align with advertisers' true performance metric. However, the sparsity of real-world LTV data presents a significant challenge to LTV predictive model(i.e., pLTV), severely limiting the their capabilities. Therefore, we propose to utilize external data, in addition to the internal data of advertising platform, to expand the size of purchase samples and enhance the LTV prediction model of the advertising platform. To tackle the issue of data distribution shift between internal and external platforms, we introduce an Adaptive Difference Siamese Network (ADSNet), which employs cross-domain transfer learning to prevent negative transfer. Specifically, ADSNet is designed to learn information that is beneficial to the target domain. We introduce a gain evaluation strategy to calculate information gain, aiding the model in learning helpful information for the target domain and providing the ability to reject noisy samples, thus avoiding negative transfer. Additionally, we also design a Domain Adaptation Module as a bridge to connect different domains, reduce the distribution distance between them, and enhance the consistency of representation space distribution. We conduct extensive offline experiments and online A/B tests on a real advertising platform. Our proposed ADSNet method outperforms other methods, improving GINI by 2$\%$. The ablation study highlights the importance of the gain evaluation strategy in negative gain sample rejection and improving model performance. Additionally, ADSNet significantly improves long-tail prediction. The online A/B tests confirm ADSNet's efficacy, increasing online LTV by 3.47$\%$ and GMV by 3.89$\%$.

cs.IR↗

arXiv2024

On the Nonlinearity of Layer Normalization

Layer normalization (LN) is a ubiquitous technique in deep learning but our theoretical understanding to it remains elusive. This paper investigates a new theoretical direction for LN, regarding to its nonlinearity and representation capacity. We investigate the representation capacity of a network with layerwise composition of linear and LN transformations, referred to as LN-Net. We theoretically show that, given $m$ samples with any label assignment, an LN-Net with only 3 neurons in each layer and $O(m)$ LN layers can correctly classify them. We further show the lower bound of the VC dimension of an LN-Net. The nonlinearity of LN can be amplified by group partition, which is also theoretically demonstrated with mild assumption and empirically supported by our experiments. Based on our analyses, we consider to design neural architecture by exploiting and amplifying the nonlinearity of LN, and the effectiveness is supported by our experiments.

cs.LG↗

arXiv2024

Efficient Data Distribution Estimation for Accelerated Federated Learning

Federated Learning(FL) is a privacy-preserving machine learning paradigm where a global model is trained in-situ across a large number of distributed edge devices. These systems are often comprised of millions of user devices and only a subset of available devices can be used for training in each epoch. Designing a device selection strategy is challenging, given that devices are highly heterogeneous in both their system resources and training data. This heterogeneity makes device selection very crucial for timely model convergence and sufficient model accuracy. To tackle the FL client heterogeneity problem, various client selection algorithms have been developed, showing promising performance improvement in terms of model coverage and accuracy. In this work, we study the overhead of client selection algorithms in a large scale FL environment. Then we propose an efficient data distribution summary calculation algorithm to reduce the overhead in a real-world large scale FL environment. The evaluation shows that our proposed solution could achieve up to 30x reduction in data summary time, and up to 360x reduction in clustering time.

cs.DC↗

arXiv2024

Probing orbits of stellar mass objects deep in galactic nuclei with quasi-periodic eruptions

Quasi-periodic eruptions (QPEs) are intense repeating soft X-ray bursts with recurrence times about a few to ten hours from nearby galactic nuclei. The origin of QPEs is still unclear. In this work, we investigated the extreme mass ratio inspiral (EMRI) + accretion disk model, where the disk is formed from a previous tidal disruption event (TDE). In this EMRI+TDE disk model, the QPEs are the result of collisions between a TDE disk and a stellar mass object (a stellar mass black hole or a main sequence star) orbiting around a supermassive black hole (SMBH) in galactic nuclei. If this interpretation is correct, QPEs will be invaluable in probing the orbits of stellar mass objects in the vicinity of SMBHs, and further inferring the formation of EMRIs which are one of the primary targets of spaceborne gravitational wave missions. Taking GSN 069 as an example, we find the EMRI wherein is of low eccentricity ($e<0.1$ at 3-$σ$ confidence level) and semi-major axis about $O(10^2)$ gravitational radii of the central SMBH, which is consistent with the prediction of the wet EMRI formation channel, while incompatible with alternatives.

astro-ph.HE↗

arXiv2024

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models

We present TinyLLaVA Factory, an open-source modular codebase for small-scale large multimodal models (LMMs) with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of training results. Following the design philosophy of the factory pattern in software engineering, TinyLLaVA Factory modularizes the entire system into interchangeable components, with each component integrating a suite of cutting-edge models and methods, meanwhile leaving room for extensions to more features. In addition to allowing users to customize their own LMMs, TinyLLaVA Factory provides popular training recipes to let users pretrain and finetune their models with less coding effort. Empirical experiments validate the effectiveness of our codebase. The goal of TinyLLaVA Factory is to assist researchers and practitioners in exploring the wide landscape of designing and training small-scale LMMs with affordable computational resources.

cs.LG↗

arXiv2024

Unsupervised Learning for Joint Beamforming Design in RIS-aided ISAC Systems

It is critical to design efficient beamforming in reconfigurable intelligent surface (RIS)-aided integrated sensing and communication (ISAC) systems for enhancing spectrum utilization. However, conventional methods often have limitations, either incurring high computational complexity due to iterative algorithms or sacrificing performance when using heuristic methods. To achieve both low complexity and high spectrum efficiency, an unsupervised learning-based beamforming design is proposed in this work. We tailor image-shaped channel samples and develop an ISAC beamforming neural network (IBF-Net) model for beamforming. By leveraging unsupervised learning, the loss function incorporates key performance metrics like sensing and communication channel correlation and sensing channel gain, eliminating the need of labeling. Simulations show that the proposed method achieves competitive performance compared to benchmarks while significantly reduces computational complexity.

eess.SP↗

arXiv2024

Moment-SOS relaxations for moment and tensor recovery problems

This paper studies moment and tensor recovery problems whose decomposing vectors are contained in some given semialgebraic sets. We propose Moment-SOS relaxations with generic objectives for recovering moments and tensors, whose decomposition lengths are expected to be low. This kind of problems have broad applications in various tensor decomposition questions. Numerical experiments are provided to demonstrate the efficiency of this approach.

math.OC↗

arXiv2024

One-Bit Target Detection in Collocated MIMO Radar with Colored Background Noise

One-bit sampling has emerged as a promising technique in multiple-input multiple-output (MIMO) radar systems due to its ability to significantly reduce data volume and processing requirements. Nevertheless, current detection methods have not adequately addressed the impact of colored noise, which is frequently encountered in real scenarios. In this paper, we present a novel detection method that accounts for colored noise in MIMO radar systems. Specifically, we derive Rao's test by computing the derivative of the likelihood function with respect to the target reflectivity parameter and the Fisher information matrix, resulting in a detector that takes the form of a weighted matched filter. To ensure the constant false alarm rate (CFAR) property, we also consider noise covariance uncertainty and examine its effect on the probability of false alarm. The detection probability is also studied analytically. Simulation results demonstrate that the proposed detector provides considerable performance gains in the presence of colored noise.

eess.SP↗

arXiv2024

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning

In the context of online education, designing an automatic solver for geometric problems has been considered a crucial step towards general math Artificial Intelligence (AI), empowered by natural language understanding and traditional logical inference. In most instances, problems are addressed by adding auxiliary components such as lines or points. However, adding auxiliary components automatically is challenging due to the complexity in selecting suitable auxiliary components especially when pivotal decisions have to be made. The state-of-the-art performance has been achieved by exhausting all possible strategies from the category library to identify the one with the maximum likelihood. However, an extensive strategy search have to be applied to trade accuracy for ef-ficiency. To add auxiliary components automatically and efficiently, we present deep reinforcement learning framework based on the language model, such as BERT. We firstly apply the graph attention mechanism to reduce the strategy searching space, called AttnStrategy, which only focus on the conclusion-related components. Meanwhile, a novel algorithm, named Automatically Adding Auxiliary Components using Reinforcement Learning framework (A3C-RL), is proposed by forcing an agent to select top strategies, which incorporates the AttnStrategy and BERT as the memory components. Results from extensive experiments show that the proposed A3C-RL algorithm can substantially enhance the average precision by 32.7% compared to the traditional MCTS. In addition, the A3C-RL algorithm outperforms humans on the geometric questions from the annual University Entrance Mathematical Examination of China.

cs.CY↗

arXiv2024

Robust Synthetic-to-Real Transfer for Stereo Matching

With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in real-world scenarios, during which the domain generalization ability can be seriously degraded. In this paper, we explore fine-tuning stereo matching networks without compromising their robustness to unseen domains. Our motivation stems from comparing Ground Truth (GT) versus Pseudo Label (PL) for fine-tuning: GT degrades, but PL preserves the domain generalization ability. Empirically, we find the difference between GT and PL implies valuable information that can regularize networks during fine-tuning. We also propose a framework to utilize this difference for fine-tuning, consisting of a frozen Teacher, an exponential moving average (EMA) Teacher, and a Student network. The core idea is to utilize the EMA Teacher to measure what the Student has learned and dynamically improve GT and PL for fine-tuning. We integrate our framework with state-of-the-art networks and evaluate its effectiveness on several real-world datasets. Extensive experiments show that our method effectively preserves the domain generalization ability during fine-tuning.

cs.CV↗

arXiv2024

Determining the Number of Common Functional Factors with Twice Cross-Validation

The semiparametric factor model serves as a vital tool to describe the dependence patterns in the data. It recognizes that the common features observed in the data are actually explained by functions of specific exogenous variables.Unlike traditional factor models, where the focus is on selecting the number of factors, our objective here is to identify the appropriate number of common functions, a crucial parameter in this model. In this paper, we develop a novel data-driven method to determine the number of functional factors using cross validation (CV). Our proposed method employs a two-step CV process that ensures the orthogonality of functional factors, which we refer to as Functional Twice Cross-Validation (FTCV). Extensive simulations demonstrate that FTCV accurately selects the number of common functions and outperforms existing methods in most cases.Furthermore, by specifying market volatility as the exogenous force, we provide real data examples that illustrate the interpretability of selected common functions in characterizing the influence on U.S. Treasury Yields and the cross correlations between Dow30 returns.

stat.ME↗

arXiv2024

TinyLLaVA: A Framework of Small-scale Large Multimodal Models

We present the TinyLLaVA framework that provides a unified perspective in designing and analyzing the small-scale Large Multimodal Models (LMMs). We empirically study the effects of different vision encoders, connection modules, language models, training data and training recipes. Our extensive experiments showed that better quality of data combined with better training recipes, smaller LMMs can consistently achieve on-par performances compared to bigger LMMs. Under our framework, we train a family of small-scale LMMs. Our best model, TinyLLaVA-3.1B, achieves better overall performance against existing 7B models such as LLaVA-1.5 and Qwen-VL. We hope our findings can serve as baselines for future research in terms of data scaling, training setups and model selections. Our model weights and codes will be made public.

cs.LG↗

arXiv2024

Sparse Polynomial Optimization with Unbounded Sets

This paper considers sparse polynomial optimization with unbounded sets. When the problem possesses correlative sparsity, we propose a sparse homogenized Moment-SOS hierarchy with perturbations to solve it. The new hierarchy introduces one extra auxiliary variable for each variable clique according to the correlative sparsity pattern. Under the running intersection property, we prove that this hierarchy has asymptotic convergence. Furthermore, we provide two alternative sparse hierarchies to remove perturbations while preserving asymptotic convergence. As byproducts, new Positivstellensätze are obtained for sparse positive polynomials on unbounded sets. Extensive numerical experiments demonstrate the power of our approach in solving sparse polynomial optimization problems on unbounded sets with up to thousands of variables. Finally, we apply our approach to tackle two trajectory optimization problems (block-moving with minimum work and optimal control of Van der Pol).

math.OC↗

arXiv2024

Hyperbolic photonic topological insulators

Topological photonics provides a new degree of freedom to robustly control electromagnetic fields. To date, most of established topological states in photonics have been employed in Euclidean space. Motivated by unique properties of hyperbolic lattices, which are regular tessellations in non-Euclidean space with a constant negative curvature, the boundarydominated hyperbolic topological states have been proposed. However, limited by highly crowded boundary resonators and complicated site couplings, the hyperbolic topological insulator has only been experimentally constructed in electric circuits. How to achieve hyperbolic photonic topological insulators is still an open question. Here, we report the experimental realization of hyperbolic photonic topological insulators using coupled ring resonators on silicon chips. Boundary-dominated one-way edge states with pseudospindependent propagation directions have been observed. Furthermore, the robustness of edge states in hyperbolic photonic topological insulators is also verified. Our findings have potential applications in the field of designing high-efficient topological photonic devices with enhanced boundary responses.

physics.optics↗

arXiv2024

Modulate Your Spectrum in Self-Supervised Learning

Whitening loss offers a theoretical guarantee against feature collapse in self-supervised learning (SSL) with joint embedding architectures. Typically, it involves a hard whitening approach, transforming the embedding and applying loss to the whitened output. In this work, we introduce Spectral Transformation (ST), a framework to modulate the spectrum of embedding and to seek for functions beyond whitening that can avoid dimensional collapse. We show that whitening is a special instance of ST by definition, and our empirical investigations unveil other ST instances capable of preventing collapse. Additionally, we propose a novel ST instance named IterNorm with trace loss (INTL). Theoretical analysis confirms INTL's efficacy in preventing collapse and modulating the spectrum of embedding toward equal-eigenvalues during optimization. Our experiments on ImageNet classification and COCO object detection demonstrate INTL's potential in learning superior representations. The code is available at https://github.com/winci-ai/INTL.

cs.LG↗