arXiv subjects

Bo Ji

Publications and source records attributed to Bo Ji.

At least 55 records · Page 3Linked to original sources

arXiv2024

Manipulating multiple optical parametric processes in photonic topological insulators

Topological quantum optics, an emerging area of study, holds the potential to bring about substantial enhancements for integrated quantum devices. Here we propose integrated topological quantum devices performing various functions including optical parametric amplification, frequency division, and frequency entangled biphoton generation. We show two distinct edge modes corresponding to different frequency ranges in both sandwich kagome and honeycomb topological designs that emulate the quantum valley Hall effect. These two topological edge modes enable two types of optical parametric processes through four-wave mixing, specifically inter-band and intra-band cases. The devices emulating photonic valley-Hall insulators allow the frequency division of two transverse modes, and furthermore, enable the separation of two quantum functionalities - optical parametric amplification and frequency entangled biphoton state generation. More importantly, the parametric processes are inborn topological protected, showing robustness against sharp bends and disorders. Our proposal significantly widens the possibilities for robust, multifunctional topological quantum devices on-chip, which may find applications in quantum information processing.

physics.optics↗

arXiv2023

Securing Bystander Privacy in Mixed Reality While Protecting the User Experience

The modern Mixed Reality devices that make the Metaverse viable require vast information about the physical world and can also violate the privacy of unsuspecting or unwilling bystanders in their vicinity. In this article, we provide an introduction to the problem, existing solutions, and avenues for future research.

cs.CY↗

arXiv2023

On-chip topological transport of optical frequency combs in silicon-based valley photonic crystals

The generation and control of optical frequency combs in integrated photonic systems enables complex, high-controllable, and large-scale devices. In parallel, harnessing topological physics in multipartite systems has allowed them with compelling features such as robustness against fabrication imperfections. Here we experimentally demonstrate on-chip topological transport for optical frequency combs at telecommunication wavelengths, both in classical and nonclassical domains. We access both the quantum frequency combs and dissipative Kerr soliton combs with a micro-resonator. The quantum frequency comb, that is, a coherent superposition of multiple frequency modes, is proven to be a frequency-entangled qudit state. We also show that dissipative Kerr soliton combs are highly coherent and mode-locked due to the collective coherence or self-organization of solitons. Moreover, the valley kink states allow both quantum frequency combs and dissipative Kerr soliton combs with robustness against sharp bends. Our topologically protected optical frequency combs could enable the inherent robustness in integrated complex photonic systems.

physics.optics↗

arXiv2023

Single-flux-quantum-based Qubit Control with Tunable Driving Strength

Single-flux-quantum (SFQ) circuits have great potential in building cryogenic quantum-classical interfaces for scaling up superconducting quantum processors. SFQ-based quantum gates have been designed and realized. However, current control schemes are difficult to tune the driving strength to qubits, which restricts the gate length and usually induces leakage to unwanted levels. In this study, we design the scheme and corresponding pulse generator circuit to continuously adjust the driving strength by coupling SFQ pulses with variable intervals. This scheme not only provides a way to adjust the SFQ-based gate length, but also proposes the possibility to tune the driving strength envelope. Simulations show that our scheme can suppress leakage to unwanted levels and reduce the error of SFQ-based Clifford gates by more than an order of magnitude.

quant-ph↗

arXiv2023

Understanding the Role of Feedback in Online Learning with Switching Costs

In this paper, we study the role of feedback in online learning with switching costs. It has been shown that the minimax regret is $\widetildeΘ(T^{2/3})$ under bandit feedback and improves to $\widetildeΘ(\sqrt{T})$ under full-information feedback, where $T$ is the length of the time horizon. However, it remains largely unknown how the amount and type of feedback generally impact regret. To this end, we first consider the setting of bandit learning with extra observations; that is, in addition to the typical bandit feedback, the learner can freely make a total of $B_{\mathrm{ex}}$ extra observations. We fully characterize the minimax regret in this setting, which exhibits an interesting phase-transition phenomenon: when $B_{\mathrm{ex}} = O(T^{2/3})$, the regret remains $\widetildeΘ(T^{2/3})$, but when $B_{\mathrm{ex}} = Ω(T^{2/3})$, it becomes $\widetildeΘ(T/\sqrt{B_{\mathrm{ex}}})$, which improves as the budget $B_{\mathrm{ex}}$ increases. To design algorithms that can achieve the minimax regret, it is instructive to consider a more general setting where the learner has a budget of $B$ total observations. We fully characterize the minimax regret in this setting as well and show that it is $\widetildeΘ(T/\sqrt{B})$, which scales smoothly with the total budget $B$. Furthermore, we propose a generic algorithmic framework, which enables us to design different learning algorithms that can achieve matching upper bounds for both settings based on the amount and type of feedback. One interesting finding is that while bandit feedback can still guarantee optimal regret when the budget is relatively limited, it no longer suffices to achieve optimal regret when the budget is relatively large.

cs.LG↗

arXiv2023

$Radar^2$: Passive Spy Radar Detection and Localization using COTS mmWave Radar

Millimeter-wave (mmWave) radars have found applications in a wide range of domains, including human tracking, health monitoring, and autonomous driving, for their unobtrusive nature and high range accuracy. These capabilities, however, if used for malicious purposes, could also result in serious security and privacy issues. For example, a user's daily life could be secretly monitored by a spy radar. Hence, there is a strong urge to develop systems that can detect and locate such spy radars. In this paper, we propose $Radar^2$, a practical system for passive spy radar detection and localization using a single commercial off-the-shelf (COTS) mmWave radar. Specifically, we propose a novel \textit{Frequency Component Detection} method to detect the existence of mmWave signals, distinguish between mmWave radar and WiGig signals using a waveform classifier based on a convolutional neural network (CNN), and localize spy radars using triangulation based on the detector's observations at multiple anchor points. Not only does $Radar^2$ work for different types of mmWave radar, but it can also detect and localize multiple radars simultaneously. Finally, we performed extensive experiments to evaluate the effectiveness and robustness of $Radar^2$ in various settings. Our evaluation results show that the radar detection rate is above 96$\%$ and the localization error is within 0.3m. The results also reveal that $Radar^2$ is robust against various environmental factors (e.g., room layout and human activities).

eess.SP↗

arXiv2023

GazePair: Efficient Pairing of Augmented Reality Devices Using Gaze Tracking

As Augmented Reality (AR) devices become more prevalent and commercially viable, the need for quick, efficient, and secure schemes for pairing these devices has become more pressing. Current methods to securely exchange holograms require users to send this information through large data centers, creating security and privacy concerns. Existing techniques to pair these devices on a local network and share information fall short in terms of usability and scalability. These techniques either require hardware not available on AR devices, intricate physical gestures, removal of the device from the head, do not scale to multiple pairing partners, or rely on methods with low entropy to create encryption keys. To that end, we propose a novel pairing system, called GazePair, that improves on all existing local pairing techniques by creating an efficient, effective, and intuitive pairing protocol. GazePair uses eye gaze tracking and a spoken key sequence cue (KSC) to generate identical, independently generated symmetric encryption keys with 64 bits of entropy. GazePair also achieves improvements in pairing success rates and times over current methods. Additionally, we show that GazePair can extend to multiple users. Finally, we assert that GazePair can be used on any Mixed Reality (MR) device equipped with eye gaze tracking.

cs.CR↗

arXiv2023

A Worst-Case Approximate Analysis of Peak Age-of-Information Via Robust Queueing Approach

A new timeliness metric, called Age-of-Information (AoI), has recently attracted a lot of research interests for real-time applications with information updates. It has been extensively studied for various queueing models based on the probabilistic approaches, where the analyses heavily depend on the properties of specific distributions (e.g., the memoryless property of the exponential distribution or the i.i.d. assumption). In this work, we take an alternative new approach, the robust queueing approach, to analyze the Peak Age-of-Information (PAoI). Specifically, we first model the uncertainty in the stochastic arrival and service processes using uncertainty sets. This enables us to approximate the expected PAoI performance for very general arrival and service processes, including those exhibiting heavy-tailed behaviors or correlations, where traditional probabilistic approaches cannot be applied. We then derive a new bound on the PAoI in the single-source single-server setting. Furthermore, we generalize our analysis to two-source single-server systems with symmetric arrivals, which involves new challenges (e.g., the service times of the updates from two sources are coupled in one single uncertainty set). Finally, through numerical experiments, we show that our new bounds provide a good approximation for the expected PAoI. Compared to some well-known bounds in the literature (e.g., one based on Kingman's bound under the i.i.d. assumption) that tends to be inaccurate under light load, our new approximation is accurate under both light and high loads, both of which are critical scenarios for the AoI performance.

cs.IT↗

arXiv2023

(Private) Kernelized Bandits with Distributed Biased Feedback

In this paper, we study kernelized bandits with distributed biased feedback. This problem is motivated by several real-world applications (such as dynamic pricing, cellular network configuration, and policy making), where users from a large population contribute to the reward of the action chosen by a central entity, but it is difficult to collect feedback from all users. Instead, only biased feedback (due to user heterogeneity) from a subset of users may be available. In addition to such partial biased feedback, we are also faced with two practical challenges due to communication cost and computation complexity. To tackle these challenges, we carefully design a new \emph{distributed phase-then-batch-based elimination (\texttt{DPBE})} algorithm, which samples users in phases for collecting feedback to reduce the bias and employs \emph{maximum variance reduction} to select actions in batches within each phase. By properly choosing the phase length, the batch size, and the confidence width used for eliminating suboptimal actions, we show that \texttt{DPBE} achieves a sublinear regret of $\tilde{O}(T^{1-α/2}+\sqrt{γ_T T})$, where $α\in (0,1)$ is the user-sampling parameter one can tune. Moreover, \texttt{DPBE} can significantly reduce both communication cost and computation complexity in distributed kernelized bandits, compared to some variants of the state-of-the-art algorithms (originally developed for standard kernelized bandits). Furthermore, by incorporating various \emph{differential privacy} models (including the central, local, and shuffle models), we generalize \texttt{DPBE} to provide privacy guarantees for users participating in the distributed learning process. Finally, we conduct extensive simulations to validate our theoretical results and evaluate the empirical performance.

cs.LG↗

arXiv2023

Towards Optimal Tradeoff Between Data Freshness and Update Cost in Information-update Systems

In this paper, we consider a discrete-time information-update system, where a service provider can proactively retrieve information from the information source to update its data and users query the data at the service provider. One example is crowdsensing-based applications. In order to keep users satisfied, the application desires to provide users with fresh data, where the freshness is measured by the Age-of-Information (AoI). However, maintaining fresh data requires the application to update its database frequently, which incurs an update cost (e.g., incentive payment). Hence, there exists a natural tradeoff between the AoI and the update cost at the service provider who needs to make update decisions. To capture this tradeoff, we formulate an optimization problem with the objective of minimizing the total cost, which is the sum of the staleness cost (which is a function of the AoI) and the update cost. Then, we provide two useful guidelines for the design of efficient update policies. Following these guidelines and assuming that the aggregated request arrival process is Bernoulli, we prove that there exists a threshold-based policy that is optimal among all online policies and thus focus on the class of threshold-based policies. Furthermore, we derive the closed-form formula for computing the long-term average cost under any threshold-based policy and obtain the optimal threshold. Finally, we perform extensive simulations using both synthetic data and real traces to verify our theoretical results and demonstrate the superior performance of the optimal threshold-based policy compared with several baseline policies.

cs.IT↗

arXiv2022

FSCNN: A Fast Sparse Convolution Neural Network Inference System

Convolution neural networks (CNNs) have achieved remarkable success, but typically accompany high computation cost and numerous redundant weight parameters. To reduce the FLOPs, structure pruning is a popular approach to remove the entire hidden structures via introducing coarse-grained sparsity. Meanwhile, plentiful pruning works leverage fine-grained sparsity instead (sparsity are randomly distributed), whereas their sparse models lack special designed computing library for potential speedup. In this technical report, we study and present an efficient convolution neural network inference system to accelerate its forward pass by utilizing the fine-grained sparsity of compressed CNNs. Our developed FSCNN is established based on a set of specialized designed sparse data structures, operators and associated algorithms. Experimentally, we validate that FSCNN outperforms standard deep learning library PyTorch on popular CNN architectures such as VGG16 if sufficiently high sparsity exhibits. However, due to the contiguity issue of sparse operators, FSCNN is typically not comparable with highly optimized dense operator. Therefore, coarse-grained (structured) sparsity is our recommendation for generic model compression.

cs.CV↗

arXiv2022

Minute ventilation measurement using Plethysmographic Imaging and lighting parameters

Breathing disorders such as sleep apnea is a critical disorder that affects a large number of individuals due to the insufficient capacity of the lungs to contain/exchange oxygen and carbon dioxide to ensure that the body is in the stable state of homeostasis. Respiratory Measurements such as minute ventilation can be used in correlation with other physiological measurements such as heart rate and heart rate variability for remote monitoring of health and detecting symptoms of such breathing related disorders. In this work, we formulate a deep learning based approach to measure remote ventilation on a private dataset. The dataset will be made public upon acceptance of this work. We use two versions of a deep neural network to estimate the minute ventilation from data streams obtained through wearable heart rate and respiratory devices. We demonstrate that the simple design of our pipeline - which includes lightweight deep neural networks - can be easily incorporate into real time health monitoring systems.

cs.LG↗

arXiv2022

Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution

In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that successfully balance the trade-off rely on fusing results from separately trained models with ad-hoc post-processing. In this paper, we propose a novel super-resolution model with a low-frequency constraint (LFc-SR), which balances the objective and perceptual quality through a single model and yields super-resolved images with high PSNR and perceptual scores. We further introduce an ADMM-based alternating optimization method for the non-trivial learning of the constrained model. Experiments showed that our method, without cumbersome post-processing procedures, achieved the state-of-the-art performance. The code is available at https://github.com/Yuehan717/PDASR.

eess.IV↗

arXiv2022

On Scheduling Ring-All-Reduce Learning Jobs in Multi-Tenant GPU Clusters with Communication Contention

Powered by advances in deep learning (DL) techniques, machine learning and artificial intelligence have achieved astonishing successes. However, the rapidly growing needs for DL also led to communication- and resource-intensive distributed training jobs for large-scale DL training, which are typically deployed over GPU clusters. To sustain the ever-increasing demand for DL training, the so-called "ring-all-reduce" (RAR) technologies have recently emerged as a favorable computing architecture to efficiently process network communication and computation load in GPU clusters. The most salient feature of RAR is that it removes the need for dedicated parameter servers, thus alleviating the potential communication bottleneck. However, when multiple RAR-based DL training jobs are deployed over GPU clusters, communication bottlenecks could still occur due to contentions between DL training jobs. So far, there remains a lack of theoretical understanding on how to design contention-aware resource scheduling algorithms for RAR-based DL training jobs, which motivates us to fill this gap in this work. Our main contributions are three-fold: i) We develop a new analytical model that characterizes both communication overhead related to the worker distribution of the job and communication contention related to the co-location of different jobs; ii) Based on the proposed analytical model, we formulate the problem as a non-convex integer program to minimize the makespan of all RAR-based DL training jobs. To address the unique structure in this problem that is not amenable for optimization algorithm design, we reformulate the problem into an integer linear program that enables provable approximation algorithm design called SJF-BCO (Smallest Job First with Balanced Contention and Overhead); and iii) We conduct extensive experiments to show the superiority of SJF-BCO over existing schedulers.

cs.DC↗

arXiv2022

A Closer Look at Branch Classifiers of Multi-exit Architectures

Multi-exit architectures consist of a backbone and branch classifiers that offer shortened inference pathways to reduce the run-time of deep neural networks. In this paper, we analyze different branching patterns that vary in their allocation of computational complexity for the branch classifiers. Constant-complexity branching keeps all branches the same, while complexity-increasing and complexity-decreasing branching place more complex branches later or earlier in the backbone respectively. Through extensive experimentation on multiple backbones and datasets, we find that complexity-decreasing branches are more effective than constant-complexity or complexity-increasing branches, which achieve the best accuracy-cost trade-off. We investigate a cause by using knowledge consistency to probe the effect of adding branches onto a backbone. Our findings show that complexity-decreasing branching yields the least disruption to the feature abstraction hierarchy of the backbone, which explains the effectiveness of the branching patterns.

cs.CV↗

arXiv2022

Waiting but not Aging: Optimizing Information Freshness Under the Pull Model

The Age-of-Information is an important metric for investigating the timeliness performance in information-update systems. In this paper, we study the AoI minimization problem under a new Pull model with replication schemes, where a user proactively sends a replicated request to multiple servers to "pull" the information of interest. Interestingly, we find that under this new Pull model, replication schemes capture a novel tradeoff between different values of the AoI across the servers (due to the random updating processes) and different response times across the servers, which can be exploited to minimize the expected AoI at the user's side. Specifically, assuming Poisson updating process for the servers and exponentially distributed response time, we derive a closed-form formula for computing the expected AoI and obtain the optimal number of responses to wait for to minimize the expected AoI. Then, we extend our analysis to the setting where the user aims to maximize the AoI-based utility, which represents the user's satisfaction level with respect to the freshness of the received information. Furthermore, we consider a more realistic scenario where the user has no prior knowledge of the system. In this case, we reformulate the utility maximization problem as a stochastic Multi-Armed Bandit problem with side observations and leverage a special linear structure of side observations to design learning algorithms with improved performance guarantees. Finally, we conduct extensive simulations to elucidate our theoretical results and compare the performance of different algorithms. Our findings reveal that under the Pull model, waiting does not necessarily lead to aging; waiting for more than one response can often significantly reduce the AoI and improve the AoI-based utility in most scenarios.

cs.NI↗

arXiv2022

Toward Efficient Online Scheduling for Distributed Machine Learning Systems

Recent years have witnessed a rapid growth of distributed machine learning (ML) frameworks, which exploit the massive parallelism of computing clusters to expedite ML training. However, the proliferation of distributed ML frameworks also introduces many unique technical challenges in computing system design and optimization. In a networked computing cluster that supports a large number of training jobs, a key question is how to design efficient scheduling algorithms to allocate workers and parameter servers across different machines to minimize the overall training time. Toward this end, in this paper, we develop an online scheduling algorithm that jointly optimizes resource allocation and locality decisions. Our main contributions are three-fold: i) We develop a new analytical model that considers both resource allocation and locality; ii) Based on an equivalent reformulation and observations on the worker-parameter server locality configurations, we transform the problem into a mixed packing and covering integer program, which enables approximation algorithm design; iii) We propose a meticulously designed approximation algorithm based on randomized rounding and rigorously analyze its performance. Collectively, our results contribute to the state of the art of distributed ML system optimization and algorithm design.

cs.DC↗

arXiv2022

Multi-Scale Memory-Based Video Deblurring

Video deblurring has achieved remarkable progress thanks to the success of deep neural networks. Most methods solve for the deblurring end-to-end with limited information propagation from the video sequence. However, different frame regions exhibit different characteristics and should be provided with corresponding relevant information. To achieve fine-grained deblurring, we designed a memory branch to memorize the blurry-sharp feature pairs in the memory bank, thus providing useful information for the blurry query input. To enrich the memory of our memory bank, we further designed a bidirectional recurrency and multi-scale strategy based on the memory bank. Experimental results demonstrate that our model outperforms other state-of-the-art methods while keeping the model complexity and inference time low. The code is available at https://github.com/jibo27/MemDeblur.

eess.IV↗