Searcharxiv⌕ Search

arXiv subjects

Jian Huang

Publications and source records attributed to Jian Huang.

At least 127 records · Page 7Linked to original sources
arXiv2024

DisGNet: A Distance Graph Neural Network for Forward Kinematics Learning of Gough-Stewart Platform

In this paper, we propose a graph neural network, DisGNet, for learning the graph distance matrix to address the forward kinematics problem of the Gough-Stewart platform. DisGNet employs the k-FWL algorithm for message-passing, providing high expressiveness with a small parameter count, making it suitable for practical deployment. Additionally, we introduce the GPU-friendly Newton-Raphson method, an efficient parallelized optimization method executed on the GPU to refine DisGNet's output poses, achieving ultra-high-precision pose. This novel two-stage approach delivers ultra-high precision output while meeting real-time requirements. Our results indicate that on our dataset, DisGNet can achieves error accuracys below 1mm and 1deg at 79.8\% and 98.2\%, respectively. As executed on a GPU, our two-stage method can ensure the requirement for real-time computation. Codes are released at https://github.com/FLAMEZZ5201/DisGNet.

cs.RO↗
arXiv2023

Dark-Mode Theorems for Quantum Networks

We propose and prove two theorems for determining the number of dark modes in linear two-component quantum networks composed of two types of bosonic modes. This is achieved by diagonalizing the two sub-networks of the same type of modes, mapping the networks to either a standard or a thick arrowhead matrix, and analyzing the linear dependence and independence between the column vectors associated with degenerate normal modes in the coupling matrix. We confirm the two theorems by checking the simultaneous ground-state cooling of the mechanical modes in linearized optomechanical networks. These results also work for linear fermionic networks and other networks described by quadratic coupled-mode Hamiltonian. The present method can be extended to study the dark-state effect in driven atom systems and to construct large decoherence-free subspaces for processing quantum information. This work will initiate the studies on dynamical, transport, and statistical properties of linear networks with decoupled subspaces.

quant-ph↗
arXiv2023

G10: Enabling An Efficient Unified GPU Memory and Storage Architecture with Smart Tensor Migrations

To break the GPU memory wall for scaling deep learning workloads, a variety of architecture and system techniques have been proposed recently. Their typical approaches include memory extension with flash memory and direct storage access. However, these techniques still suffer from suboptimal performance and introduce complexity to the GPU memory management, making them hard to meet the scalability requirement of deep learning workloads today. In this paper, we present a unified GPU memory and storage architecture named G10 driven by the fact that the tensor behaviors of deep learning workloads are highly predictable. G10 integrates the host memory, GPU memory, and flash memory into a unified memory space, to scale the GPU memory capacity while enabling transparent data migrations. Based on this unified GPU memory and storage architecture, G10 utilizes compiler techniques to characterize the tensor behaviors in deep learning workloads. Therefore, it can schedule data migrations in advance by considering the available bandwidth of flash memory and host memory. The cooperative mechanism between deep learning compilers and the unified memory architecture enables G10 to hide data transfer overheads in a transparent manner. We implement G10 based on an open-source GPU simulator. Our experiments demonstrate that G10 outperforms state-of-the-art GPU memory solutions by up to 1.75$\times$, without code modifications to deep learning workloads. With the smart data migration mechanism, G10 can reach 90.3\% of the performance of the ideal case assuming unlimited GPU memory.

cs.AR↗
arXiv2023

RackBlox: A Software-Defined Rack-Scale Storage System with Network-Storage Co-Design

Software-defined networking (SDN) and software-defined flash (SDF) have been serving as the backbone of modern data centers. They are managed separately to handle I/O requests. At first glance, this is a reasonable design by following the rack-scale hierarchical design principles. However, it suffers from suboptimal end-to-end performance, due to the lack of coordination between SDN and SDF. In this paper, we co-design the SDN and SDF stack by redefining the functions of their control plane and data plane, and splitting up them within a new architecture named RackBlox. RackBlox decouples the storage management functions of flash-based solid-state drives (SSDs), and allow the SDN to track and manage the states of SSDs in a rack. Therefore, we can enable the state sharing between SDN and SDF, and facilitate global storage resource management. RackBlox has three major components: (1) coordinated I/O scheduling, in which it dynamically adjusts the I/O scheduling in the storage stack with the measured and predicted network latency, such that it can coordinate the effort of I/O scheduling across the network and storage stack for achieving predictable end-to-end performance; (2) coordinated garbage collection (GC), in which it will coordinate the GC activities across the SSDs in a rack to minimize their impact on incoming I/O requests; (3) rack-scale wear leveling, in which it enables global wear leveling among SSDs in a rack by periodically swapping data, for achieving improved device lifetime for the entire rack. We implement RackBlox using programmable SSDs and switch. Our experiments demonstrate that RackBlox can reduce the tail latency of I/O requests by up to 5.8x over state-of-the-art rack-scale storage systems.

cs.OS↗
arXiv2023

Lipschitz Transport Maps via the Follmer Flow

Inspired by the construction of the F{ö}llmer process, we construct a unit-time flow on the Euclidean space, termed the F{ö}llmer flow, whose flow map at time 1 pushes forward a standard Gaussian measure onto a general target measure. We study the well-posedness of the F{ö}llmer flow and establish the Lipschitz property of the flow map at time 1. We apply the Lipschitz mapping to several rich classes of probability measures on deriving dimension-free functional inequalities and concentration inequalities for the empirical measure.

math.PR↗
arXiv2023

Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models

We propose a general approach to evaluating the performance of robust estimators based on adversarial losses under misspecified models. We first show that adversarial risk is equivalent to the risk induced by a distributional adversarial attack under certain smoothness conditions. This ensures that the adversarial training procedure is well-defined. To evaluate the generalization performance of the adversarial estimator, we study the adversarial excess risk. Our proposed analysis method includes investigations on both generalization error and approximation error. We then establish non-asymptotic upper bounds for the adversarial excess risk associated with Lipschitz loss functions. In addition, we apply our general results to adversarial training for classification and regression problems. For the quadratic loss in nonparametric regression, we show that the adversarial excess risk bound can be improved over those for a general loss.

stat.ML↗
arXiv2023

Controllable generation of mechanical quadrature squeezing via dark-mode engineering in cavity optomechanics

Quantum squeezing is an important resource in modern quantum technologies, such as quantum precision measurement and continuous-variable quantum information processing. The generation of squeezed states of mechanical modes is a significant task in cavity optomechanics. Motivated by recent interest in multimode optomechanics, it becomes an interesting topic to create quadrature squeezing in multiple mechanical resonators. However, in the multiple-degenerate-mechanical-mode optomechanical systems, the dark-mode effect strongly suppresses the quantum effects in mechanical modes. Here we study the generation of mechanical squeezing in a two-mechanical-mode optomechanical system by breaking the dark-mode effect with the synthetic-gauge-field method. We find that when the mechanical modes work at a finite temperature, the mechanical squeezing is weak or even disappeared due to the dark-mode effect, while the strong mechanical squeezing can be generated once the dark-mode effect is broken. In particular, the thermal-phonon-occupation tolerance of the mechanical squeezing is approximately three orders of magnitude larger than that without breaking the dark-mode effect. We also generalize this method to break the dark modes and to create the mechanical squeezing in a multiple-mechanical-mode optomechanical system. Our results describe a general physical mechanism and pave the way towards the generation of noise-resistant quantum resources.

quant-ph↗
arXiv2023

XMM-Newton Observations of Two Archival X-ray Weak Type 1 Quasars: Obscuration Induced X-ray Weakness and Variability

We report \hbox{XMM-Newton} observations of two examples of an unclassified type of \hbox{X-ray} weak quasars from the \citet{2020ApJ...900..141P} survey of \hbox{X-ray} weak quasars in the Chandra archive, SDSS J083116.62+321329.6 at $z=1.797$ and SDSS J142339.87+042041.1 at $z=1.702$. They do not belong to the known populations of \hbox{X-ray} weak quasars that show broad absorption lines, weak ultraviolet (UV) broad emission lines, or red optical/UV continua. Instead, they display typical quasar UV spectra and spectral energy distributions. In the \hbox{XMM-Newton} observations, both quasars show nominal levels of \hbox{X-ray} emission with typical quasar \hbox{X-ray} spectral shapes (\hbox{power-law} photon indices of $1.99^{+0.27}_{-0.23}$ and $1.86^{+0.15}_{-0.14}$), displaying strong \hbox{X-ray} variability compared to the archival Chandra data (variability factors of $4.0^{+1.6}_{-1.4}$ and $9.0^{+7.4}_{-3.8}$ in terms of the 2 keV flux density). Simultaneous optical (rest-frame UV) spectra indicate no strong variability compared to the archival spectra. Long-term optical/UV and infrared light curves do not show any substantial variability either. We consider that the \hbox{X-ray} weakness observed in the Chandra data is due to \hbox{X-ray} obscuration from a small-scale dust-free absorber, likely related to accretion-disk winds. Such \hbox{X-ray} weak/absorbed states are probably rare in typical quasars, and thus both targets recovered to \hbox{X-ray} nominal-strength states in the \hbox{XMM-Newton} observations.

astro-ph.GA↗
arXiv2023

Wasserstein Generative Regression

In this paper, we propose a new and unified approach for nonparametric regression and conditional distribution learning. Our approach simultaneously estimates a regression function and a conditional generator using a generative learning framework, where a conditional generator is a function that can generate samples from a conditional distribution. The main idea is to estimate a conditional generator that satisfies the constraint that it produces a good regression function estimator. We use deep neural networks to model the conditional generator. Our approach can handle problems with multivariate outcomes and covariates, and can be used to construct prediction intervals. We provide theoretical guarantees by deriving non-asymptotic error bounds and the distributional consistency of our approach under suitable assumptions. We also perform numerical experiments with simulated and real data to demonstrate the effectiveness and superiority of our approach over some existing approaches in various scenarios.

stat.ML↗
arXiv2023

On Newton Screening

Screening and working set techniques are important approaches to reducing the size of an optimization problem. They have been widely used in accelerating first-order methods for solving large-scale sparse learning problems. In this paper, we develop a new screening method called Newton screening (NS) which is a generalized Newton method with a built-in screening mechanism. We derive an equivalent KKT system for the Lasso and utilize a generalized Newton method to solve the KKT equations. Based on this KKT system, a built-in working set with a relatively small size is first determined using the sum of primal and dual variables generated from the previous iteration, then the primal variable is updated by solving a least-squares problem on the working set and the dual variable updated based on a closed-form expression. Moreover, we consider a sequential version of Newton screening (SNS) with a warm-start strategy. We show that NS possesses an optimal convergence property in the sense that it achieves one-step local convergence. Under certain regularity conditions on the feature matrix, we show that SNS hits a solution with the same signs as the underlying true target and achieves a sharp estimation error bound with high probability. Simulation studies and real data analysis support our theoretical results and demonstrate that SNS is faster and more accurate than several state-of-the-art methods in our comparative studies.

stat.ML↗
arXiv2023

Strong and Rapid X-ray Variability of the Super-Eddington Accreting Quasar SDSS J081456.10+532533.5

We report strong and rapid X-ray variability found from the super-Eddington accreting quasar SDSS J081456.10+532533.5 at $z=0.1197$. It has a black-hole mass of $2.7\times10^{7}{M_{\odot}}$ and a dimensionless accretion rate of $\approx4$ measured from reverberation-mapping observations. It showed weak X-ray emission in the 2021 February Chandra observation, with the 2 keV flux density being $9.6^{+11.6}_{-4.6}$ times lower compared to an archival Swift observation. The 2 keV flux density is also $11.7^{+9.6}_{-6.3}$ times weaker compared to the expectation from its optical/UV emission. In a follow-up XMM-Newton observation 32 days later, the 2 keV flux density increased by a factor of $5.3^{+6.4}_{-2.4}$, and the spectra are best described by a power law modified with partial-covering absorption; the absorption-corrected intrinsic continuum is at a nominal flux level. Nearly simultaneous optical spectra reveal no variability, and there is only mild long-term optical/infrared variability from archival data (with a maximum variability amplitude of $\approx50\%$). We interpret the X-ray variability with an obscuration scenario, where the intrinsic X-ray continuum does not vary but the absorber has variable column density and covering factor along the line of sight. The absorber is likely the small-scale clumpy accretion wind that has been proposed to be responsible for similar X-ray variability in other super-Eddington accreting quasars.

astro-ph.HE↗
arXiv2023

CREPES: Cooperative RElative Pose Estimation System

Mutual localization plays a crucial role in multi-robot cooperation. CREPES, a novel system that focuses on six degrees of freedom (DOF) relative pose estimation for multi-robot systems, is proposed in this paper. CREPES has a compact hardware design using active infrared (IR) LEDs, an IR fish-eye camera, an ultra-wideband (UWB) module and an inertial measurement unit (IMU). By leveraging IR light communication, the system solves data association between visual detection and UWB ranging. Ranging measurements from the UWB and directional information from the camera offer relative 3-DOF position estimation. Combining the mutual relative position with neighbors and the gravity constraints provided by IMUs, we can estimate the 6-DOF relative pose from a single frame of sensor measurements. In addition, we design an estimator based on the error-state Kalman filter (ESKF) to enhance system accuracy and robustness. When multiple neighbors are available, a Pose Graph Optimization (PGO) algorithm is applied to further improve system accuracy. We conduct enormous experiments to demonstrate CREPES' accuracy between robot pairs and a team of robots, as well as performance under challenging conditions.

cs.RO↗
arXiv2023

Deep Nonparametric Regression on Approximate Manifolds: Non-Asymptotic Error Bounds with Polynomial Prefactors

We study the properties of nonparametric least squares regression using deep neural networks. We derive non-asymptotic upper bounds for the prediction error of the empirical risk minimizer of feedforward deep neural regression. Our error bounds achieve minimax optimal rate and significantly improve over the existing ones in the sense that they depend polynomially on the dimension of the predictor, instead of exponentially on dimension. We show that the neural regression estimator can circumvent the curse of dimensionality under the assumption that the predictor is supported on an approximate low-dimensional manifold or a set with low Minkowski dimension. We also establish the optimal convergence rate under the exact manifold support assumption. We investigate how the prediction error of the neural regression estimator depends on the structure of neural networks and propose a notion of network relative efficiency between two types of neural networks, which provides a quantitative measure for evaluating the relative merits of different network structures. To establish these results, we derive a novel approximation error bound for the Hölder smooth functions with a positive smoothness index using ReLU activated neural networks, which may be of independent interest. Our results are derived under weaker assumptions on the data distribution and the neural network structure than those in the existing literature.

math.ST↗
arXiv2022

LeaFTL: A Learning-Based Flash Translation Layer for Solid-State Drives

In modern solid-state drives (SSDs), the indexing of flash pages is a critical component in their storage controllers. It not only affects the data access performance, but also determines the efficiency of the precious in-device DRAM resource. A variety of address mapping schemes and optimization techniques have been proposed. However, most of them were developed with human-driven heuristics. They cannot automatically capture diverse data access patterns at runtime in SSD controllers, which leaves a large room for improvement. In this paper, we present a learning-based flash translation layer (FTL), named LeaFTL, which learns the address mapping to tolerate dynamic data access patterns via linear regression at runtime. By grouping a large set of mapping entries into a learned segment, it significantly reduces the memory footprint of the address mapping table, which further benefits the data caching in SSD controllers. LeaFTL also employs various optimization techniques, including out-of-band metadata verification to tolerate mispredictions, optimized flash allocation, and dynamic compaction of learned index segments. We implement LeaFTL with an SSD simulator and evaluate it with various storage workloads. LeaFTL saves the memory consumption of the mapping table by 2.9x on average and improves the storage performance by 1.4x on average, in comparison with state-of-the-art FTL schemes.

cs.OS↗
arXiv2022

BoostTree and BoostForest for Ensemble Learning

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This paper proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It increases the randomness (diversity) by drawing the cut-points randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest generally outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 35 classification and regression datasets. Remarkably, BoostForest tunes its parameters by simply sampling them randomly from a parameter pool, which can be easily specified, and its ensemble learning framework can also be used to combine many other base learners.

cs.LG↗
arXiv2022

Thermal-noise-resistant optomechanical entanglement via general dark-mode control

Quantum entanglement not only plays an important role in the study of the fundamentals of quantum theory, but also is considered as a crucial resource in quantum information science. The generation of macroscopic entanglement involving multiple optical and mechanical modes is a desired task in cavity optomechanics. However, the dark-mode effect is a critical obstacle against the generation of quantum entanglement in multimode optomechanical systems consisting of multiple degenerate or near-degenerate mechanical modes coupled to a common cavity mode. Here we propose an auxiliary-cavity-mode method to enhance optomechanical entanglement in a multimode optomechanical system by breaking the dark-mode effect. We find that the introduction of the auxiliary cavity mode not only assists the entanglement creation between the cavity mode and the mechanical modes, but also improves the immunity of the optomechanical entanglement to the thermal excitations by about three orders of magnitude. We also study the optomechanical entanglement in the network-coupled optomechanical system consisting of two mechanical modes and two cavity modes. By analyzing the correspondence between the optomechanical entanglement and the dark-mode effect, we find that optomechanical entanglement can be largely enhanced once the dark mode is broken. In addition, we study the mechanical entanglement and find that it is negligibly small. We also present some discussions on the experimental implementation with a microwave optomechanical setup, on the relationship between the dark-mode-breaking mechanism and the center-of-mass and relative coordinates, and on the explanation of the important role of the dark-mode breaking in the enhancement of optomechanical entanglement. Our results pave the way towards the preparation of entangled optomechanical networks and noise-resistant quantum resources.

quant-ph↗
arXiv2022

Nonparametric Quantile Regression: Non-Crossing Constraints and Conformal Prediction

We propose a nonparametric quantile regression method using deep neural networks with a rectified linear unit penalty function to avoid quantile crossing. This penalty function is computationally feasible for enforcing non-crossing constraints in multi-dimensional nonparametric quantile regression. We establish non-asymptotic upper bounds for the excess risk of the proposed nonparametric quantile regression function estimators. Our error bounds achieve optimal minimax rate of convergence for the Holder class, and the prefactors of the error bounds depend polynomially on the dimension of the predictor, instead of exponentially. Based on the proposed non-crossing penalized deep quantile regression, we construct conformal prediction intervals that are fully adaptive to heterogeneity. The proposed prediction interval is shown to have good properties in terms of validity and accuracy under reasonable conditions. We also derive non-asymptotic upper bounds for the difference of the lengths between the proposed non-crossing conformal prediction interval and the theoretically oracle prediction interval. Numerical experiments including simulation studies and a real data example are conducted to demonstrate the effectiveness of the proposed method.

stat.ML↗
arXiv2022

Inference on High-dimensional Single-index Models with Streaming Data

Traditional statistical methods are faced with new challenges due to streaming data. The major challenge is the rapidly growing volume and velocity of data, which makes storing such huge datasets in memory impossible. The paper presents an online inference framework for regression parameters in high-dimensional semiparametric single-index models with unknown link functions. The proposed online procedure updates only the current data batch and summary statistics of historical data instead of re-accessing the entire raw data set. At the same time, we do not need to estimate the unknown link function, which is a highly challenging task. In addition, a generalized convex loss function is used in the proposed inference procedure. To illustrate the proposed method, we use the Huber loss function and the logistic regression model's negative log-likelihood. In this study, the asymptotic normality of the proposed online debiased Lasso estimators and the bounds of the proposed online Lasso estimators are investigated. To evaluate the performance of the proposed method, extensive simulation studies have been conducted. We provide applications to Nasdaq stock prices and financial distress datasets.

stat.ME↗