arXiv subjects

Zhe Qu

Publications and source records attributed to Zhe Qu.

At least 37 records · Page 2Linked to original sources

arXiv2024

Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations

STOchastic Recursive Momentum (STORM)-based algorithms have been widely developed to solve one to $K$-level ($K \geq 3$) stochastic optimization problems. Specifically, they use estimators to mitigate the biased gradient issue and achieve near-optimal convergence results. However, there is relatively little work on understanding their generalization performance, particularly evident during the transition from one to $K$-level optimization contexts. This paper provides a comprehensive generalization analysis of three representative STORM-based algorithms: STORM, COVER, and SVMR, for one, two, and $K$-level stochastic optimizations under both convex and strongly convex settings based on algorithmic stability. Firstly, we define stability for $K$-level optimizations and link it to generalization. Then, we detail the stability results for three prominent STORM-based algorithms. Finally, we derive their excess risk bounds by balancing stability results with optimization errors. Our theoretical results provide strong evidence to complete STORM-based algorithms: (1) Each estimator may decrease their stability due to variance with its estimation target. (2) Every additional level might escalate the generalization error, influenced by the stability and the variance between its cumulative stochastic gradient and the true gradient. (3) Increasing the batch size for the initial computation of estimators presents a favorable trade-off, enhancing the generalization performance.

cs.LG↗

arXiv2024

Quantum oscillations in kagome metals (Ti, Zr, Hf)V6Sn6 at Van Hove filling

Kagome materials have recently drawn great attention due to the interplay between nontrivial band topology, electron correlations, and Van Hove singularities related many-body orders. Here we report three new vanadium-based kagome metals, TiV6Sn6, ZrV6Sn6, and HfV6Sn6, and conduct a comprehensive investigation of their structural, magnetic, and electrical transport properties. All three compounds exhibit large unsaturated magnetoresistances and multiband Hall effects at low temperatures, indicating the existence of multiple highly mobile carriers. Both the diagonal and off-diagonal resistivity show quantum oscillations with nontrivial Berry phases and high quantum mobilities. First-principles calculations together with quantum oscillation analyses suggest the Van Hove singularities at the M point for the three compounds all located in close vicinity of the Fermi level, and there also exist multiple topological nontrivial band crossings, including a nodal ring and a massive Dirac cone. Our work extends the kagome AM6X6 family and paves the way for searching possible Van Hove physics in the V kagome lattice.

cond-mat.str-el↗

arXiv2024

What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.

cs.CV↗

arXiv2023

Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization

This paper delves into the realm of stochastic optimization for compositional minimax optimization - a pivotal challenge across various machine learning domains, including deep AUC and reinforcement learning policy evaluation. Despite its significance, the problem of compositional minimax optimization is still under-explored. Adding to the complexity, current methods of compositional minimax optimization are plagued by sub-optimal complexities or heavy reliance on sizable batch sizes. To respond to these constraints, this paper introduces a novel method, called Nested STOchastic Recursive Momentum (NSTORM), which can achieve the optimal sample complexity of $O(κ^3 /ε^3 )$ to obtain the $ε$-accuracy solution. We also demonstrate that NSTORM can achieve the same sample complexity under the Polyak-Łojasiewicz (PL)-condition - an insightful extension of its capabilities. Yet, NSTORM encounters an issue with its requirement for low learning rates, potentially constraining its real-world applicability in machine learning. To overcome this hurdle, we present ADAptive NSTORM (ADA-NSTORM) with adaptive learning rates. We demonstrate that ADA-NSTORM can achieve the same sample complexity but the experimental results show its more effectiveness. All the proposed complexities indicate that our proposed methods can match lower bounds to existing minimax optimizations, without requiring a large batch size in each iteration. Extensive experiments support the efficiency of our proposed methods.

cs.LG↗

arXiv2023

Parrot-Trained Adversarial Examples: Pushing the Practicality of Black-Box Audio Attacks against Speaker Recognition Models

Audio adversarial examples (AEs) have posed significant security challenges to real-world speaker recognition systems. Most black-box attacks still require certain information from the speaker recognition model to be effective (e.g., keeping probing and requiring the knowledge of similarity scores). This work aims to push the practicality of the black-box attacks by minimizing the attacker's knowledge about a target speaker recognition model. Although it is not feasible for an attacker to succeed with completely zero knowledge, we assume that the attacker only knows a short (or a few seconds) speech sample of a target speaker. Without any probing to gain further knowledge about the target model, we propose a new mechanism, called parrot training, to generate AEs against the target model. Motivated by recent advancements in voice conversion (VC), we propose to use the one short sentence knowledge to generate more synthetic speech samples that sound like the target speaker, called parrot speech. Then, we use these parrot speech samples to train a parrot-trained(PT) surrogate model for the attacker. Under a joint transferability and perception framework, we investigate different ways to generate AEs on the PT model (called PT-AEs) to ensure the PT-AEs can be generated with high transferability to a black-box target model with good human perceptual quality. Real-world experiments show that the resultant PT-AEs achieve the attack success rates of 45.8% - 80.8% against the open-source models in the digital-line scenario and 47.9% - 58.3% against smart devices, including Apple HomePod (Siri), Amazon Echo, and Google Home, in the over-the-air scenario.

cs.SD↗

arXiv2023

You Only Forward Once: Prediction and Rationalization in A Single Forward Pass

Unsupervised rationale extraction aims to extract concise and contiguous text snippets to support model predictions without any annotated rationale. Previous studies have used a two-phase framework known as the Rationalizing Neural Prediction (RNP) framework, which follows a generate-then-predict paradigm. They assumed that the extracted explanation, called rationale, should be sufficient to predict the golden label. However, the assumption above deviates from the original definition and is too strict to perform well. Furthermore, these two-phase models suffer from the interlocking problem and spurious correlations. To solve the above problems, we propose a novel single-phase framework called You Only Forward Once (YOFO), derived from a relaxed version of rationale where rationales aim to support model predictions rather than make predictions. In our framework, A pre-trained language model like BERT is deployed to simultaneously perform prediction and rationalization with less impact from interlocking or spurious correlations. Directly choosing the important tokens in an unsupervised manner is intractable. Instead of directly choosing the important tokens, YOFO gradually removes unimportant tokens during forward propagation. Through experiments on the BeerAdvocate and Hotel Review datasets, we demonstrate that our model is able to extract rationales and make predictions more accurately compared to RNP-based models. We observe an improvement of up to 18.4\% in token-level F1 compared to previous state-of-the-art methods. We also conducted analyses and experiments to explore the extracted rationales and token decay strategies. The results show that YOFO can extract precise and important rationales while removing unimportant tokens in the middle part of the model.

cs.CL↗

arXiv2023

Quantum Interactions in Topological R166 Kagome Magnet

Kagome magnet has been found to be a fertile ground for the search of exotic quantum states in condensed matter. Arising from the unusual geometry, the quantum interactions in the kagome lattice give rise to various quantum states, including the Chern-gapped Dirac fermion, Weyl fermion, flat band and van Hove singularity. Here we review recent advances in the study of the R166 kagome magnet (RT6E6, R = rare earths; T = transition metals; and E = Sn, Ge, etc.) whose crystal structure highlights the transition-metal-based kagome lattice and rare-earth sublattice. Compared with other kagome magnets, the R166 family owns the particularly strong interplays between the d electrons on the kagome site and the localized f electrons on the rare-earth site. In the form of spin-orbital coupling, exchange interaction and many-body effect, the quantum interactions play an essential role in the Berry curvature field in both the reciprocal and real spaces of R166 family. We discuss the spectroscopic and transport visualization of the topological electrons hosted in the Mn kagome layer of RMn6Sn6 and the various topological effects due to the quantum interactions, including the Chern-gap opening, the exchange-biased effect, the topological Hall effect and the emergent inductance. We hope this work serves as a guide for future explorations of quantum magnets.

cond-mat.str-el↗

arXiv2023

Static and dynamical properties of the spin-5/2 nearly ideal triangular lattice antiferromagnet Ba3MnSb2O9

We study the ground state and spin excitations in Ba3MnSb2O9, an easy-plane S = 5/2 triangular lattice antiferromagnet. By combining single-crystal neutron scattering, electric spin resonance (ESR), and spin wave calculations, we determine the frustrated quasi-two-dimensional spin Hamiltonian parameters describing the material. While the material has a slight monoclinic structural distortion, which could allow for isosceles-triangular exchanges and biaxial anisotropy by symmetry, we observe no deviation from the behavior expected for spin waves in the in-plane 120o state. Even the easy-plane anisotropy is so small that it can only be detected by ESR in our study. In conjunction with the quasi-two-dimensionality, our study establishes that Ba3MnSb2O9 is a nearly ideal triangular lattice antiferromagnet with the quasi-classical spin S = 5/2, which suggests that it has the potential for an experimental study of Z- or Z2-vortex excitations.

cond-mat.str-el↗

arXiv2023

Inter-Instance Similarity Modeling for Contrastive Learning

The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich inter-instance similarities among natural images, then leading to potential representation degeneration. In this paper, we propose a novel image mix method, PatchMix, for contrastive learning in Vision Transformer (ViT), to model inter-instance similarities among images. Following the nature of ViT, we randomly mix multiple images from mini-batch in patch level to construct mixed image patch sequences for ViT. Compared to the existing sample mix methods, our PatchMix can flexibly and efficiently mix more than two images and simulate more complicated similarity relations among natural images. In this manner, our contrastive framework can significantly reduce the gap between contrastive objective and ground truth in reality. Experimental results demonstrate that our proposed method significantly outperforms the previous state-of-the-art on both ImageNet-1K and CIFAR datasets, e.g., 3.0% linear accuracy improvement on ImageNet-1K and 8.7% kNN accuracy improvement on CIFAR100. Moreover, our method achieves the leading transfer performance on downstream tasks, object detection and instance segmentation on COCO dataset. The code is available at https://github.com/visresearch/patchmix

cs.CV↗

arXiv2023

Data-Driven Next-Generation Wireless Networking: Embracing AI for Performance and Security

New network architectures, such as the Internet of Things (IoT), 5G, and next-generation (NextG) cellular systems, put forward emerging challenges to the design of future wireless networks toward ultra-high data rate, massive data processing, smart designs, low-cost deployment, reliability and security in dynamic environments. As one of the most promising techniques today, artificial intelligence (AI) is advocated to enable a data-driven paradigm for wireless network design. In this paper, we are motivated to review existing AI techniques and their applications for the full wireless network protocol stack toward improving network performance and security. Our goal is to summarize the current motivation, challenges, and methodology of using AI to enhance wireless networking from the physical to the application layer, and shed light on creating new AI-enabled algorithms, mechanisms, protocols, and system designs for future data-driven wireless networking.

cs.NI↗

arXiv2023

Probing the electronic topological transitions of WTe2 under pressure using ultrafast spectroscopy

We investigate the nonequilibrium photocarrier dynamics of WTe2 under pressure using the optical pump-probe spectroscopy. The pressure dependences of the electronic relaxation manifest anomalous changes around 0.8, 3.5, and 6 GPa, indicating the abruptions in the electron-phonon interactions. In addition, the coherent phonon oscillations originating from shear mode suddenly disappears above 3.5 GPa, which marks the onset of Td-1T' structural phase transition. Supported by the theoretical calculation, we unveil the electronic topological transitions (ETTs), especially an emergence of a new type-II Weyl point for Td-WTe2 under pressure. Our work demonstrates a novel route to probe the ETTs under pressure.

cond-mat.str-el↗

arXiv2023

Magnetic field effects on the quantum spin liquid behaviors of NaYbS$_2$

Spin-orbit coupling is an important ingredient to regulate the many-body physics, especially for many spin liquid candidate materials such as rare-earth magnets and Kitaev materials. The rare-earth chalcogenides NaYbCh$_2$ (Ch = O, S, Se) is a congenital frustrating system to exhibit the intrinsic landmark of spin liquid by eliminating both the site disorders between Na$^{+}$ and Yb$^{3+}$ ions with the big ionic size difference and the Dzyaloshinskii-Moriya interaction with the perfect triangular lattice of the Yb$^{3+}$ ions. The temperature versus magnetic-field phase diagram is established by the magnetization, specific heat, and neutron-scattering measurements. Notably, the neutron diffraction spectra and the magnetization curve might provide microscopic evidence for a series of spin configuration for in-plane fields, which include the disordered spin liquid state, 120$^{o}$ antiferromagnet, and one-half magnetization state. Furthermore, the ground state is suggested to be a gapless spin liquid from inelastic neutron scattering, and the magnetic field adjusts the spin orbit coupling. Therefore, the strong spin-orbit coupling in the frustrated quantum magnet substantially enriches low-energy spin physics. This rare-earth family could offer a good platform for exploring the quantum spin liquid ground state and quantum magnetic transitions.

cond-mat.str-el↗

arXiv2022

Modeling Global Distribution for Federated Learning with Label Distribution Skew

Federated learning achieves joint training of deep models by connecting decentralized data sources, which can significantly mitigate the risk of privacy leakage. However, in a more general case, the distributions of labels among clients are different, called ``label distribution skew''. Directly applying conventional federated learning without consideration of label distribution skew issue significantly hurts the performance of the global model. To this end, we propose a novel federated learning method, named FedMGD, to alleviate the performance degradation caused by the label distribution skew issue. It introduces a global Generative Adversarial Network to model the global data distribution without access to local datasets, so the global model can be trained using the global information of data distribution without privacy leakage. The experimental results demonstrate that our proposed method significantly outperforms the state-of-the-art on several public benchmarks. Code is available at \url{https://github.com/Sheng-T/FedMGD}.

cs.LG↗

arXiv2022

D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data

Modern biomedical studies often collect multi-view data, that is, multiple types of data measured on the same set of objects. A popular model in high-dimensional multi-view data analysis is to decompose each view's data matrix into a low-rank common-source matrix generated by latent factors common across all data views, a low-rank distinctive-source matrix corresponding to each view, and an additive noise matrix. We propose a novel decomposition method for this model, called decomposition-based generalized canonical correlation analysis (D-GCCA). The D-GCCA rigorously defines the decomposition on the L2 space of random variables in contrast to the Euclidean dot product space used by most existing methods, thereby being able to provide the estimation consistency for the low-rank matrix recovery. Moreover, to well calibrate common latent factors, we impose a desirable orthogonality constraint on distinctive latent factors. Existing methods, however, inadequately consider such orthogonality and may thus suffer from substantial loss of undetected common-source variation. Our D-GCCA takes one step further than generalized canonical correlation analysis by separating common and distinctive components among canonical variables, while enjoying an appealing interpretation from the perspective of principal component analysis. Furthermore, we propose to use the variable-level proportion of signal variance explained by common or distinctive latent factors for selecting the variables most influenced. Consistent estimators of our D-GCCA method are established with good finite-sample numerical performance, and have closed-form expressions leading to efficient computation especially for large-scale data. The superiority of D-GCCA over state-of-the-art methods is also corroborated in simulations and real-world data examples.

stat.ML↗

arXiv2022

On the Convergence of Multi-Server Federated Learning with Overlapping Area

Multi-server Federated learning (FL) has been considered as a promising solution to address the limited communication resource problem of single-server FL. We consider a typical multi-server FL architecture, where the coverage areas of regional servers may overlap. The key point of this architecture is that the clients located in the overlapping areas update their local models based on the average model of all accessible regional models, which enables indirect model sharing among different regional servers. Due to the complicated network topology, the convergence analysis is much more challenging than single-server FL. In this paper, we firstly propose a novel MS-FedAvg algorithm for this multi-server FL architecture and analyze its convergence on non-iid datasets for general non-convex settings. Since the number of clients located in each regional server is much less than in single-server FL, the bandwidth of each client should be large enough to successfully communicate training models with the server, which indicates that full client participation can work in multi-server FL. Also, we provide the convergence analysis of the partial client participation scheme and develop a new biased partial participation strategy to further accelerate convergence. Our results indicate that the convergence results highly depend on the ratio of the number of clients in each area type to the total number of clients in all three strategies. The extensive experiments show remarkable performance and support our theoretical results.

cs.DC↗

arXiv2022

Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception

Recently, adversarial machine learning attacks have posed serious security threats against practical audio signal classification systems, including speech recognition, speaker recognition, and music copyright detection. Previous studies have mainly focused on ensuring the effectiveness of attacking an audio signal classifier via creating a small noise-like perturbation on the original signal. It is still unclear if an attacker is able to create audio signal perturbations that can be well perceived by human beings in addition to its attack effectiveness. This is particularly important for music signals as they are carefully crafted with human-enjoyable audio characteristics. In this work, we formulate the adversarial attack against music signals as a new perception-aware attack framework, which integrates human study into adversarial attack design. Specifically, we conduct a human study to quantify the human perception with respect to a change of a music signal. We invite human participants to rate their perceived deviation based on pairs of original and perturbed music signals, and reverse-engineer the human perception process by regression analysis to predict the human-perceived deviation given a perturbed signal. The perception-aware attack is then formulated as an optimization problem that finds an optimal perturbation signal to minimize the prediction of perceived deviation from the regressed human perception model. We use the perception-aware framework to design a realistic adversarial music attack against YouTube's copyright detector. Experiments show that the perception-aware attack produces adversarial music with significantly better perceptual quality than prior work.

cs.SD↗

arXiv2022

Generalized Federated Learning via Sharpness Aware Minimization

Federated Learning (FL) is a promising framework for performing privacy-preserving, distributed learning with a set of clients. However, the data distribution among clients often exhibits non-IID, i.e., distribution shift, which makes efficient optimization difficult. To tackle this problem, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by increasing the performance of the global model. However, almost all algorithms leverage Empirical Risk Minimization (ERM) to be the local optimizer, which is easy to make the global model fall into a sharp valley and increase a large deviation of parts of local clients. Therefore, in this paper, we revisit the solutions to the distribution shift problem in FL with a focus on local learning generality. To this end, we propose a general, effective algorithm, \texttt{FedSAM}, based on Sharpness Aware Minimization (SAM) local optimizer, and develop a momentum FL algorithm to bridge local and global models, \texttt{MoFedSAM}. Theoretically, we show the convergence analysis of these two algorithms and demonstrate the generalization bound of \texttt{FedSAM}. Empirically, our proposed algorithms substantially outperform existing FL studies and significantly decrease the learning deviation.

cs.LG↗

arXiv2022

Regulate the direct-indirect electronic band gap transition by electron-phonon interaction in BaSnO3

The neutron powder diffraction, specific heat, thermal conductivity, and Raman scattering measurements were presented to study the interplays of lattice, phonons and electrons of the Sr-doping Ba1-xSrxSnO3 (x was less than or equal to 0.1). Although Ba1-xSrxSnO3 kept the cubic lattice, the Raman spectra suggested a dynamic distortion at low temperature. The density functional theory was applied to analyze the electronic structures and phonon dispersions of Ba1-xSrxSnO3(x = 0, 0.0125), and the behaviors of electron bands around Fermi levels were discussed. According to the experimental and theoretical results, the Sr-doping played a significant role in tuning the indirect band gap of BaSnO3 and influenced the electron-phonon interaction.

cond-mat.mtrl-sci↗