arXiv subjects

Yi Li

Publications and source records attributed to Yi Li.

At least 307 records · Page 17Linked to original sources

arXiv2024

Harmonic Machine Learning Models are Robust

We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels. It is based on functional deviation from the harmonic mean value property, indicating instability and lack of explainability. We show implementation examples in low-dimensional trees and feedforward NNs, where the method reliably identifies overfitting, as well as in more complex high-dimensional models such as ResNet-50 and Vision Transformer where it efficiently measures adversarial vulnerability across image classes.

cs.LG↗

arXiv2024

The Complex Estimand of Clone-Censor-Weighting When Studying Treatment Initiation Windows

Clone-censor-weighting (CCW) is an analytic method for studying treatment regimens that are indistinguishable from one another at baseline without relying on landmark dates or creating immortal person time. One particularly interesting CCW application is estimating outcomes when starting treatment within specific time windows in observational data (e.g., starting a treatment within 30 days of hospitalization). In such cases, CCW estimates something fairly complex. We show how using CCW to study a regimen such as "start treatment prior to day 30" estimates the potential outcome of a hypothetical intervention where A) prior to day 30, everyone follows the treatment start distribution of the study population and B) everyone who has not initiated by day 30 initiates on day 30. As a result, the distribution of treatment initiation timings provides essential context for the results of CCW studies. We also show that if the exposure effect varies over time, ignoring exposure history when estimating inverse probability of censoring weights (IPCW) estimates the risk under an impossible intervention and can create selection bias. Finally, we examine some simplifying assumptions that can make this complex treatment effect more interpretable and allow everyone to contribute to IPCW.

stat.ME↗

arXiv2024

An energy efficient quantum-enhanced machine

Quantum friction, a quantum analog of classical friction, reduces the performance of quantum machines, such as heat engines, and makes them less energy efficient. We here report the experimental realization of an energy efficient quantum engine coupled to a quantum battery that stores the produced work, using a single ion in a linear Paul trap. We first establish the quantum nature of the device by observing nonclassical work oscillations with the number of cycles as verified by energy measurements of the battery. We moreover successfully apply shortcut-to-adiabaticity techniques to suppress quantum friction and improve work production. While the average energy cost of the shortcut protocol is only about $3\%$, the work output is enhanced by up to approximately 33$\%$, making the machine significantly more energy efficient. In addition, we show that the quantum engine consistently outperforms its classical counterpart in this regime. Our results pave the way for energy efficient machines with quantum-enhanced performance.

quant-ph↗

arXiv2024

Cross-Temporal Spectrogram Autoencoder (CTSAE): Unsupervised Dimensionality Reduction for Clustering Gravitational Wave Glitches

The advancement of The Laser Interferometer Gravitational-Wave Observatory (LIGO) has significantly enhanced the feasibility and reliability of gravitational wave detection. However, LIGO's high sensitivity makes it susceptible to transient noises known as glitches, which necessitate effective differentiation from real gravitational wave signals. Traditional approaches predominantly employ fully supervised or semi-supervised algorithms for the task of glitch classification and clustering. In the future task of identifying and classifying glitches across main and auxiliary channels, it is impractical to build a dataset with manually labeled ground-truth. In addition, the patterns of glitches can vary with time, generating new glitches without manual labels. In response to this challenge, we introduce the Cross-Temporal Spectrogram Autoencoder (CTSAE), a pioneering unsupervised method for the dimensionality reduction and clustering of gravitational wave glitches. CTSAE integrates a novel four-branch autoencoder with a hybrid of Convolutional Neural Networks (CNN) and Vision Transformers (ViT). To further extract features across multi-branches, we introduce a novel multi-branch fusion method using the CLS (Class) token. Our model, trained and evaluated on the GravitySpy O3 dataset on the main channel, demonstrates superior performance in clustering tasks when compared to state-of-the-art semi-supervised learning methods. To the best of our knowledge, CTSAE represents the first unsupervised approach tailored specifically for clustering LIGO data, marking a significant step forward in the field of gravitational wave research. The code of this paper is available at https://github.com/Zod-L/CTSAE

cs.CV↗

arXiv2024

Generalized Aubry-Andre-Harper Models in Optical Superlattices

Ultracold atoms trapped in optical superlattices provide a simple platform for realizing the seminal Aubry-André-Harper (AAH) model. However, the periodic modulations on the nearest-neighbour hoppings have been ignored in this model. In this paper, we find that optical superlattice system actually can be approximately described by a generalized AAH model in the case of $V_1\gg V_2$, with periodic modulations on both on-site energies and nearest-neighbour hoppings, supporting much richer topological properties that are absent in the standard AAH model. Specifically, by calculating Chern numbers and topological edge states, we show that the generalized AAH model possesses multifarious topological phases and topological phase transitions, as compared to the standard AAH model only supporting a single topological phase. Our findings can open up more opportunities for using optical superlattices to study topological and localization physics.

cond-mat.quant-gas↗

arXiv2024

Learning the Positions in CountSketch

We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g., low-rank approximation and regression. In the learning-based sketching paradigm proposed by~\cite{indyk2019learning}, the sketch matrix is found by choosing a random sparse matrix, e.g., CountSketch, and then the values of its non-zero entries are updated by running gradient descent on a training data set. Despite the growing body of work on this paradigm, a noticeable omission is that the locations of the non-zero entries of previous algorithms were fixed, and only their values were learned. In this work, we propose the first learning-based algorithms that also optimize the locations of the non-zero entries. Our first proposed algorithm is based on a greedy algorithm. However, one drawback of the greedy algorithm is its slower training time. We fix this issue and propose approaches for learning a sketching matrix for both low-rank approximation and Hessian approximation for second order optimization. The latter is helpful for a range of constrained optimization problems, such as LASSO and matrix estimation with a nuclear norm constraint. Both approaches achieve good accuracy with a fast running time. Moreover, our experiments suggest that our algorithm can still reduce the error significantly even if we only have a very limited number of training matrices.

cs.LG↗

arXiv2024

Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model

Human brains image complicated scenes when reading a novel. Replicating this imagination is one of the ultimate goals of AI-Generated Content (AIGC). However, current AIGC methods, such as score-based diffusion, are still deficient in terms of rapidity and efficiency. This deficiency is rooted in the difference between the brain and digital computers. Digital computers have physically separated storage and processing units, resulting in frequent data transfers during iterative calculations, incurring large time and energy overheads. This issue is further intensified by the conversion of inherently continuous and analog generation dynamics, which can be formulated by neural differential equations, into discrete and digital operations. Inspired by the brain, we propose a time-continuous and analog in-memory neural differential equation solver for score-based diffusion, employing emerging resistive memory. The integration of storage and computation within resistive memory synapses surmount the von Neumann bottleneck, benefiting the generative speed and energy efficiency. The closed-loop feedback integrator is time-continuous, analog, and compact, physically implementing an infinite-depth neural network. Moreover, the software-hardware co-design is intrinsically robust to analog noise. We experimentally validate our solution with 180 nm resistive memory in-memory computing macros. Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64.8 and 156.5, respectively. Moreover, it accomplished reductions in energy consumption by factors of 5.2 and 4.1. Our approach heralds a new horizon for hardware solutions in edge computing for generative AI applications.

cs.AR↗

arXiv2024

RoNet: Rotation-oriented Continuous Image Translation

The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation. Linear relationship acts as the basic assumption in most existing approaches, while applied to different aspects including features, models or labels. However, the linear assumption is hard to conform with the element dimension increases and suffers from the limit that having to obtain both ends of the line. In this paper, we propose a novel rotation-oriented solution and model the continuous generation with an in-plane rotation over the style representation of an image, achieving a network named RoNet. A rotation module is implanted in the generation network to automatically learn the proper plane while disentangling the content and the style of an image. To encourage realistic texture, we also design a patch-based semantic style loss that learns the different styles of the similar object in different domains. We conduct experiments on forest scenes (where the complex texture makes the generation very challenging), faces, streetscapes and the iphone2dslr task. The results validate the superiority of our method in terms of visual quality and continuity.

cs.CV↗

arXiv2024

Probing the band splitting near the $Γ$ point in the van der Waals magnetic semiconductor CrSBr

This study investigates the electronic band structure of Chromium Sulfur Bromide (CrSBr) through comprehensive photoluminescence (PL) characterization. We clearly identify low-temperature optical transitions between two closely adjacent conduction-band states and two different valence-band states. The analysis of the PL data robustly unveils energy splittings, bandgaps and excitonic transitions across different thicknesses of CrSBr, ranging from monolayer to bulk. Temperature-dependent PL measurements elucidate the stability of the band splitting below the Néel temperature, suggesting that magnons coupled with excitons are responsible for the symmetry breaking and brightening of the transitions from the secondary conduction band minimum (CBM2) to the global valence band maximum (VBM1). Collectively, these results not only reveal band splitting in both the conduction and valence bands, but also point to an intricate interplay between the optical, electronic and magnetic properties of antiferromagnetic two-dimensional van der Waals crystals.

cond-mat.mes-hall↗

arXiv2024

GT-Rain Single Image Deraining Challenge Report

This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023. The aim of this competition is to study the rainy weather phenomenon in real world scenarios, provide a novel real world rainy image dataset, and to spark innovative ideas that will further the development of single image deraining methods on real images. Submissions were trained on the GT-Rain dataset and evaluated on an extension of the dataset consisting of 15 additional scenes. Scenes in GT-Rain are comprised of real rainy image and ground truth image captured moments after the rain had stopped. 275 participants were registered in the challenge and 55 competed in the final testing phase.

cs.CV↗

arXiv2024

Combinatorial split-ring and spiral meta-resonator for efficient magnon-photon coupling

Developing hybrid materials and structures for electromagnetic wave engineering has been a promising route towards novel functionalities and tunabilities in many modern applications and perspectives in new quantum technologies. Despite its established success in engineering optical light and terahertz waves, the implementation of meta-resonators operating at the microwave band is still emerging, especially those that allow for on-chip integration and size miniaturization, which has turned out crucial to developing hybrid quantum systems at the microwave band. In this work, we present a microwave meta-resonator consisting of split-ring and and spiral resonators, and implement it to the investigation of photon-magnon coupling for hybrid magnonic applications. We observe broadened bandwidth to the split ring modes augmented by the additional spiral resonator, and, by coupling the modes to a magnetic sample, the resultant photon-magnon coupling can be significantly enhanced to more than ten-fold. Our work suggests that combinatorial, hybrid microwave resonators may be a promising approach towards future development and implementation of photon-magnon coupling in hybrid magnonic systems.

physics.app-ph↗

arXiv2024

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation (SSSS) has been proposed to alleviate the burden of time-consuming pixel-level manual labeling, which leverages limited labeled data along with larger amounts of unlabeled data. Current state-of-the-art methods train the labeled data with ground truths and unlabeled data with pseudo labels. However, the two training flows are separate, which allows labeled data to dominate the training process, resulting in low-quality pseudo labels and, consequently, sub-optimal results. To alleviate this issue, we present AllSpark, which reborns the labeled features from unlabeled ones with the channel-wise cross-attention mechanism. We further introduce a Semantic Memory along with a Channel Semantic Grouping strategy to ensure that unlabeled features adequately represent labeled features. The AllSpark shed new light on the architecture level designs of SSSS rather than framework level, which avoids increasingly complicated training pipeline designs. It can also be regarded as a flexible bottleneck module that can be seamlessly integrated into a general transformer-based segmentation model. The proposed AllSpark outperforms existing methods across all evaluation protocols on Pascal, Cityscapes and COCO benchmarks without bells-and-whistles. Code and model weights are available at: https://github.com/xmed-lab/AllSpark.

cs.CV↗

arXiv2024

Spin: An Efficient Secure Computation Framework with GPU Acceleration

Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks. Spin is a GPU-accelerated MPC framework that supports multiple computation parties and a dishonest majority adversarial setup. We propose optimized protocols for non-linear functions that are critical for machine learning, as well as several novel optimizations specific to attention that is the fundamental unit of Transformer models, allowing Spin to perform non-trivial CNNs training and Transformer inference without sacrificing security. At the backend level, Spin leverages GPU, CPU, and RDMA-enabled smart network cards for acceleration. Comprehensive evaluations demonstrate that Spin can be up to $2\times$ faster than the state-of-the-art for deep neural network training. For inference on a Transformer model with 18.9 million parameters, our attention-specific optimizations enable Spin to achieve better efficiency, less communication, and better accuracy.

cs.CR↗

arXiv2024

The $\ell_p$-Subspace Sketch Problem in Small Dimensions with Applications to Support Vector Machines

In the $\ell_p$-subspace sketch problem, we are given an $n\times d$ matrix $A$ with $n>d$, and asked to build a small memory data structure $Q(A,ε)$ so that, for any query vector $x\in\mathbb{R}^d$, we can output a number in $(1\pmε)\|Ax\|_p^p$ given only $Q(A,ε)$. This problem is known to require $\tildeΩ(dε^{-2})$ bits of memory for $d=Ω(\log(1/ε))$. However, for $d=o(\log(1/ε))$, no data structure lower bounds were known. We resolve the memory required to solve the $\ell_p$-subspace sketch problem for any constant $d$ and integer $p$, showing that it is $Ω(ε^{-2(d-1)/(d+2p)})$ bits and $\tilde{O} (ε^{-2(d-1)/(d+2p)})$ words. This shows that one can beat the $Ω(ε^{-2})$ lower bound, which holds for $d = Ω(\log(1/ε))$, for any constant $d$. We also show how to implement the upper bound in a single pass stream, with an additional multiplicative $\operatorname{poly}(\log \log n)$ factor and an additive $\operatorname{poly}(\log n)$ cost in the memory. Our bounds can be applied to point queries for SVMs with additive error, yielding an optimal bound of $\tildeΘ(ε^{-2d/(d+3)})$ for every constant $d$. This is a near-quadratic improvement over the $Ω(ε^{-(d+1)/(d+3)})$ lower bound of (Andoni et al. 2020). Our techniques rely on a novel connection to low dimensional techniques from geometric functional analysis.

cs.DS↗

arXiv2024

Evaluating Airline Service Quality Through the Comprehensive Text-mining and TOPSIS-VIKOR-AISM Analysis

Service quality rankings are pivotal for maintaining sustainability in the fiercely competitive airline industry. However, prior research in this domain has often fallen short in aspects of sample size, efficiency, and dependability. This study introduces refined insights into this area and establishes a comprehensive, yet highly elucidative, ranking framework. Initially, we employ Latent Semantic Analysis (LSA) to distill principal themes and sentiments from online reviews of 80 airlines. Subsequently, we utilize the SentiWordNet lexicon and the TextBlob package for conducting sentiment analysis based on these reviews. Following this, we construct a hierarchical structure using the computation of compromise solutions, employing an integrated Technique for Order Preference by Similarity to Ideal Solution, vis-à-vis Kriterijumska Optimizacija I Kompromisno Resenje-Adversarial Interpretive Structural Model (TOPSIS-VIKOR-AISM) methodology. Beyond aiding consumer decision-making and fostering airline growth, this study contributes novel viewpoints on evaluating the efficacy of airlines and other sectors.

stat.AP↗

arXiv2024

Holographic Euclidean thermal correlator

In this paper, we compute holographic Euclidean thermal correlators of the stress tensor and $U(1)$ current from the AdS planar black hole. To this end, we set up perturbative boundary value problems for Einstein's gravity and Maxwell theory in the spirit of Gubser-Klebanov-Polyakov-Witten, with appropriate gauge fixing and regularity boundary conditions at the horizon of the black hole. The linearized Einstein equation and Maxwell equation in the black hole background are related to the Heun equation of degenerate local monodromy. Leveraging the connection relation of local solutions of the Heun equation, we partly solve the boundary value problem and obtain exact two-point thermal correlators for $U(1)$ current and stress tensor in the scalar and shear channels.

hep-th↗

arXiv2024

Strong Exciton-Phonon Coupling as a Fingerprint of Magnetic Ordering in van der Waals Layered CrSBr

The layered, air-stable van der Waals antiferromagnetic compound CrSBr exhibits pronounced coupling between its optical, electronic, and magnetic properties. As an example, exciton dynamics can be significantly influenced by lattice vibrations through exciton-phonon coupling. Using low-temperature photoluminescence spectroscopy, we demonstrate the effective coupling between excitons and phonons in nanometer-thick CrSBr. By careful analysis, we identify that the satellite peaks predominantly arise from the interaction between the exciton and an optical phonon with a frequency of 118 cm-1 (~14.6 meV) due to the out-of-plane vibration of Br atoms. Power-dependent and temperature-dependent photoluminescence measurements support exciton-phonon coupling and indicate a coupling between magnetic and optical properties, suggesting the possibility of carrier localization in the material. The presence of strong coupling between the exciton and the lattice may have important implications for the design of light-matter interactions in magnetic semiconductors and provides new insights into the exciton dynamics in CrSBr. This highlights the potential for exploiting exciton-phonon coupling to control the optical properties of layered antiferromagnetic materials.

cond-mat.mtrl-sci↗

arXiv2024

A Dynamic YOLO-Based Sequence-Matching Model for Efficient Coverless Image Steganography

Many existing coverless steganography methods establish a mapping relationship between cover images and hidden data. There exists an issue that the number of images stored in the database grows exponentially as the steganographic capacity rises. The need for a high steganographic capacity makes it challenging to build an image database. To improve the image library utilization and anti-attack capability of the steganography system, we present an efficient coverless scheme based on dynamically matched substrings. YOLO is employed for selecting optimal objects, and a mapping dictionary is established between these objects and scrambling factors. With the aid of this dictionary, each image is effectively assigned to a specific scrambling factor, which is used to scramble the receiver's sequence key. To achieve sufficient steganography capability based on a limited image library, all substrings of the scrambled sequences hold the potential to hide data. After completing the secret information matching, the ideal number of stego images will be obtained from the database. According to experimental results, this technology outperforms most previous works on data load, transmission security, and hiding capacity. Under typical geometric attacks, it can recover 79.85\% of secret information on average. Furthermore, only approximately 200 random images are needed to meet a capacity of 19 bits per image.

cs.CR↗