arXiv subjects

Shuai Li

Publications and source records attributed to Shuai Li.

At least 307 records · Page 17Linked to original sources

arXiv2021

Combinatorial Bandits under Strategic Manipulations

Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed. Motivated by such behavior we study the problem of combinatorial multi-armed bandits (CMAB) under strategic manipulations of rewards, where each arm can modify the emitted reward signals for its own interest. This characterization of the adversarial behavior is a relaxation of previously well-studied settings such as adversarial attacks and adversarial corruption. We propose a strategic variant of the combinatorial UCB algorithm, which has a regret of at most $O(m\log T + m B_{max})$ under strategic manipulations, where $T$ is the time horizon, $m$ is the number of arms, and $B_{max}$ is the maximum budget of an arm. We provide lower bounds on the budget for arms to incur certain regret of the bandit algorithm. Extensive experiments on online worker selection for crowdsourcing systems, online influence maximization and online recommendations with both synthetic and real datasets corroborate our theoretical findings on robustness and regret bounds, in a variety of regimes of manipulation budgets.

cs.LG↗

arXiv2021

Interior and Boundary Regularity Criteria for the 6D steady Navier-Stokes Equations

It is shown in this paper that suitable weak solutions to the 6D steady incompressible Navier-Stokes are Hölder continuous at $0$ provided that $\int_{B_1}|u(x)|^3dx+\int_{B_1}|f(x)|^qdx$ or $\int_{B_1}|\nabla u(x)|^2dx$+$\int_{B_1}|\nabla u(x)|^2dx\left(\int_{B_1}|u(x)|dx\right)^2+\int_{B_1}|f(x)|^qdx$ with $q>3$ is sufficiently small, which implies that the 2D Hausdorff measure of the set of singular points is zero. For the boundary case, we obtain that $0$ is regular provided that $\int_{B_1^+} |u(x)|^3 dx + \int_{B_1^+} |f(x)|^3 dx$ or $\int_{B_1^+} |\nabla u(x)|^2 dx + \int_{B_1^+} |f(x)|^3 dx$ is sufficiently small. These results improve previous regularity theorems by Dong-Strain (\cite{DS}, Indiana Univ. Math. J., 2012), Dong-Gu (\cite{DG2}, J. Funct. Anal., 2014), and Liu-Wang (\cite{LW}, J. Differential Equations, 2018), where either the smallness of the pressure or the smallness on all balls is necessary.

math.AP↗

arXiv2021

The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle

Thompson sampling (TS) has attracted a lot of interest in the bandit area. It was introduced in the 1930s but has not been theoretically proven until recent years. All of its analysis in the combinatorial multi-armed bandit (CMAB) setting requires an exact oracle to provide optimal solutions with any input. However, such an oracle is usually not feasible since many combinatorial optimization problems are NP-hard and only approximation oracles are available. An example (Wang and Chen, 2018) has shown the failure of TS to learn with an approximation oracle. However, this oracle is uncommon and is designed only for a specific problem instance. It is still an open question whether the convergence analysis of TS can be extended beyond the exact oracle in CMAB. In this paper, we study this question under the greedy oracle, which is a common (approximation) oracle with theoretical guarantees to solve many (offline) combinatorial optimization problems. We provide a problem-dependent regret lower bound of order $Ω(\log T/Δ^2)$ to quantify the hardness of TS to solve CMAB problems with greedy oracle, where $T$ is the time horizon and $Δ$ is some reward gap. We also provide an almost matching regret upper bound. These are the first theoretical results for TS to solve CMAB with a common approximation oracle and break the misconception that TS cannot work with approximation oracles.

cs.LG↗

arXiv2021

Understanding Bandits with Graph Feedback

The bandit problem with graph feedback, proposed in [Mannor and Shamir, NeurIPS 2011], is modeled by a directed graph $G=(V,E)$ where $V$ is the collection of bandit arms, and once an arm is triggered, all its incident arms are observed. A fundamental question is how the structure of the graph affects the min-max regret. We propose the notions of the fractional weak domination number $δ^*$ and the $k$-packing independence number capturing upper bound and lower bound for the regret respectively. We show that the two notions are inherently connected via aligning them with the linear program of the weakly dominating set and its dual -- the fractional vertex packing set respectively. Based on this connection, we utilize the strong duality theorem to prove a general regret upper bound $O\left(\left( δ^*\log |V|\right)^{\frac{1}{3}}T^{\frac{2}{3}}\right)$ and a lower bound $Ω\left(\left(δ^*/α\right)^{\frac{1}{3}}T^{\frac{2}{3}}\right)$ where $α$ is the integrality gap of the dual linear program. Therefore, our bounds are tight up to a $\left(\log |V|\right)^{\frac{1}{3}}$ factor on graphs with bounded integrality gap for the vertex packing problem including trees and graphs with bounded degree. Moreover, we show that for several special families of graphs, we can get rid of the $\left(\log |V|\right)^{\frac{1}{3}}$ factor and establish optimal regret.

cs.LG↗

arXiv2021

Manipulating Goldstone modes via the superradiant light in a bosonic lattice gas inside a cavity

We study the low-energy excitations of a bosonic lattice gas with cavity-mediated interactions. By performing two successive Hubbard-Stratonovich transformations, we derive an effective field theory to study the strongly-coupling regime. Taking into account the quantum fluctuation, we report the unusual effect of the superradiant cavity light induced density imbalance, which has been shown to have a negligible effect on the single particle excitation in the previous studies. Instead, we show that such negligible fluctuation of density imbalance dramatically changes the behavior of the low-energy excitation and results in a free switching between two types of Goldstone modes in its single particle excitation, i.e., type I and type II with odd and even power energy-momentum dispersion, respectively. Our proposal would open a new horizon for manipulating Goldstone modes from bridging the cavity light and strongly interacting quantum matters.

cond-mat.quant-gas↗

arXiv2021

Gate-induced half-metals in Bernal stacked graphene multilayer

Recent experiments indicate that the Bernal stacked graphene multilayer (BGM) have an interaction induced gapped (or pseudo gapped) ground state. Here, we propose that, due to the electron correlation, the BGM can be induced into a half metallic phase by applying a vertical electric field and doping. The half metallic states in even-layer and odd-layer BGMs have totally different behaviors, due to their different band structures. We systematically calculate the graphene tetralayer (4L-BGM) and trilayer (3L-BGM) as the typical examples of the even-layer and odd-layer BGMs, respectively. In 4L-BGM, we find an interesting phenomenon of electric field induced inversion of the spin-polarized bands. Namely, in the half metallic phase, the spin polarization of the conducting channel and the net magnetic moment are inversed when the applied electric field exceeds a critical value. In 3L-BGM, a remarkable feature is that the inequivalence of the the two sublattices will intrinsically break the degeneracy of the the spin-up and spin-down bands even in the zero electric field case. Our results suggest that 4L-BGM should be an ideal platform to detect the proposed half metallic phase in BGM systems.

cond-mat.mes-hall↗

arXiv2021

Incentivizing an Unknown Crowd

Motivated by the common strategic activities in crowdsourcing labeling, we study the problem of sequential eliciting information without verification (EIWV) for workers with a heterogeneous and unknown crowd. We propose a reinforcement learning-based approach that is effective against a wide range of settings including potential irrationality and collusion among workers. With the aid of a costly oracle and the inference method, our approach dynamically decides the oracle calls and gains robustness even under the presence of frequent collusion activities. Extensive experiments show the advantage of our approach. Our results also present the first comprehensive experiments of EIWV on large-scale real datasets and the first thorough study of the effects of environmental variables.

cs.LG↗

arXiv2021

Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography

The lensless pinhole camera is perhaps the earliest and simplest form of an imaging system using only a pinhole-sized aperture in place of a lens. They can capture an infinite depth-of-field and offer greater freedom from optical distortion over their lens-based counterparts. However, the inherent limitations of a pinhole system result in lower sharpness from blur caused by optical diffraction and higher noise levels due to low light throughput of the small aperture, requiring very long exposure times to capture well-exposed images. In this paper, we explore an image restoration pipeline using deep learning and domain-knowledge of the pinhole system to enhance the pinhole image quality through a joint denoise and deblur approach. Our approach allows for more practical exposure times for hand-held photography and provides higher image quality, making it more suitable for daily photography compared to other lensless cameras while keeping size and cost low. This opens up the potential of pinhole cameras to be used in smaller devices, such as smartphones.

cs.CV↗

arXiv2021

Using nonlocal surface transport to identify the axion insulator

The axion is a hypothetical but experimentally undetected particle. Recently, the antiferromagnetic topological insulator MnBi$_2$Te$_4$ has been predicted to host the axion insulator, but the experimental evidence remains elusive. Specifically, the axion insulator is believed to carry "half-quantized" chiral currents running antiparallel on its top and bottom surfaces. However, it is challenging to measure precisely the half-quantization. Here, we propose a nonlocal surface transport device, in which the axion insulator can be distinguished from normal insulators without a precise measurement of the half-quantization. More importantly, we show that the nonlocal surface transport, as a qualitative measurement, is robust in realistic situations when the gapless side surfaces and disorder come to play. Moreover, thick electrodes can be used in the device of MnBi$_2$Te$_4$ thick films, enhancing the feasibility of the surface measurements. This proposal will be insightful for the search of the axion insulator and axion in topological matter.

cond-mat.mes-hall↗

arXiv2021

Towards Black-box Attacks on Deep Learning Apps

Deep learning is a powerful weapon to boost application performance in many fields, including face recognition, object detection, image classification, natural language understanding, and recommendation system. With the rapid increase in the computing power of mobile devices, developers can embed deep learning models into their apps for building more competitive products with more accurate and faster responses. Although there are several works about adversarial attacks against deep learning models in mobile apps, they all need information about the models' internals (i.e., structures, weights) or need to modify the models. In this paper, we propose an effective black-box approach by training a substitute model to spoof the deep learning system inside the apps. To evaluate our approach, we select 10 real-world deep-learning apps with high popularity from Google Play to perform black-box adversarial attacks. Through the study, we find three factors that can influence the performance of attacks. Our approach can reach a relatively high attack success rate of 66.60% on average. Compared with other adversarial attacks on mobile deep learning models, in terms of the average attack success rates, our approach outperforms counterparts by 27.63%.

cs.SE↗

arXiv2021

Fractional order graph neural network

This paper proposes fractional order graph neural networks (FGNNs), optimized by the approximation strategy to address the challenges of local optimum of classic and fractional graph neural networks which are specialised at aggregating information from the feature and adjacent matrices of connected nodes and their neighbours to solve learning tasks on non-Euclidean data such as graphs. Meanwhile the approximate calculation of fractional order gradients also overcomes the high computational complexity of fractional order derivations. We further prove that such an approximation is feasible and the FGNN is unbiased towards global optimization solution. Extensive experiments on citation networks show that FGNN achieves great advantage over baseline models when selected appropriate fractional order.

cs.LG↗

arXiv2021

A Global Appearance and Local Coding Distortion based Fusion Framework for CNN based Filtering in Video Coding

In-loop filtering is used in video coding to process the reconstructed frame in order to remove blocking artifacts. With the development of convolutional neural networks (CNNs), CNNs have been explored for in-loop filtering considering it can be treated as an image de-noising task. However, in addition to being a distorted image, the reconstructed frame is also obtained by a fixed line of block based encoding operations in video coding. It carries coding-unit based coding distortion of some similar characteristics. Therefore, in this paper, we address the filtering problem from two aspects, global appearance restoration for disrupted texture and local coding distortion restoration caused by fixed pipeline of coding. Accordingly, a three-stream global appearance and local coding distortion based fusion network is developed with a high-level global feature stream, a high-level local feature stream and a low-level local feature stream. Ablation study is conducted to validate the necessity of different features, demonstrating that the global features and local features can complement each other in filtering and achieve better performance when combined. To the best of our knowledge, we are the first one that clearly characterizes the video filtering process from the above global appearance and local coding distortion restoration aspects with experimental verification, providing a clear pathway to developing filter techniques. Experimental results demonstrate that the proposed method significantly outperforms the existing single-frame based methods and achieves 13.5%, 11.3%, 11.7% BD-Rate saving on average for AI, LDP and RA configurations, respectively, compared with the HEVC reference software.

eess.IV↗

arXiv2021

Remarks on Liouville type theorems for the steady MHD and Hall-MHD equations

In this note we investigate Liouville type theorems for the steady three dimensional MHD and Hall-MHD equations, and show that the velocity field $u$ and the magnetic field $B$ are vanishing provided that $B\in L^{6,\infty}(\mathbb{R}^3)$ and $u\in BMO^{-1}(\mathbb{R}^3)$, which state that the velocity field plays an important role. Moreover, the similar result holds in the case of partial viscosity or diffusivity for the three dimensional MHD equations.

math.AP↗

arXiv2021

Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions

We study the problem of stochastic bandits with adversarial corruptions in the cooperative multi-agent setting, where $V$ agents interact with a common $K$-armed bandit problem, and each pair of agents can communicate with each other to expedite the learning process. In the problem, the rewards are independently sampled from distributions across all agents and rounds, but they may be corrupted by an adversary. Our goal is to minimize both the overall regret and communication cost across all agents. We first show that an additive term of corruption is unavoidable for any algorithm in this problem. Then, we propose a new algorithm that is agnostic to the level of corruption. Our algorithm not only achieves near-optimal regret in the stochastic setting, but also obtains a regret with an additive term of corruption in the corrupted setting, while maintaining efficient communication. The algorithm is also applicable for the single-agent corruption problem, and achieves a high probability regret that removes the multiplicative dependence of $K$ on corruption level. Our result of the single-agent case resolves an open question from Gupta et al. [2019].

cs.LG↗

arXiv2021

On Learning to Rank Long Sequences with Contextual Bandits

Motivated by problems of learning to rank long item sequences, we introduce a variant of the cascading bandit model that considers flexible length sequences with varying rewards and losses. We formulate two generative models for this problem within the generalized linear setting, and design and analyze upper confidence algorithms for it. Our analysis delivers tight regret bounds which, when specialized to vanilla cascading bandits, results in sharper guarantees than previously available in the literature. We evaluate our algorithms on a number of real-world datasets, and show significantly improved empirical performance as compared to known cascading bandit baselines.

cs.LG↗

arXiv2021

Cascading Bandit under Differential Privacy

This paper studies \emph{differential privacy (DP)} and \emph{local differential privacy (LDP)} in cascading bandits. Under DP, we propose an algorithm which guarantees $ε$-indistinguishability and a regret of $\mathcal{O}((\frac{\log T}ε)^{1+ξ})$ for an arbitrarily small $ξ$. This is a significant improvement from the previous work of $\mathcal{O}(\frac{\log^3 T}ε)$ regret. Under ($ε$,$δ$)-LDP, we relax the $K^2$ dependence through the tradeoff between privacy budget $ε$ and error probability $δ$, and obtain a regret of $\mathcal{O}(\frac{K\log (1/δ) \log T}{ε^2})$, where $K$ is the size of the arm subset. This result holds for both Gaussian mechanism and Laplace mechanism by analyses on the composition. Our results extend to combinatorial semi-bandit. We show respective lower bounds for DP and LDP cascading bandits. Extensive experiments corroborate our theoretic findings.

cs.LG↗

arXiv2021

Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners

Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) are two typical strategies to reduce expensive manual annotations in machine learning. In order to learn effective models for a target task, UDA utilizes the available labeled source data, which may have different distributions from unlabeled samples in the target domain, while SSL employs few manually annotated target samples. Although UDA and SSL are seemingly very different strategies, we find that they are closely related in terms of task objectives and solutions, and SSL is a special case of UDA problems. Based on this finding, we further investigate whether SSL methods work on UDA tasks. By adapting eight representative SSL algorithms on UDA benchmarks, we show that SSL methods are strong UDA learners. Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques. We thus promote that SSL methods should be employed as baselines in future UDA studies and expect that the revealed relationship between UDA and SSL could shed light on future UDA development. Codes are available at \url{https://github.com/YBZh}.

cs.LG↗

arXiv2021

Online Influence Maximization under Linear Threshold Model

Online influence maximization (OIM) is a popular problem in social networks to learn influence propagation model parameters and maximize the influence spread at the same time. Most previous studies focus on the independent cascade (IC) model under the edge-level feedback. In this paper, we address OIM in the linear threshold (LT) model. Because node activations in the LT model are due to the aggregated effect of all active neighbors, it is more natural to model OIM with the node-level feedback. And this brings new challenge in online learning since we only observe aggregated effect from groups of nodes and the groups are also random. Based on the linear structure in node activations, we incorporate ideas from linear bandits and design an algorithm LT-LinUCB that is consistent with the observed feedback. By proving group observation modulated (GOM) bounded smoothness property, a novel result of the influence difference in terms of the random observations, we provide a regret of order $\tilde{O}(\mathrm{poly}(m)\sqrt{T})$, where $m$ is the number of edges and $T$ is the number of rounds. This is the first theoretical result in such order for OIM under the LT model. In the end, we also provide an algorithm OIM-ETC with regret bound $O(\mathrm{poly}(m)\ T^{2/3})$, which is model-independent, simple and has less requirement on online feedback and offline computation.

cs.LG↗