arXiv subjects

Yang Yu

Publications and source records attributed to Yang Yu.

At least 397 records · Page 22Linked to original sources

arXiv2020

Binary Representaion for Non-binary LDPC Code with Decoder Design

The equivalent binary parity check matrices for the binary images of the cycle-free non-binary LDPC codes have numerous bit-level cycles. In this paper, we show how to transform these binary parity check matrices into their cycle-free forms. It is shown that the proposed methodology can be adopted not only for the binary images of non-binary LDPC codes but also for a large class of binary LDPC codes. Specifically, we present an extended $p$-reducible (EPR) LDPC code structure to eliminate the bit-level cycles. For the non-binary LDPC codes with short length symbol-level cycles, the EPR-LDPC codes can largely avoid the corresponding short length bit-level cycles. As to the decoding of the EPR-LDPC codes, we propose a hybrid hard-decision decoder and a hybrid parallel decoder for binary symmetric channel and binary input Gaussian channel, respectively. A simple code optimization algorithm for these binary decoders is also provided. Simulations show the comparative results and justify the advantages, i.e., better performance and lower decoding complexity, of the proposed binary constructions.

eess.SP↗

arXiv2020

Novelty-Prepared Few-Shot Classification

Few-shot classification algorithms can alleviate the data scarceness issue, which is vital in many real-world problems, by adopting models pre-trained from abundant data in other domains. However, the pre-training process was commonly unaware of the future adaptation to other concept classes. We disclose that a classically fully trained feature extractor can leave little embedding space for unseen classes, which keeps the model from well-fitting the new classes. In this work, we propose to use a novelty-prepared loss function, called self-compacting softmax loss (SSL), for few-shot classification. The SSL can prevent the full occupancy of the embedding space. Thus the model is more prepared to learn new classes. In experiments on CUB-200-2011 and mini-ImageNet datasets, we show that SSL leads to significant improvement of the state-of-the-art performance. This work may shed some light on considering the model capacity for few-shot classification tasks.

cs.LG↗

arXiv2020

Residual Bootstrap Exploration for Bandit Algorithms

In this paper, we propose a novel perturbation-based exploration method in bandit algorithms with bounded or unbounded rewards, called residual bootstrap exploration (\texttt{ReBoot}). The \texttt{ReBoot} enforces exploration by injecting data-driven randomness through a residual-based perturbation mechanism. This novel mechanism captures the underlying distributional properties of fitting errors, and more importantly boosts exploration to escape from suboptimal solutions (for small sample sizes) by inflating variance level in an \textit{unconventional} way. In theory, with appropriate variance inflation level, \texttt{ReBoot} provably secures instance-dependent logarithmic regret in Gaussian multi-armed bandits. We evaluate the \texttt{ReBoot} in different synthetic multi-armed bandits problems and observe that the \texttt{ReBoot} performs better for unbounded rewards and more robustly than \texttt{Giro} \cite{kveton2018garbage} and \texttt{PHE} \cite{kveton2019perturbed}, with comparable computational efficiency to the Thompson sampling method.

stat.ML↗

arXiv2020

Simultaneous Inference for Massive Data: Distributed Bootstrap

In this paper, we propose a bootstrap method applied to massive data processed distributedly in a large number of machines. This new method is computationally efficient in that we bootstrap on the master machine without over-resampling, typically required by existing methods \cite{kleiner2014scalable,sengupta2016subsampled}, while provably achieving optimal statistical efficiency with minimal communication. Our method does not require repeatedly re-fitting the model but only applies multiplier bootstrap in the master machine on the gradients received from the worker machines. Simulations validate our theory.

stat.ML↗

arXiv2020

Day-to-Day Dynamic Traffic Assignment with Imperfect Information, Bounded Rationality and Information Sharing

This paper presents a doubly dynamic day-to-day (DTD) traffic assignment model with simultaneous route-and-departure-time (SRDT) choices while incorporating incomplete and imperfect information as well as bounded rationality. Two SRDT choice models are proposed to incorporate imperfect travel information: One based on multinomial Logit (MNL) model and the other on sequential, mixed multinomial/nested Logit model. These two variants, serving as based models, are further extended with two features: bounded rationality (BR) and information sharing. BR is considered by incorporating the indifference band into the random utility component of the MNL model, forming a BR-based DTD stochastic model. A macroscopic model of travel information sharing is integrated into the DTD dynamics to account for the impact of incomplete information on travelers' SRDT choices. These DTD choice models are combined with within-day dynamics following the Lighthill-Whitham-Richards (LWR) fluid dynamic network loading model. Simulations on large-scale networks (Anaheim) illustrate the interactions between users' adaptive decision making and network conditions (including local disruption) with different levels of information availability and user behavior. Our findings highlight the need for modeling network transient and disequilibriated states, which are often overlooked in equilibrium-constrained network design and optimization. The MATLAB package and computational examples are available at https://github.com/DrKeHan/DTD

physics.soc-ph↗

arXiv2020

Identifying defect-related quantum emitters in monolayer WSe$_2$

Monolayer transition metal dichalcogenides have recently attracted great interests because the quantum dots embedded in monolayer can serve as optically active single photon emitters. Here, we provide an interpretation of the recombination mechanisms of these quantum emitters through polarization-resolved and magneto-optical spectroscopy at low temperature. Three types of defect-related quantum emitters in monolayer tungsten diselenide (WSe$_2$) are observed, with different exciton g factors of 2.02, 9.36 and unobservable Zeeman shift, respectively. The various magnetic response of the spatially localized excitons strongly indicate that the radiative recombination stems from the different transitions between defect-induced energy levels, valance and conduction bands. Furthermore, the different g factors and zero-field splittings of the three types of emitters strongly show that quantum dots embedded in monolayer have various types of confining potentials for localized excitons, resulting in electron-hole exchange interaction with a range of values in the presence of anisotropy. Our work further sheds light on the recombination mechanisms of defect-related quantum emitters and paves a way toward understanding the role of defects in single photon emitters in atomically thin semiconductors.

cond-mat.mes-hall↗

arXiv2020

Temporal-adaptive Hierarchical Reinforcement Learning

Hierarchical reinforcement learning (HRL) helps address large-scale and sparse reward issues in reinforcement learning. In HRL, the policy model has an inner representation structured in levels. With this structure, the reinforcement learning task is expected to be decomposed into corresponding levels with sub-tasks, and thus the learning can be more efficient. In HRL, although it is intuitive that a high-level policy only needs to make macro decisions in a low frequency, the exact frequency is hard to be simply determined. Previous HRL approaches often employed a fixed-time skip strategy or learn a terminal condition without taking account of the context, which, however, not only requires manual adjustments but also sacrifices some decision granularity. In this paper, we propose the \emph{temporal-adaptive hierarchical policy learning} (TEMPLE) structure, which uses a temporal gate to adaptively control the high-level policy decision frequency. We train the TEMPLE structure with PPO and test its performance in a range of environments including 2-D rooms, Mujoco tasks, and Atari games. The results show that the TEMPLE structure can lead to improved performance in these environments with a sequential adaptive high-level control.

cs.AI↗

arXiv2020

A Topology-Controlled Photonic Cavity Based on the Near-Conservation of the Valley Degree of Freedom

We demonstrate a novel path to localizing topologically-nontrivial photonic edge modes along their propagation direction. Our approach is based on the near-conservation of the photonic valley degree of freedom associated with valley-polarized edge states. When the edge state is reflected from a judiciously oriented mirror, its optical energy is localized at the mirror surface because of an extended time delay required for valley-index-flipping. The degree of energy localization at the resulting topology-controlled photonic cavity (TCPC) is determined by the valley-flipping time, which is in turn controlled by the geometry of the mirror. Intuitive analytic descriptions of the "leaky" and closed TCPCs are presented, and two specific designs--one for the microwave and the other for the optical spectral ranges--are proposed.

cond-mat.mes-hall↗

arXiv2020

Diabolical Points in Coupled Active Cavities with Quantum Emitters

In single microdisks, embedded active emitters intrinsically affect the cavity mode of microdisks, which results in a trivial symmetric backscattering and a low controllability. Here we propose a macroscopical control of the backscattering direction by optimizing the cavity size. The signature of positive and negative backscattering directions in each single microdisk is confirmed with two strongly coupled microdisks. Furthermore, the diabolical points are achieved at the resonance of two microdisks, which agrees well with the theoretical calculations considering backscattering directions. The diabolical points in active optical structures pave a way to implement quantum information processing with geometric phase in quantum photonic networks.

physics.optics↗

arXiv2019

Storage Control for Carbon Emission Reduction: Opportunities and Challenges

Storage is vital to power systems as it provides the urgently needed flexibility to the system. Meanwhile, it can contribute more than flexibility. In this paper, we study the possibility of utilizing storage system for carbon emission reduction. The opportunity arises due to the pending implementation of carbon tax throughout the world. Without the right incentive, most system operators have to dispatch the generators according to the merit order of the fuel costs, without any control for carbon emissions. However, we submit that storage may provide necessary flexibility in carbon emission reduction even without carbon tax. We identify the non-convex structure to conduct storage control for this task and propose an easy to implement dynamic programming algorithm to investigate the value of storage in carbon emission reduction.

eess.SY↗

arXiv2019

Robust Data-driven Profile-based Pricing Schemes

To enable an efficient electricity market, a good pricing scheme is of vital importance. Among many practical schemes, customized pricing is commonly believed to be able to best exploit the flexibility in the demand side. However, due to the large volume of consumers in the electricity sector, such task is simply too overwhelming. In this paper, we first compare two data driven schemes: one based on load profile and the other based on user's marginal system cost. Vulnerability analysis shows that the former approach may lead to loopholes in the electricity market while the latter one is able to guarantee the robustness, which yields our robust data-driven pricing scheme. Although k-means clustering is in general NP-hard, surprisingly, by exploiting the structure of our problem, we design an efficient yet optimal k-means clustering algorithm to implement our proposed scheme.

cs.CE↗

arXiv2019

Optimal Electricity Storage Sharing Mechanism for Single Peaked Time-of-Use Pricing Scheme

Sharing economy has disrupted many industries. We foresee that electricity storage systems could be the enabler for sharing economy in electricity sector, though its implementation is a delicate task. Unlike in the 2-tier Time-of-Use (ToU) pricing, where greedy arbitrage policy can achieve the maximal electricity bill savings, most existing ToU schemes consist of multiple tiers, which renders the arbitrage challenging. The difficulty comes from the hedging against multiple tiers and the coupling between the decisions across the day. In this work, we focus on designing the energy sharing mechanism for single peaked ToU scheme. To solve the problem, we identify that it suffices to understand the arbitrage policies for two forms of 3-tier ToU schemes. We submit that under mild conditions, the sharing mechanism yields a unique equilibrium, which supports the maximal social welfare.

eess.SY↗

arXiv2019

Value of Storage for Renewable Portfolio Standard

The ambitious targets for renewable energy penetration warrant huge flexibility in the power system. Such flexibility does not come free. In this paper, we examine the possibility of utilizing storage systems for achieving high renewable energy penetration, and identify the trade-off between providing flexibility and arbitrage against real-time prices. More precisely, we investigate the relationship among the operation cost, storage capacity, and the renewable penetration level. This illustrates the value of storage as well as the true cost induced by the high renewable penetration targets.

eess.SY↗

arXiv2019

A Data-driven Storage Control Framework for Dynamic Pricing

Dynamic pricing is both an opportunity and a challenge to the demand side. It is an opportunity as it better reflects the real time market conditions and hence enables an active demand side. However, demand's active participation does not necessarily lead to benefits. The challenge conventionally comes from the limited flexible resources and limited intelligent devices in demand side. The decreasing cost of storage system and the widely deployed smart meters inspire us to design a data-driven storage control framework for dynamic prices. We first establish a stylized model by assuming the knowledge and structure of dynamic price distributions, and design the optimal storage control policy. Based on Gaussian Mixture Model, we propose a practical data-driven control framework, which helps relax the assumptions in the stylized model. Numerical studies illustrate the remarkable performance of the proposed data-driven framework.

eess.SY↗

arXiv2019

Improving Fictitious Play Reinforcement Learning with Expanding Models

Fictitious play with reinforcement learning is a general and effective framework for zero-sum games. However, using the current deep neural network models, the implementation of fictitious play faces crucial challenges. Neural network model training employs gradient descent approaches to update all connection weights, and thus is easy to forget the old opponents after training to beat the new opponents. Existing approaches often maintain a pool of historical policy models to avoid the forgetting. However, learning to beat a pool in stochastic games, i.e., a wide distribution over policy models, is either sample-consuming or insufficient to exploit all models with limited amount of samples. In this paper, we propose a learning process with neural fictitious play to alleviate the above issues. We train a single model as our policy model, which consists of sub-models and a selector. Everytime facing a new opponent, the model is expanded by adding a new sub-model, where only the new sub-model is updated instead of the whole model. At the same time, the selector is also updated to mix up the new sub-model with the previous ones at the state-level, so that the model is maintained as a behavior strategy instead of a wide distribution over policy models. Experiments on Kuhn poker, a grid-world Treasure Hunting game, and Mini-RTS environments show that the proposed approach alleviates the forgetting problem, and consequently improves the learning efficiency and the robustness of neural fictitious play.

cs.LG↗

arXiv2019

Realization of Superadiabatic Two-qubit Gates Using Parametric Modulation in Superconducting Circuits

Fast robust two-qubit gate operation with low susceptibility to crosstalk are the key to scalable quantum information processing. Parametrically driven gate is inherently insensitive to crosstalk while superadiabatic control can speed up the gate without losing accuracy. We propose and experimentally implement superadiabatic two-qubit gates using parametric modulation on superconducting quantum circuits. Our results demonstrate the preservation of adiabaticity at a gate speed close to the quantum limit, in addition to robustness against control instability. We demonstrate a CZ gate with error rate of 5.8$\%$, limited largely by qubit decoherence, promising future improvement and scalable implementation.

quant-ph↗

arXiv2019

Vulnerability Analysis for Data Driven Pricing Schemes

Data analytics and machine learning techniques are being rapidly adopted into the power system, including power system control as well as electricity market design. In this paper, from an adversarial machine learning point of view, we examine the vulnerability of data-driven electricity market design. More precisely, we follow the idea that consumer's load profile should uniquely determine its electricity rate, which yields a clustering oriented pricing scheme. We first identify the strategic behaviors of malicious users by defining a notion of disguising. Based on this notion, we characterize the sensitivity zones to evaluate the percentage of malicious users in each cluster. Based on a thorough cost benefit analysis, we conclude with the vulnerability analysis.

cs.LG↗

arXiv2019

Hot Polarons with Trapped Excitons and Octahedra-Twist Phonons in CH3NH3PbBr3 Hybrid Perovskite Nanowires

Hybrid Perovskites have shown a great potential for applications in photovoltaics and light-emitting devices with high efficiency. Interaction between defect-induced trapped excitons and phonons plays an important role in understanding the emerging phenomena for such an excellent figure-of-merit. Here we demonstrate hot polarons with narrow linewidth in $\mathrm{CH_{3}NH_{3}PbBr_{3}}$ nanowires, which originate from the interaction between trapped excitons and octahedra-twist phonons. The observation of hot polarons in photoluminescence without gain methods indicates the large interaction strength between excitons and phonons. The multiple hot polarons are further confirmed by magneto-optical spectra with a Zeeman splitting of the trapped excitons and a phonon energy increase with diamagnetic effect. Furthermore, the phonons participating in the interaction are demonstrated to be the octahedra-twist vibrations which are transverse optical phonons, while the interaction between trapped excitons and longitudinal optical phonons is weak. Our work demonstrates that trapped excitons in perovskites prefer to interact with transverse rather than longitudinal optical phonons. Since bulk materials usually interact with longitudinal optical phonons, this result provides a physical explanation of the high tolerance of defects in perovskites.

cond-mat.mes-hall↗