arXiv subjects

Xu He

Publications and source records attributed to Xu He.

At least 91 records · Page 5Linked to original sources

arXiv2022

Dynamic control of octahedral rotation in perovskites by defect engineering

Engineering oxygen octahedra rotation patterns in $ABO_3$ perovskites is a powerful route to design functional materials. Here we propose a strategy that exploits point defects that create local electric dipoles and couple to the oxygen sublattice, enabling direct actuation on the rotational degrees of freedom. This approach, which relies on substituting an $A$ site with a smaller ion, paves a way to couple dynamically octahedra rotations to external electric fields. A common antisite defect, $\mathrm{Al_{La}}$ in rhombohedral LaAlO$_3$ is taken as a prototype to validate the idea, with atomistic density functional theory calculations supported with an effective lattice model to simulate the dynamics of switching of the local rotational degrees of freedom to long distances. Our simulations provide an insight of the main parameters that govern the operation of the proposed mechanism, and allow to define guidelines for screening other systems where this approach could be used for tuning the properties of the host material.

cond-mat.mtrl-sci↗

arXiv2022

Phase Diagram of Infinite-layer Nickelate Compounds from First- and Second-principles Calculations

The fundamental properties of infinite-layer rare-earth nickelates (RNiO2) are carefully revisited and compared with those of CaCuO2 and RNiO3 perovskites. Combining first-principles and finite-temperature second-principles calculations, we highlight that bulk NdNiO2 compound are far from equivalent to CaCuO2, together at the structural, electronic, and magnetic levels. Structurally, it is shown to be prone to spin-phonon coupling induced oxygen square rotation motion, which might be responsible for the intriguing upturn of the resistivity. At the electronic and magnetic levels, we point out orbital-selective Mott localization with strong out-of-plane band dispersion, which should result in the isotropic upper critical fields and weakly three-dimensional magnetic interactions with in-plane local moment and out-of-plane itinerant moment. We further demonstrate that as in RNiO3 perovskites, oxygen rotation motion and rare-earth ion controlled electronic and magnetic properties can give rise in RNiO2 compounds to a rich phase diagram and high tunability of various appealing properties. In line with that, we reveal that key ingredients of high-Tc superconductor such as orbital polarization, Fermi surface, and antiferromagnetic interactions can be deliberately controlled in NdNiO2 through epitaxial strain. Exploiting strain-orbital engineering, a crossover from three- to two-dimensional magnetic transition can be established, making then NdNiO2 thin film a true analog of high-Tc cuprates.

cond-mat.mtrl-sci↗

arXiv2021

Magnetic properties of {M$_4$} coordination clusters with different magnetic cores (M=Co, Mn)

We present a joint experimental and theoretical characterization of the magnetic properties of coordination clusters with an antiferromagnetic core of four magnetic ions. Two different compounds are analyzed, with Co and Mn ions in the core. While both molecules are antiferromagnetic, they display different sensitivities to external magnetic field, according to the different strength of the intra-molecular magnetic coupling. In particular, the dependence of the magnetization versus field of the two molecules switches with temperatures: at low temperature the magnetization is smaller in \{Mn$_4$\}, while the opposite happens at high temperature. Through a detailed analysis of the electronic and magnetic properties of the two compounds we identify a stronger magnetic interaction between the magnetic ions in \{Mn$_4$\} with respect to \{Co$_4$\}. Moreover \{Co$_4$\} displays not negligible spin-orbit related effects that could affect the spin lifetime in future antiferromagnetic spintronic applications. We highlight the necessity to account for these spin-orbit effects for a reliable description of these compounds.

physics.chem-ph↗

arXiv2021

PPCA: Privacy-preserving Principal Component Analysis Using Secure Multiparty Computation(MPC)

Privacy-preserving data mining has become an important topic. People have built several multi-party-computation (MPC)-based frameworks to provide theoretically guaranteed privacy, the poor performance of real-world algorithms have always been a challenge. Using Principal Component Analysis (PCA) as an example, we show that by considering the unique performance characters of the MPC platform, we can design highly effective algorithm-level optimizations, such as replacing expensive operators and batching up. We achieve about 200$\times$ performance boost over existing privacy-preserving PCA algorithms with the same level of privacy guarantee. Also, using real-world datasets, we show that by combining multi-party data, we can achieve better training results.

cs.CR↗

arXiv2021

RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents

Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value is not sufficient even with CTDE due to the randomness of rewards and the uncertainty in environments, which causes the failure of these methods to train coordinating agents in complex environments. To address these issues, we propose RMIX, a novel cooperative MARL method with the Conditional Value at Risk (CVaR) measure over the learned distributions of individuals' Q values. Specifically, we first learn the return distributions of individuals to analytically calculate CVaR for decentralized execution. Then, to handle the temporal nature of the stochastic outcomes during executions, we propose a dynamic risk level predictor for risk level tuning. Finally, we optimize the CVaR policies with CVaR values used to estimate the target in TD error during centralized training and the CVaR values are used as auxiliary local rewards to update the local distribution via Quantile Regression loss. Empirically, we show that our method significantly outperforms state-of-the-art methods on challenging StarCraft II tasks, demonstrating enhanced coordination and improved sample efficiency.

cs.LG↗

arXiv2020

Personalized Adaptive Meta Learning for Cold-start User Preference Prediction

A common challenge in personalized user preference prediction is the cold-start problem. Due to the lack of user-item interactions, directly learning from the new users' log data causes serious over-fitting problem. Recently, many existing studies regard the cold-start personalized preference prediction as a few-shot learning problem, where each user is the task and recommended items are the classes, and the gradient-based meta learning method (MAML) is leveraged to address this challenge. However, in real-world application, the users are not uniformly distributed (i.e., different users may have different browsing history, recommended items, and user profiles. We define the major users as the users in the groups with large numbers of users sharing similar user information, and other users are the minor users), existing MAML approaches tend to fit the major users and ignore the minor users. To address this cold-start task-overfitting problem, we propose a novel personalized adaptive meta learning approach to consider both the major and the minor users with three key contributions: 1) We are the first to present a personalized adaptive learning rate meta-learning approach to improve the performance of MAML by focusing on both the major and minor users. 2) To provide better personalized learning rates for each user, we introduce a similarity-based method to find similar users as a reference and a tree-based method to store users' features for fast search. 3) To reduce the memory usage, we design a memory agnostic regularizer to further reduce the space complexity to constant while maintain the performance. Experiments on MovieLens, BookCrossing, and real-world production datasets reveal that our method outperforms the state-of-the-art methods dramatically for both the minor and major users.

cs.IR↗

arXiv2020

TB2J: a python package for computing magnetic interaction parameters

We present TB2J, a Python package for the automatic computation of magnetic interactions, including exchange and Dzyaloshinskii-Moriya interactions, between atoms of magnetic crystals from the results of density functional calculations. The program is based on the Green's function method with the local rigid spin rotation treated as a perturbation. As input,the package uses the output of either Wannier90, which is interfaced with many density functional theory packages,or of codes based on localized orbitals. A minimal user input is needed, which allows for easy integration into high-throughput workflows. The package is open source under BSD 2-Clause license, available at https://github.com/mailhexu/TB2J.

cond-mat.mtrl-sci↗

arXiv2020

When the Differences in Frequency Domain are Compensated: Understanding and Defeating Modulated Replay Attacks on Automatic Speech Recognition

Automatic speech recognition (ASR) systems have been widely deployed in modern smart devices to provide convenient and diverse voice-controlled services. Since ASR systems are vulnerable to audio replay attacks that can spoof and mislead ASR systems, a number of defense systems have been proposed to identify replayed audio signals based on the speakers' unique acoustic features in the frequency domain. In this paper, we uncover a new type of replay attack called modulated replay attack, which can bypass the existing frequency domain based defense systems. The basic idea is to compensate for the frequency distortion of a given electronic speaker using an inverse filter that is customized to the speaker's transform characteristics. Our experiments on real smart devices confirm the modulated replay attacks can successfully escape the existing detection mechanisms that rely on identifying suspicious features in the frequency domain. To defeat modulated replay attacks, we design and implement a countermeasure named DualGuard. We discover and formally prove that no matter how the replay audio signals could be modulated, the replay attacks will either leave ringing artifacts in the time domain or cause spectrum distortion in the frequency domain. Therefore, by jointly checking suspicious features in both frequency and time domains, DualGuard can successfully detect various replay attacks including the modulated replay attacks. We implement a prototype of DualGuard on a popular voice interactive platform, ReSpeaker Core v2. The experimental results show DualGuard can achieve 98% accuracy on detecting modulated replay attacks.

cs.CR↗

arXiv2020

Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication

With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page often consists of different independent modules. The ranking policies of these modules are decided by different teams and optimized individually without cooperation, which might result in competition between modules. Thus, the global policy of the whole page could be sub-optimal. In this paper, we propose a novel multi-agent cooperative reinforcement learning approach with the restriction that different modules cannot communicate. Our contributions are three-fold. Firstly, inspired by a solution concept in game theory named correlated equilibrium, we design a signal network to promote cooperation of all modules by generating signals (vectors) for different modules. Secondly, an entropy-regularized version of the signal network is proposed to coordinate agents' exploration of the optimal global policy. Furthermore, experiments based on real-world e-commerce data demonstrate that our algorithm obtains superior performance over baselines.

cs.LG↗

arXiv2020

Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation

Online recommendation services recommend multiple commodities to users. Nowadays, a considerable proportion of users visit e-commerce platforms by mobile devices. Due to the limited screen size of mobile devices, positions of items have a significant influence on clicks: 1) Higher positions lead to more clicks for one commodity. 2) The 'pseudo-exposure' issue: Only a few recommended items are shown at first glance and users need to slide the screen to browse other items. Therefore, some recommended items ranked behind are not viewed by users and it is not proper to treat this kind of items as negative samples. While many works model the online recommendation as contextual bandit problems, they rarely take the influence of positions into consideration and thus the estimation of the reward function may be biased. In this paper, we aim at addressing these two issues to improve the performance of online mobile recommendation. Our contributions are four-fold. First, since we concern the reward of a set of recommended items, we model the online recommendation as a contextual combinatorial bandit problem and define the reward of a recommended set. Second, we propose a novel contextual combinatorial bandit method called UBM-LinUCB to address two issues related to positions by adopting the User Browsing Model (UBM), a click model for web search. Third, we provide a formal regret analysis and prove that our algorithm achieves sublinear regret independent of the number of items. Finally, we evaluate our algorithm on two real-world datasets by a novel unbiased estimator. An online experiment is also implemented in Taobao, one of the most popular e-commerce platforms in the world. Results on two CTR metrics show that our algorithm outperforms the other contextual bandit algorithms.

cs.LG↗

arXiv2020

Continual Learning from the Perspective of Compression

Connectionist models such as neural networks suffer from catastrophic forgetting. In this work, we study this problem from the perspective of information theory and define forgetting as the increase of description lengths of previous data when they are compressed with a sequentially learned model. In addition, we show that continual learning approaches based on variational posterior approximation and generative replay can be considered as approximations to two prequential coding methods in compression, namely, the Bayesian mixture code and maximum likelihood (ML) plug-in code. We compare these approaches in terms of both compression and forgetting and empirically study the reasons that limit the performance of continual learning methods based on variational posterior approximation. To address these limitations, we propose a new continual learning method that combines ML plug-in and Bayesian mixture codes.

cs.LG↗

arXiv2020

Learning Efficient Multi-agent Communication: An Information Bottleneck Approach

We consider the problem of the limited-bandwidth communication for multi-agent reinforcement learning, where agents cooperate with the assistance of a communication protocol and a scheduler. The protocol and scheduler jointly determine which agent is communicating what message and to whom. Under the limited bandwidth constraint, a communication protocol is required to generate informative messages. Meanwhile, an unnecessary communication connection should not be established because it occupies limited resources in vain. In this paper, we develop an Informative Multi-Agent Communication (IMAC) method to learn efficient communication protocols as well as scheduling. First, from the perspective of communication theory, we prove that the limited bandwidth constraint requires low-entropy messages throughout the transmission. Then inspired by the information bottleneck principle, we learn a valuable and compact communication protocol and a weight-based scheduler. To demonstrate the efficiency of our method, we conduct extensive experiments in various cooperative and competitive multi-agent tasks with different numbers of agents and different bandwidths. We show that IMAC converges faster and leads to efficient communication among agents under the limited bandwidth as compared to many baseline methods.

cs.AI↗

arXiv2020

Learning Behaviors with Uncertain Human Feedback

Human feedback is widely used to train agents in many domains. However, previous works rarely consider the uncertainty when humans provide feedback, especially in cases that the optimal actions are not obvious to the trainers. For example, the reward of a sub-optimal action can be stochastic and sometimes exceeds that of the optimal action, which is common in games or real-world. Trainers are likely to provide positive feedback to sub-optimal actions, negative feedback to the optimal actions and even do not provide feedback in some confusing situations. Existing works, which utilize the Expectation Maximization (EM) algorithm and treat the feedback model as hidden parameters, do not consider uncertainties in the learning environment and human feedback. To address this challenge, we introduce a novel feedback model that considers the uncertainty of human feedback. However, this incurs intractable calculus in the EM algorithm. To this end, we propose a novel approximate EM algorithm, in which we approximate the expectation step with the Gradient Descent method. Experimental results in both synthetic scenarios and two real-world scenarios with human participants demonstrate the superior performance of our proposed approach.

cs.AI↗

arXiv2020

Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving

Driving in a human-like manner is important for an autonomous vehicle to be a smart and predictable traffic participant. To achieve this goal, parameters of the motion planning module should be carefully tuned, which needs great effort and expert knowledge. In this study, a method of learning cost parameters of a motion planner from naturalistic driving data is proposed. The learning is achieved by encouraging the selected trajectory to approximate the human driving trajectory under the same traffic situation. The employed motion planner follows a widely accepted methodology that first samples candidate trajectories in the trajectory space, then select the one with minimal cost as the planned trajectory. Moreover, in addition to traditional factors such as comfort, efficiency and safety, the cost function is proposed to incorporate incentive of behavior decision like a human driver, so that both lane change decision and motion planning are coupled into one framework. Two types of lane incentive cost -- heuristic and learning based -- are proposed and implemented. To verify the validity of the proposed method, a data set is developed by using the naturalistic trajectory data of human drivers collected on the motorways in Beijing, containing samples of lane changes to the left and right lanes, and car followings. Experiments are conducted with respect to both lane change decision and motion planning, and promising results are achieved.

cs.CV↗

arXiv2020

Lattice-based designs possessing quasi-optimal separation distance on all projections

Experimental designs that spread out points apart from each other on projections are important for computer experiments when not necessarily all factors have substantial influence on the response. We provide a theoretical framework to generate designs that possess quasi-optimal separation distance on all of the projections and quasi-optimal fill distance on univariate margins. The key is to use special techniques to rotate certain lattices. One such type of design is densest packing-based maximum projection designs, which outperform existing types of space-filling designs in many scenarios. Computer code to generate these designs is provided in R package LatticeDesign.

math.ST↗

arXiv2019

PyProcar: A Python library for electronic structure pre/post-processing

The PyProcar Python package plots the band structure and the Fermi surface as a function of site and/or s,p,d,f - projected wavefunctions obtained for each $k$-point in the Brillouin zone and band in an electronic structure calculation. This can be performed on top of any electronic structure code, as long as the band and projection information is written in the PROCAR format, as done by the VASP and ABINIT codes. PyProcar can be easily modified to read other formats as well. This package is particularly suitable for understanding atomic effects into the band structure, Fermi surface, spin texture, etc. PyProcar can be conveniently used in a command line mode, where each one of the parameters define a plot property. In the case of Fermi-surfaces, the package is able to plot the surface with colors depending on other properties such as the electron velocity or spin projection. The mesh used to calculate the property does not need to be the same as the one used to obtain the Fermi surface. A file with a specific property evaluated for each $k$-point in a $k-$mesh and for each band can be used to project other properties such as electron-phonon mean path, Fermi velocity, electron effective mass, etc. Another existing feature refers to the band unfolding of supercell calculations into predefined unit cells.

cond-mat.mtrl-sci↗

arXiv2019

Task Agnostic Continual Learning via Meta Learning

While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided by continual learning, where the non-stationarity is imposed by a sequence of distinct tasks. Most methods in this space assume, however, the knowledge of task boundaries, and focus on alleviating catastrophic forgetting. In this work, we depart from this view and move the focus towards faster remembering -- i.e measuring how quickly the network recovers performance rather than measuring the network's performance without any adaptation. We argue that in many settings this can be more effective and that it opens the door to combining meta-learning and continual learning techniques, leveraging their complementary advantages. We propose a framework specific for the scenario where no information about task boundaries or task identity is given. It relies on a separation of concerns into what task is being solved and how the task should be solved. This framework is implemented by differentiating task specific parameters from task agnostic parameters, where the latter are optimized in a continual meta learning fashion, without access to multiple tasks at the same time. We showcase this framework in a supervised learning scenario and discuss the implication of the proposed formalism.

stat.ML↗

arXiv2019

Sliced Latin hypercube designs with arbitrary run sizes

Latin hypercube designs achieve optimal univariate stratifications and are useful for computer experiments. Sliced Latin hypercube designs are Latin hypercube designs that can be partitioned into smaller Latin hypercube designs. In this work, we give, to the best of our knowledge, the first construction of sliced Latin hypercube designs that allow arbitrarily chosen run sizes for the slices. We also provide an algorithm to reduce correlations of our proposed designs.

math.ST↗