arXiv subjects

Qi Guo

Publications and source records attributed to Qi Guo.

At least 217 records · Page 12Linked to original sources

arXiv2022

StereoISP: Rethinking Image Signal Processing for Dual Camera Systems

Conventional image signal processing (ISP) frameworks are designed to reconstruct an RGB image from a single raw measurement. As multi-camera systems become increasingly popular these days, it is worth exploring improvements in ISP frameworks by incorporating raw measurements from multiple cameras. This manuscript is an intermediate progress report of a new ISP framework that is under development, StereoISP. It employs raw measurements from a stereo camera pair to generate a demosaicked, denoised RGB image by utilizing disparity estimated between the two views. We investigate StereoISP by testing the performance on raw image pairs synthesized from stereo datasets. Our preliminary results show an improvement in the PSNR of the reconstructed RGB image by at least 2dB on KITTI 2015 and drivingStereo datasets using ground truth sparse disparity maps.

eess.IV↗

arXiv2022

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning

Hierarchical reinforcement learning (HRL) effectively improves agents' exploration efficiency on tasks with sparse reward, with the guide of high-quality hierarchical structures (e.g., subgoals or options). However, how to automatically discover high-quality hierarchical structures is still a great challenge. Previous HRL methods can hardly discover the hierarchical structures in complex environments due to the low exploration efficiency by exploiting the randomness-driven exploration paradigm. To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, leveraging a causality-driven discovery instead of a randomness-driven exploration to effectively build high-quality hierarchical structures in complicated environments. The key insight is that the causalities among environment variables are naturally fit for modeling reachable subgoals and their dependencies and can perfectly guide to build high-quality hierarchical structures. The results in two complex environments, 2D-Minecraft and Eden, show that CDHRL significantly boosts exploration efficiency with the causality-driven paradigm.

cs.LG↗

arXiv2022

Object-Category Aware Reinforcement Learning

Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL. Recent works that try to solve OORL tasks without additional feature engineering mainly focus on learning the object representations and then solving tasks via reasoning based on these object representations. However, none of these works tries to explicitly model the inherent similarity between different object instances of the same category. Objects of the same category should share similar functionalities; therefore, the category is the most critical property of an object. Following this insight, we propose a novel framework named Object-Category Aware Reinforcement Learning (OCARL), which utilizes the category information of objects to facilitate both perception and reasoning. OCARL consists of three parts: (1) Category-Aware Unsupervised Object Discovery (UOD), which discovers the objects as well as their corresponding categories; (2) Object-Category Aware Perception, which encodes the category information and is also robust to the incompleteness of (1) at the same time; (3) Object-Centric Modular Reasoning, which adopts multiple independent and object-category-specific networks when reasoning based on objects. Our experiments show that OCARL can improve both the sample efficiency and generalization in the OORL domain.

cs.LG↗

arXiv2022

Multivariate Hawkes-based Models in LOB: European, Spread and Basket Option Pricing

In this paper, we consider pricing of European options and spread options for Hawkes-based model for the limit order book. We introduce multivariate Hawkes process and the multivariable general compound Hawkes process. Exponential multivariate general compound Hawkes processes and limit theorems for them, namely, LLN and FCLT, are considered then. We also consider a special case of one-dimensional EMGCHP and its limit theorems. Option pricing with $1D$ EGCHP in LOB, hedging strategies, and numerical example are presented. We also introduce greeks calculations for those models. Margrabe's spread options valuations with Hawkes-based models for two assets and numerical example are presented. Also, Margrabe's spread option pricing with two $2D$ EMGCHP and numerical example are included. Basket options valuations with numerical example are included. We finally discuss the implied volatility and implied order flow. It reveals the relationship between stock volatility and the order flow in the limit order book system. In this way, the Hawkes-based model can provide more market forecast information than the classical Black-Scholes model.

q-fin.MF↗

arXiv2022

Remote Work Optimization with Robust Multi-channel Graph Neural Networks

The spread of COVID-19 leads to the global shutdown of many corporate offices, and encourages companies to open more opportunities that allow employees to work from a remote location. As the workplace type expands from onsite offices to remote areas, an emerging challenge for an online hiring marketplace is how these remote opportunities and user intentions to work remotely can be modeled and matched without prior information. Despite the unprecedented amount of remote jobs posted amid COVID-19, there is no existing approach that can be directly applied. Introducing a brand new workplace type naturally leads to the cold-start problem, which is particularly more common for less active job seekers. It is challenging, if not impossible, to onboard a new workplace type for any predictive model if existing information sources can provide little information related to a new category of jobs, including data from resumes and job descriptions. Hence, in this work, we aim to propose a principled approach that jointly models the remoteness of job seekers and job opportunities with limited information, which also suffices the needs of web-scale applications. Existing research on the emerging type of remote workplace mainly focuses on qualitative studies, and classic predictive modeling approaches are inapplicable considering the problem of cold-start and information scarcity. We precisely try to close this gap with a novel graph neural architecture. Extensive experiments on large-scale data from real-world applications have been conducted to validate the superiority of the proposed approach over competitive baselines. The improvement may translate to more rapid onboarding of the new workplace type that can benefit job seekers who are interested in working remotely.

cs.SI↗

arXiv2022

FedMCSA: Personalized Federated Learning via Model Components Self-Attention

Federated learning (FL) facilitates multiple clients to jointly train a machine learning model without sharing their private data. However, Non-IID data of clients presents a tough challenge for FL. Existing personalized FL approaches rely heavily on the default treatment of one complete model as a basic unit and ignore the significance of different layers on Non-IID data of clients. In this work, we propose a new framework, federated model components self-attention (FedMCSA), to handle Non-IID data in FL, which employs model components self-attention mechanism to granularly promote cooperation between different clients. This mechanism facilitates collaboration between similar model components while reducing interference between model components with large differences. We conduct extensive experiments to demonstrate that FedMCSA outperforms the previous methods on four benchmark datasets. Furthermore, we empirically show the effectiveness of the model components self-attention mechanism, which is complementary to existing personalized FL and can significantly improve the performance of FL.

cs.LG↗

arXiv2022

Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks

DNN-based video object detection (VOD) powers autonomous driving and video surveillance industries with rising importance and promising opportunities. However, adversarial patch attack yields huge concern in live vision tasks because of its practicality, feasibility, and powerful attack effectiveness. This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection. We observe that adversarial patches exhibit extremely localized superficial feature importance in a small region with non-robust predictions, and thus propose the adversarial region detection algorithm for adversarial effect elimination. Themis also proposes a systematic design to efficiently support the algorithm by eliminating redundant computations and memory traffics. Experimental results show that the proposed methodology can effectively recover the system from the adversarial attack with negligible hardware overhead.

cs.CV↗

arXiv2022

D-Flat: A Differentiable Flat-Optics Framework for End-to-End Metasurface Visual Sensor Design

Optical metasurfaces are planar substrates with custom-designed, nanoscale features that selectively modulate incident light with respect to direction, wavelength, and polarization. When coupled with photodetectors and appropriate post-capture processing, they provide a means to create computational imagers and sensors that are exceptionally small and have distinctive capabilities. We introduce D-Flat, a framework in TensorFlow that renders physically-accurate images induced by metasurface optical systems. This framework is fully differentiable with respect to metasurface shape and post-capture computational parameters and allows simultaneous optimization with respect to almost any measure of sensor performance. D-Flat enables simulation of millimeter to centimeter diameter metasurfaces on commodity computers, and it is modular in the sense of accommodating a variety of wave optics models for scattering at the metasurface and for propagation to photosensors. We validate D-Flat against symbolic calculations and previous experimental measurements, and we provide simulations that demonstrate its ability to discover novel computational sensor designs for two applications: single-shot depth sensing and single-shot spatial frequency filtering.

physics.optics↗

arXiv2022

Normalized Solutions to the mixed fractional Schrodinger equations with potential and general nonlinear term

The purpose of this paper is to establish the existence of solutions with prescribed norm to a class of nonlinear equations involving the mixed fractional Laplacians. This type of equations arises in various fields ranging from biophysics to population dynamics. Due to the importance of these applications, this topic has very recently received an increasing interest. Our method is novel and our results cover all the previous ones.

math.AP↗

arXiv2022

The impact of filaments on dwarf galaxy properties in the Auriga simulations

With a hydrodynamical simulation using a simple galaxy formation model without taking into account feedback, our previous work has shown that dense and massive filaments at high redshift can provide potential wells to trap and compress gas, and hence affect galaxy formation in their resident low-mass haloes. In this paper, we make use of the Auriga simulations, a suite of high-resolution zoom-in hydrodynamical simulations of Milky Way-like galaxies, to study whether the conclusion still holds in the simulations with a sophisticated galaxy formation model. In agreement with the results of our previous work, we find that, comparing to their counterparts with similar halo masses in field, dwarf galaxies residing in filaments tend to have higher baryonic and stellar fractions. At the fixed parent halo mass, the filament dwarfs tend to have slightly higher star formation rates than those of field ones. But overall we do not find a clear difference in galaxy g - r colours between the filament and field populations. We also show that at high redshifts, the gas components in dwarf galaxies tend to have their spins aligned with the filaments in which they reside. Our results support a picture in which massive filaments at high redshift assist gas accretion and enhance star formation in their resident dwarf sized dark matter haloes.

astro-ph.GA↗

arXiv2022

The spatial distribution of satellites in galaxy clusters

The planar distributions of satellite galaxies around the Milky Way and Andromeda have been extensively studied as potential challenges to the standard cosmological model. Using the Sloan Digital Sky Survey and the Millennium simulation we extend such studies to the satellite galaxies of massive galaxy clusters. We find that both observations and simulations of galaxy clusters show an excess of anisotropic satellite distributions. On average, satellites in clusters have a higher degree of anisotropy than their counterparts in Milky-Way-mass hosts once we account for the difference in their radial distributions. The normal vector of the plane of satellites is strongly aligned with the host halo's minor axis, while the alignment with the large-scale structure is weak. At fixed cluster mass, the degree of anisotropy is higher at higher redshift. This reflects the highly anisotropic nature of satellites accretion points, a feature that is partly erased by the subsequent orbital evolution of the satellites. We also find that satellite galaxies are mostly accreted singly so group accretion is not the explanation for the high flattening of the planes of satellites.

astro-ph.GA↗

arXiv2022

Neural Program Synthesis with Query

Aiming to find a program satisfying the user intent given input-output examples, program synthesis has attracted increasing interest in the area of machine learning. Despite the promising performance of existing methods, most of their success comes from the privileged information of well-designed input-output examples. However, providing such input-output examples is unrealistic because it requires the users to have the ability to describe the underlying program with a few input-output examples under the training distribution. In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space. The quality of the query depends on the amount of the mutual information between the query and the corresponding program, which can guide the optimization of the query framework. To estimate the mutual information more accurately, we introduce the functional space (F-space) which models the relevance between the input-output examples and the programs in a differentiable way. We evaluate the effectiveness and generalization of the proposed query-based framework on the Karel task and the list processing task. Experimental results show that the query-based framework can generate informative input-output examples which achieve and even outperform well-designed input-output examples.

cs.LG↗

arXiv2021

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial patch attacks work well on small images like MNIST and CIFAR-10 datasets, but achieve very poor certified accuracy on higher-resolution images like ImageNet. It is urgent to design both robust and effective defenses against such a practical and harmful attack in industry-level larger images. In this work, we propose the certified defense methodology that achieves high provable robustness for high-resolution images and largely improves the practicality for real adoption of the certified defense. The basic insight of our work is that the adversarial patch intends to leverage localized superficial important neurons (SIN) to manipulate the prediction results. Hence, we leverage the SIN-based DNN compression techniques to significantly improve the certified accuracy, by reducing the adversarial region searching overhead and filtering the prediction noises. Our experimental results show that the certified accuracy is increased from 36.3% (the state-of-the-art certified detection) to 60.4% on the ImageNet dataset, largely pushing the certified defenses for practical use.

cs.CV↗

arXiv2021

The Formation and Evolution of Massive Galaxies

The discovery of massive galaxies at high redshifts, especially the passive ones, poses a big challenge for the current standard galaxy formation models. Here we use the semi-analytic galaxy formation model developed by Henriques et al. to explore the formation and evolution of massive galaxies (MGs, stellar-mass $M_{*}> 10^{11}$ M$_{\odot}$). Different from previous works, we focus on the ones just formed (e.g. just reach $\simeq 10^{11}$ M$_{\odot}$). We find that most of the MGs are formed around $z=0.6$, with the earliest formation at $z>4$. Interestingly, although most of the MGs in the local Universe are passive, we find that only $13\%$ of the MGs are quenched at the formation time. Most of the quenched MGs at formation already hosts a very massive supermassive black hole (SMBH) which could power the very effective AGN feedback. For the star-forming MGs, the ones with more massive SMBH prefer to quench in shorter timescales; in particular, those with $M_{\textrm{SMBH}} > 10^{7.5}$ M$_{\odot}$ have a quenching timescale of $\sim 0.5$ Gyr and the characteristic $M_{\textrm{SMBH}}$ depends on the chosen stellar mass threshold in the definition of MGs as a result of their co-evolution. We also find that the "in-situ" star formation dominates the stellar mass growth of MGs until they are formed. Over the whole redshift range, we find the quiescent MGs prefer to stay in more massive dark matter halos, and have more massive SMBH and less cold gas masses. Our results provide a new angle on the whole life of the growth of MGs in the Universe.

astro-ph.GA↗

arXiv2021

The role of mergers and gas accretion in black hole growth and galaxy evolution

We use a semi-analytic galaxy formation model to study the co-evolution of supermassive black holes (SMBHs) with their host galaxies. Although the coalescence of SMBHs is not important, the quasar-mode accretion induced by mergers plays a dominant role in the growth of SMBHs. Mergers play a more important role in the growth of SMBH host galaxies than in the SMBH growth. It is the combined contribution from quasar mode accretion and mergers to the SMBH growth and the combined contribution from starburst and mergers to their host galaxy growth that determine the observed scaling relation between the SMBH masses and their host galaxy masses. We also find that mergers are more important in the growth of SMBH host galaxies compared to normal galaxies which share the same stellar mass range as the SMBH host galaxies.

astro-ph.GA↗

arXiv2021

Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms

With AlphaGo defeats top human players, reinforcement learning(RL) algorithms have gradually become the code-base of building stronger artificial intelligence(AI). The RL algorithm design firstly needs to adapt to the specific environment, so the designed environment guides the rapid and profound development of RL algorithms. However, the existing environments, which can be divided into real world games and customized toy environments, have obvious shortcomings. For real world games, it is designed for human entertainment, and too much difficult for most of RL researchers. For customized toy environments, there is no widely accepted unified evaluation standard for all RL algorithms. Therefore, we introduce the first virtual user-friendly environment framework for RL. In this framework, the environment can be easily configured to realize all kinds of RL tasks in the mainstream research. Then all the mainstream state-of-the-art(SOTA) RL algorithms can be conveniently evaluated and compared. Therefore, our contributions mainly includes the following aspects: 1.single configured environment for all classification of SOTA RL algorithms; 2.combined environment of more than one classification RL algorithms; 3.the evaluation standard for all kinds of RL algorithms. With all these efforts, a possibility for breeding an AI with capability of general competency in a variety of tasks is provided, and maybe it will open up a new chapter for AI.

cs.LG↗

arXiv2021

Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment

Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied commonly. However, the effect of the state value function becomes limited in stochastic dynamic environments, where the unexpected state dynamics and rewards will increase the variance. In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments. Particularly, to obtain an ideally unbiased gradient estimate, we propose an information-theoretic approach, which optimizes the embeddings of the future to be independent of previous actions. In our experiments, we apply the proposed hindsight value function in stochastic dynamic environments, including discrete-action environments and continuous-action environments. Compared with the standard state value function, the proposed hindsight value function consistently reduces the variance, stabilizes the training, and improves the eventual policy.

cs.LG↗

arXiv2021

Multi-peak solitons in nonlocal nonlinear system with sine-oscillation response

The multi-peak solitons and their stability are investigated for the nonlocal nonlinear system with the sine-oscillation response, including both the cases of positive and negative Kerr coefficients. The Hermite-Gaussian-type multi-peak solitons and the ranges of the degree of nonlocality within which the solitons exist are analytically obtained by the variational approach. This is the first time, to our knowledge at least, to discuss the solution existence range of the multi-peak solitons analytically, although approximately. The variational analytical results are confirmed by the numerical ones. The stability of the multi-peak solitons are addressed by the linear stability analysis. It is found that the upper thresholds of the peak-number of the stable solitons are five and four for the system with negative and positive Kerr coefficients, respectively.

nlin.PS↗