Searcharxiv⌕ Search

arXiv subjects

Di Liu

Publications and source records attributed to Di Liu.

At least 127 records · Page 7Linked to original sources
arXiv2022

Spin-optical dynamics and quantum efficiency of single V1 center in silicon carbide

Color centers in silicon carbide are emerging candidates for distributed spin-based quantum applications due to the scalability of host materials and the demonstration of integration into nanophotonic resonators. Recently, silicon vacancy centers in silicon carbide have been identified as a promising system with excellent spin and optical properties. Here, we in-depth study the spin-optical dynamics of single silicon vacancy center at hexagonal lattice sites, namely V1, in 4H-polytype silicon carbide. By utilizing resonant and above-resonant sub-lifetime pulsed excitation, we determine spin-dependent excited-state lifetimes and intersystem-crossing rates. Our approach to inferring the intersystem-crossing rates is based on all-optical pulsed initialization and readout scheme, and is applicable to spin-active color centers with similar dynamics models. In addition, the optical transition dipole strength and the quantum efficiency of V1 defect are evaluated based on coherent optical Rabi measurement and local-field calibration employing electric-field simulation. The measured rates well explain the results of spin-state polarization dynamics, and we further discuss the altered photoemission dynamics in resonant enhancement structures such as radiative lifetime shortening and Purcell enhancement. By providing a thorough description of V1 center's spin-optical dynamics, our work provides deep understanding of the system which guides implementations of scalable quantum applications based on silicon vacancy centers in silicon carbide.

quant-ph↗
arXiv2022

Causality Inspired Representation Learning for Domain Generalization

Domain generalization (DG) is essentially an out-of-distribution problem, aiming to generalize the knowledge learned from multiple source domains to an unseen target domain. The mainstream is to leverage statistical models to model the dependence between data and labels, intending to learn representations independent of domain. Nevertheless, the statistical models are superficial descriptions of reality since they are only required to model dependence instead of the intrinsic causal mechanism. When the dependence changes with the target distribution, the statistic models may fail to generalize. In this regard, we introduce a general structural causal model to formalize the DG problem. Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments. Our goal is to extract the causal factors from inputs and then reconstruct the invariant causal mechanisms. However, the theoretical idea is far from practical of DG since the required causal/non-causal factors are unobserved. We highlight that ideal causal factors should meet three basic properties: separated from the non-causal ones, jointly independent, and causally sufficient for the classification. Based on that, we propose a Causality Inspired Representation Learning (CIRL) algorithm that enforces the representations to satisfy the above properties and then uses them to simulate the causal factors, which yields improved generalization ability. Extensive experimental results on several widely used datasets verify the effectiveness of our approach.

cs.LG↗
arXiv2022

Improving Robustness of Convolutional Neural Networks Using Element-Wise Activation Scaling

Recent works reveal that re-calibrating the intermediate activation of adversarial examples can improve the adversarial robustness of a CNN model. The state of the arts [Baiet al., 2021] and [Yanet al., 2021] explores this feature at the channel level, i.e. the activation of a channel is uniformly scaled by a factor. In this paper, we investigate the intermediate activation manipulation at a more fine-grained level. Instead of uniformly scaling the activation, we individually adjust each element within an activation and thus propose Element-Wise Activation Scaling, dubbed EWAS, to improve CNNs' adversarial robustness. Experimental results on ResNet-18 and WideResNet with CIFAR10 and SVHN show that EWAS significantly improves the robustness accuracy. Especially for ResNet18 on CIFAR10, EWAS increases the adversarial accuracy by 37.65% to 82.35% against C&W attack. EWAS is simple yet very effective in terms of improving robustness. The codes are anonymously available at https://anonymous.4open.science/r/EWAS-DD64.

cs.CV↗
arXiv2021

Pareto Domain Adaptation

Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source. To achieve this, DA methods include a source classification objective to extract the source knowledge and a domain alignment objective to diminish the domain shift, ensuring knowledge transfer. Typically, former DA methods adopt some weight hyper-parameters to linearly combine the training objectives to form an overall objective. However, the gradient directions of these objectives may conflict with each other due to domain shift. Under such circumstances, the linear optimization scheme might decrease the overall objective value at the expense of damaging one of the training objectives, leading to restricted solutions. In this paper, we rethink the optimization scheme for DA from a gradient-based perspective. We propose a Pareto Domain Adaptation (ParetoDA) approach to control the overall optimization direction, aiming to cooperatively optimize all training objectives. Specifically, to reach a desirable solution on the target domain, we design a surrogate loss mimicking target classification. To improve target-prediction accuracy to support the mimicking, we propose a target-prediction refining mechanism which exploits domain labels via Bayes' theorem. On the other hand, since prior knowledge of weighting schemes for objectives is often unavailable to guide optimization to approach the optimal solution on the target domain, we propose a dynamic preference mechanism to dynamically guide our cooperative optimization by the gradient of the surrogate loss on a held-out unlabeled target dataset. Extensive experiments on image classification and semantic segmentation benchmarks demonstrate the effectiveness of ParetoDA

cs.LG↗
arXiv2021

Incentive Compatible Pareto Alignment for Multi-Source Large Graphs

In this paper, we focus on learning effective entity matching models over multi-source large-scale data. For real applications, we relax typical assumptions that data distributions/spaces, or entity identities are shared between sources, and propose a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem. Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data. What's worse, one practical issue is the entanglement between both challenges. Specifically, incorrect alignments may increase negative transfer; while mitigating negative transfer for one source may result in poorly learned representations for other sources and then decrease alignment accuracy. To handle the entangled challenges, we point out that the key is to optimize information sharing first based on Pareto front optimization, by showing that information sharing significantly influences the Pareto front which depicts lower bounds of negative transfer. Consequently, we proposed an Incentive Compatible Pareto Alignment (ICPA) method to first optimize cross-source alignments based on Pareto front optimization, then mitigate negative transfer constrained on the optimized alignments. This mechanism renders each source can learn based on its true preference without worrying about deteriorating representations of other sources. Specifically, the Pareto front optimization encourages minimizing lower bounds of negative transfer, which optimizes whether and which to align. Comprehensive empirical evaluation results on four large-scale datasets are provided to demonstrate the effectiveness and superiority of ICPA. Online A/B test results at a search advertising platform also demonstrate the effectiveness of ICPA in production environments.

stat.ML↗
arXiv2021

Transverse mode-encoded quantum gate on a silicon photonic chip

As an important degree of freedom (DoF) in integrated photonic circuits, the orthogonal transverse mode provides a promising and flexible way to increasing communication capability, for both classical and quantum information processing. To construct large-scale on-chip multimode multi-DoF quantum systems, a transverse mode-encoded controlled-NOT (CNOT) gate is necessary. Here, through design and integrate transverse mode-dependent directional coupler and attenuators on a silicon photonic chip, we demonstrate the first multimode implementation of a two-qubit quantum gate. With the aid of state preparation and analysis parts, we show the ability of the gate to entangle two separated transverse mode qubits with an average fidelity of $0.89\pm0.02$ and the achievement of 10 standard deviations of violations in the quantum nonlocality verification. In addition, a fidelity of $0.82\pm0.01$ was obtained from quantum process tomography used to completely characterize the CNOT gate. Our work paves the way for universal transverse mode-encoded quantum operations and large-scale multimode multi-DoF quantum systems.

quant-ph↗
arXiv2021

Nanofabricated and integrated colour centres in silicon carbide with high-coherence spin-optical properties

Optically addressable spin defects in silicon carbide (SiC) are an emerging platform for quantum information processing. Lending themselves to modern semiconductor nanofabrication, they promise scalable high-efficiency spin-photon interfaces. We demonstrate here nanoscale fabrication of silicon vacancy centres (VSi) in 4H-SiC without deterioration of their intrinsic spin-optical properties. In particular, we show nearly transform limited photon emission and record spin coherence times for single defects generated via ion implantation and in triangular cross section waveguides. For the latter, we show further controlled operations on nearby nuclear spin qubits, which is crucial for fault-tolerant quantum information distribution based on cavity quantum electrodynamics.

quant-ph↗
arXiv2021

Hidden Frustration in Double-Perovskite CaFeTi$_2$O$_6$

We study the magnetic properties of CaFeTi$_2$O$_6$ (CFTO) by high-field magnetization and specific heat measurements. While the magnetic susceptibility data yield a vanishingly small Curie-Weiss temperature, the magnetic moments are not fully polarized in magnetic field up to 60 T, which reveals a large spin exchange energy scale. Yet, the system shows no long range magnetic order but a spin-glass-like state below 5.5 K in zero field, indicating strong magnetic frustration in this system. Applying magnetic field gradually suppresses the spin-glass-like state and gives rise to a potential quantum spin liquid state whose low-temperature specific heat exhibits a $T^{1.6}$ power-law. Crucially, conventional mechanisms for frustration do not apply to this system as it possesses neither apparent geometrical frustration nor exchange frustration. We suggest that the orbital modulation of exchange interaction is likely the source of hidden frustration in CFTO, and its full characterization may open a new route in the quest for quantum spin liquids.

cond-mat.str-el↗
arXiv2021

Forbidden Dark Matter Annihilations into Standard Model Particles

We present kinematically forbidden dark matter annihilations into Standard Model leptons. This mechanism precisely selects the dark matter mass that gives the observed relic abundance. This is qualitatively different from existing models of thermal dark matter, where fixing the relic density typically leaves open orders of magnitude of viable dark matter masses. Forbidden annihilations require the dark matter to be close in mass to the particles that dominate its annihilation rate. We show examples where the dark matter mass is close to the muon mass, the tau mass, or the average of the tau and muon masses. We find that most of the relevant parameter space can be covered by the next generation of proposed beam-dump experiments and future high-luminosity electron positron colliders. Forbidden dark matter predicts large couplings to the Standard Model that can explain the observed value of $(g-2)_μ$.

hep-ph↗
arXiv2021

Narrow inhomogeneous distribution of spin-active emitters in silicon carbide

Optically active solid-state spin registers have demonstrated their unique potential in quantum computing, communication and sensing. Realizing scalability and increasing application complexity requires entangling multiple individual systems, e.g. via photon interference in an optical network. However, most solid-state emitters show relatively broad spectral distributions, which hinders optical interference experiments. Here, we demonstrate that silicon vacancy centres in semiconductor silicon carbide (SiC) provide a remarkably small natural distribution of their optical absorption/emission lines despite an elevated defect concentration of $\approx 0.43\,\rm μm^{-3}$. In particular, without any external tuning mechanism, we show that only 13 defects have to be investigated until at least two optical lines overlap within the lifetime-limited linewidth. Moreover, we identify emitters with overlapping emission profiles within diffraction limited excitation spots, for which we introduce simplified schemes for generation of computationally-relevant Greenberger-Horne-Zeilinger (GHZ) and cluster states. Our results underline the potential of the CMOS-compatible SiC platform toward realizing networked quantum technology applications.

quant-ph↗
arXiv2021

HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search

In this paper, we present a novel multi-objective hardware-aware neural architecture search (NAS) framework, namely HSCoNAS, to automate the design of deep neural networks (DNNs) with high accuracy but low latency upon target hardware. To accomplish this goal, we first propose an effective hardware performance modeling method to approximate the runtime latency of DNNs on target hardware, which will be integrated into HSCoNAS to avoid the tedious on-device measurements. Besides, we propose two novel techniques, i.e., dynamic channel scaling to maximize the accuracy under the specified latency and progressive space shrinking to refine the search space towards target hardware as well as alleviate the search overheads. These two techniques jointly work to allow HSCoNAS to perform fine-grained and efficient explorations. Finally, an evolutionary algorithm (EA) is incorporated to conduct the architecture search. Extensive experiments on ImageNet are conducted upon diverse target hardware, i.e., GPU, CPU, and edge device to demonstrate the superiority of HSCoNAS over recent state-of-the-art approaches.

cs.LG↗
arXiv2020

Bringing AI To Edge: From Deep Learning's Perspective

Edge computing and artificial intelligence (AI), especially deep learning for nowadays, are gradually intersecting to build a novel system, called edge intelligence. However, the development of edge intelligence systems encounters some challenges, and one of these challenges is the \textit{computational gap} between computation-intensive deep learning algorithms and less-capable edge systems. Due to the computational gap, many edge intelligence systems cannot meet the expected performance requirements. To bridge the gap, a plethora of deep learning techniques and optimization methods are proposed in the past years: light-weight deep learning models, network compression, and efficient neural architecture search. Although some reviews or surveys have partially covered this large body of literature, we lack a systematic and comprehensive review to discuss all aspects of these deep learning techniques which are critical for edge intelligence implementation. As various and diverse methods which are applicable to edge systems are proposed intensively, a holistic review would enable edge computing engineers and community to know the state-of-the-art deep learning techniques which are instrumental for edge intelligence and to facilitate the development of edge intelligence systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search and adaptive deep learning models. Finally, based on observations and simple experiments we conducted, we discuss some future directions.

cs.LG↗
arXiv2020

Identifying Transition States of Chemical Kinetic Systems using Network Embedding Techniques

Using random walk sampling methods for feature learning on networks, we develop a method for generating low-dimensional node embeddings for directed graphs and identifying transition states of stochastic chemical reacting systems. We modified objective functions adopted in existing random walk based network embedding methods to handle directed graphs and neighbors of different degrees. Through optimization via gradient ascent, we embed the weighted graph vertices into a low-dimensional vector space Rd while preserving the neighborhood of each node. We then demonstrate the effectiveness of the method on dimension reduction through several examples regarding identification of transition states of chemical reactions, especially for entropic systems.

math.NA↗
arXiv2020

Global to local impacts on atmospheric CO2 caused by COVID-19 lockdown

The world-wide lockdown in response to the COVID-19 pandemic in year 2020 led to economic slowdown and large reduction of fossil fuel CO2 emissions, but it is unclear how much it would reduce atmospheric CO2 concentration, and whether it can be observed. We estimated that a 7.9% reduction in emissions for 4 months would result in a 0.25 ppm decrease in the Northern Hemisphere CO2, an increment that is within the capability of current CO2 analyzers, but is a few times smaller than natural CO2 variabilities caused by weather and the biosphere such as El Nino. We used a state-of-the-art atmospheric transport model to simulate CO2, driven by a new daily fossil fuel emissions dataset and hourly biospheric fluxes from a carbon cycle model forced with observed climate variability. Our results show a 0.13 ppm decrease in atmospheric column CO2 anomaly averaged over 50S-50N for the period February-April 2020 relative to a 10-year climatology. A similar decrease was observed by the carbon satellite GOSAT3. Using model sensitivity experiments, we further found that COVID, the biosphere and weather contributed 54%, 23%, and 23% respectively. This seemingly small change stands out as the largest sub-annual anomaly in the last 10 years. Measurements from global ground stations were analyzed. At city scale, on-road CO2 enhancement measured in Beijing shows reduction of 20-30 ppm, consistent with drastically reduced traffic during the lockdown. The ability of our current carbon monitoring systems in detecting the small and short-lasting COVID signal on the background of fossil fuel CO2 accumulated over the last two centuries is encouraging. The COVID-19 pandemic is an unintended experiment whose impact suggests that to keep atmospheric CO2 at a climate-safe level will require sustained effort of similar magnitude and improved accuracy and expanded spatiotemporal coverage of our monitoring systems.

physics.ao-ph↗
arXiv2020

A fast approximate skeleton with guarantees for any cloud of points in a Euclidean space

The tree reconstruction problem is to find an embedded straight-line tree that approximates a given cloud of unorganized points in $\mathbb{R}^m$ up to a certain error. A practical solution to this problem will accelerate a discovery of new colloidal products with desired physical properties such as viscosity. We define the Approximate Skeleton of any finite point cloud $C$ in a Euclidean space with theoretical guarantees. The Approximate Skeleton ASk$(C)$ always belongs to a given offset of $C$, i.e. the maximum distance from $C$ to ASk$(C)$ can be a given maximum error. The number of vertices in the Approximate Skeleton is close to the minimum number in an optimal tree by factor 2. The new Approximate Skeleton of any unorganized point cloud $C$ is computed in a near linear time in the number of points in $C$. Finally, the Approximate Skeleton outperforms past skeletonization algorithms on the size and accuracy of reconstruction for a large dataset of real micelles and random clouds.

cs.CG↗
arXiv2020

Spin Excitations and Spin Wave Gap in the Ferromagnetic Weyl Semimetal Co$_3$Sn$_2$S$_2$

We report a comprehensive neutron scattering study on the spin excitations in the magnetic Weyl semimetal Co$_3$Sn$_2$S$_2$ with quasi-two-dimensional structure. Both in-plane and out-of-plane dispersions of the spin waves are revealed in the ferromagnetic state, similarly dispersive but damped spin excitations persist into the paramagnetic state. The effective exchange interactions have been estimated by a semi-classical Heisenberg model to consistently reproduce the experimental $T_C$ and spin stiffness. However, a full spin wave gap below $E_g=2.3$ meV is observed at $T=4$ K, much larger than the estimated magnetic anisotropy energy ($\sim0.6$ meV), while its temperature dependence indicates a significant contribution from the Weyl fermions. These results suggest that Co$_3$Sn$_2$S$_2$ is a three-dimensional correlated system with large spin stiffness, and the low-energy spin dynamics could interplay with the topological electron states.

cond-mat.str-el↗
arXiv2020

Observation of exceptional point in a PT broken non-Hermitian system simulated using a quantum circuit

Exceptional points (EPs), the degeneracy point of non-Hermitian systems, have recently attracted great attention after its ability to greatly enhance the sensitivity of micro-cavities is demonstrated experimentally. Unlike the usual degeneracies in Hermitian systems, at EPs, both the eigenenergies and eigenvectors coalesce. Although some of the exotic properties and potential applications of EPs are explored, the range of EPs studied is largely limited by the experimental capability. Some of the systems, e.g. with higher-order EPs, are hard to achieve with conventional simulations. Here we propose an extendable method to simulate non-Hermitian systems on the quantum circuits, where a wide range of EPs can be studied. The system is inherently parity-time (PT) broken due to the non-symmetric controlling effects and post-selection. A sample circuit is implemented in a quantum programming framework, and the phase transition at EP is demonstrated. Considering the scalable and flexible nature of quantum circuits, our model is capable of simulating large scale systems with higher-order EPs. We believe this work may lead to broader applications of quantum computers and provide a tool to the studies for non-Hermitian systems and the associated EPs.

quant-ph↗