Searcharxiv⌕ Search

arXiv subjects

Bo Wu

Publications and source records attributed to Bo Wu.

At least 145 records · Page 8Linked to original sources
arXiv2019

Hard-Aware Fashion Attribute Classification

Fashion attribute classification is of great importance to many high-level tasks such as fashion item search, fashion trend analysis, fashion recommendation, etc. The task is challenging due to the extremely imbalanced data distribution, particularly the attributes with only a few positive samples. In this paper, we introduce a hard-aware pipeline to make full use of "hard" samples/attributes. We first propose Hard-Aware BackPropagation (HABP) to efficiently and adaptively focus on training "hard" data. Then for the identified hard labels, we propose to synthesize more complementary samples for training. To stabilize training, we extend semi-supervised GAN by directly deactivating outputs for synthetic complementary samples (Deact). In general, our method is more effective in addressing "hard" cases. HABP weights more on "hard" samples. For "hard" attributes with insufficient training data, Deact brings more stable synthetic samples for training and further improve the performance. Our method is verified on large scale fashion dataset, outperforming other state-of-the-art without any additional supervisions.

cs.CV↗
arXiv2019

Stochastic Heat Equations for infinite strings with Values in a Manifold

In the paper, we construct conservative Markov processes corresponding to the martingale solutions to the stochastic heat equation on $\mathbb{R}^+$ or $\mathbb{R}$ with values in a general Riemannian maifold, which is only assumed to be complete and stochastic complete. This work is an extension of the previous paper \cite{RWZZ17} on finite volume case. Moveover, we also obtain some functional inequalities associated to these Markov processes. This implies that on infinite volume case, the exponential ergodicity of the solution if the Ricci curvature is strictly positive and the non-ergodicity of the process if the sectional curvature is negative.

math.PR↗
arXiv2019

Control Theory Meets POMDPs: A Hybrid Systems Approach

Partially observable Markov decision processes (POMDPs) provide a modeling framework for a variety of sequential decision making under uncertainty scenarios in artificial intelligence (AI). Since the states are not directly observable in a POMDP, decision making has to be performed based on the output of a Bayesian filter (continuous beliefs). Hence, POMDPs are often computationally intractable to solve exactly and researchers resort to approximate methods often using discretizations of the continuous belief space. These approximate solutions are, however, prone to discretization errors, which has made POMDPs ineffective in applications, wherein guarantees for safety, optimality, or performance are required. To overcome the complexity challenge of POMDPs, we apply notions from control theory. The goal is to determine the reachable belief space of a POMDP, that is, the set of all possible evolutions given an initial belief distribution over the states and a set of actions and observations. We begin by casting the problem of analyzing a POMDP into analyzing the behavior of a discrete-time switched system. For estimating the reachable belief space, we find over-approximations in terms of sub-level sets of Lyapunov functions. Furthermore, in order to verify safety and optimality requirements of a given POMDP, we formulate a barrier certificate theorem, wherein we show that if there exists a barrier certificate satisfying a set of inequalities along with the belief update equation of the POMDP, the safety and optimality properties are guaranteed to hold. In both cases, we show how the calculations can be decomposed into smaller problems that can be solved in parallel. The conditions we formulate can be computationally implemented as a set of sum-of-squares programs. We illustrate the applicability of our method by addressing two problems in active ad scheduling and machine teaching.

eess.SY↗
arXiv2019

Reward-Based Deception with Cognitive Bias

Deception plays a key role in adversarial or strategic interactions for the purpose of self-defence and survival. This paper introduces a general framework and solution to address deception. Most existing approaches for deception consider obfuscating crucial information to rational adversaries with abundant memory and computation resources. In this paper, we consider deceiving adversaries with bounded rationality and in terms of expected rewards. This problem is commonly encountered in many applications especially involving human adversaries. Leveraging the cognitive bias of humans in reward evaluation under stochastic outcomes, we introduce a framework to optimally assign resources of a limited quantity to optimally defend against human adversaries. Modeling such cognitive biases follows the so-called prospect theory from behavioral psychology literature. Then we formulate the resource allocation problem as a signomial program to minimize the defender's cost in an environment modeled as a Markov decision process. We use police patrol hour assignment as an illustrative example and provide detailed simulation results based on real-world data.

cs.AI↗
arXiv2019

Switched Linear Systems Meet Markov Decision Processes: Stability Guaranteed Policy Synthesis

Switched linear systems are time-varying nonlinear systems whose dynamics switch between different modes, where each mode corresponds to different linear dynamics. They arise naturally to model unexpected failures, environment uncertainties or system noises during system operation. In this paper, we consider a special class of switched linear systems where the mode switches are governed by Markov decision processes (MDPs). We study the problem of synthesizing a policy in an MDP that stabilizes the switched system. Given a policy, the switched linear system becomes a Markov jump linear system whose stability conditions have been extensively studied. We make use of these stability conditions and propose three different computation approaches to find the stabilizing policy in an MDP. We derive our first approach by extending the stability conditions for a Markov jump linear system to handle switches governed by an MDP. This approach requires finding a feasible solution of a set of bilinear matrix inequalities, which makes policy synthesis typically challenging. To improve scalability, we provide two approaches based on convex optimization. We give three examples to show and compare our proposed solutions.

math.OC↗
arXiv2018

Characterizations of the upper bound of Bakry-Emery curvature

In this paper, we will present some characterizations for the upper bound of the Bakry-Emery curvature on a Riemannian manifold by using functional inequalities on path space. Moreover, some characterizations for general lower and upper bounds of Ricci curvature are also given, which extends the recent results derived by Naber \cite{N} and Wang-Wu\cite{WW}.

math.PR↗
arXiv2018

Approximation to Wiener measure on a general noncompact Riemannian manifold

In prior work \cite{AD} of Lars Andersson and Bruce K. Driver, the path space with finite interval over a compact Riemannian manifold is approximated by finite dimensional manifolds $H_{x,¶} (M)$ consisting of piecewise geodesic paths adapted to partitions $¶$ of $[0,T]$, and the associated Wiener measure is also approximated by a sequence of probability measures on finite dimensional manifolds. In this article, we will extend their results to the general path space(possibly with infinite interval) over a non-compact Riemannian manifold by using the cutoff method of compact Riemannian manifolds. Extension to the free path space. As applications, we obtain integration by parts formulas in the path space $W^T_x(M)$ and the free path space $W^T(M)$ respectively.

math.PR↗
arXiv2018

Distributed Communication-aware Motion Planning for Networked Mobile Robots under Formal Specifications

Control and communication are often tightly coupled in motion planning of networked mobile robots, due to the fact that robotic motions will affect the overall communication quality, and the quality of service (QoS) of the communication among the robots will in turn affect their coordination performance. In this paper, we propose a control theoretical motion planning framework for a team of networked mobile robots in order to accomplish high-level spatial and temporal motion objectives while optimizing communication QoS. Desired motion specifications are formulated as Signal Temporal Logic (STL), whereas the communication performances to be optimized are captured by recently proposed Spatial Temporal Reach and Escape Logic (STREL) formulas. Both the STL and STREL specifications are encoded as mixed integer linear constraints posed on the system and/or environment state variables of the mobile robot network, where satisfactory control strategies can be computed by exploiting a distributed model predictive control (MPC) approach. To the best of the authors' knowledge, we are the first to study controller synthesis for STREL specifications. A two-layer hierarchical MPC procedure is proposed to efficiently solve the problem, whose soundness and completeness are formally ensured. The effectiveness of the proposed framework is validated by simulation examples.

eess.SY↗
arXiv2018

Cost-Bounded Active Classification Using Partially Observable Markov Decision Processes

Active classification, i.e., the sequential decision-making process aimed at data acquisition for classification purposes, arises naturally in many applications, including medical diagnosis, intrusion detection, and object tracking. In this work, we study the problem of actively classifying dynamical systems with a finite set of Markov decision process (MDP) models. We are interested in finding strategies that actively interact with the dynamical system, and observe its reactions so that the true model is determined efficiently with high confidence. To this end, we present a decision-theoretic framework based on partially observable Markov decision processes (POMDPs). The proposed framework relies on assigning a classification belief (a probability distribution) to each candidate MDP model. Given an initial belief, some misclassification probabilities, a cost bound, and a finite time horizon, we design POMDP strategies leading to classification decisions. We present two different approaches to find such strategies. The first approach computes the optimal strategy "exactly" using value iteration. To overcome the computational complexity of finding exact solutions, the second approach is based on adaptive sampling to approximate the optimal probability of reaching a classification decision. We illustrate the proposed methodology using two examples from medical diagnosis and intruder detection.

eess.SY↗
arXiv2018

Stochastic Heat Equations with Values in a Manifold via Dirichlet Forms

In this paper, we prove the existence of martingale solutions to the stochastic heat equation taking values in a Riemannian manifold, which admits Wiener (Brownian bridge) measure on the Riemannian path (loop) space as an invariant measure using a suitable Dirichlet form. Using the Andersson-Driver approximation, we heuristically derive a form of the equation solved by the process given by the Dirichlet form. Moreover, we establish the log-Sobolev inequality for the Dirichlet form in the path space. In addition, some characterizations for the lower bounds of the Ricci curvature are presented related to the stochastic heat equation.

math.PR↗
arXiv2018

Beyond Keywords and Relevance: A Personalized Ad Retrieval Framework in E-Commerce Sponsored Search

On most sponsored search platforms, advertisers bid on some keywords for their advertisements (ads). Given a search request, ad retrieval module rewrites the query into bidding keywords, and uses these keywords as keys to select Top N ads through inverted indexes. In this way, an ad will not be retrieved even if queries are related when the advertiser does not bid on corresponding keywords. Moreover, most ad retrieval approaches regard rewriting and ad-selecting as two separated tasks, and focus on boosting relevance between search queries and ads. Recently, in e-commerce sponsored search more and more personalized information has been introduced, such as user profiles, long-time and real-time clicks. Personalized information makes ad retrieval able to employ more elements (e.g. real-time clicks) as search signals and retrieval keys, however it makes ad retrieval more difficult to measure ads retrieved through different signals. To address these problems, we propose a novel ad retrieval framework beyond keywords and relevance in e-commerce sponsored search. Firstly, we employ historical ad click data to initialize a hierarchical network representing signals, keys and ads, in which personalized information is introduced. Then we train a model on top of the hierarchical network by learning the weights of edges. Finally we select the best edges according to the model, boosting RPM/CTR. Experimental results on our e-commerce platform demonstrate that our ad retrieval framework achieves good performance.

cs.IR↗
arXiv2018

Privacy Verification in POMDPs via Barrier Certificates

Privacy is an increasing concern in cyber-physical systems that operates over a shared network. In this paper, we propose a method for privacy verification of cyber- physical systems modeled by Markov decision processes (MDPs) and partially-observable Markov decision processes (POMDPs) based on barrier certificates. To this end, we consider an opacity-based notion of privacy, which is characterized by the beliefs in system states. We show that the belief update equations can be represented as discrete-time switched systems, for which we propose a set of conditions for privacy verification in terms of barrier certificates. We further demonstrate that, for MDPs and for POMDPs, privacy verification can be computationally implemented by solving a set of semi-definite programs and sum-of-squares programs, respectively. The method is illustrated by an application to privacy verification of an inventory management system.

eess.SY↗
arXiv2018

POMDP Model Learning for Human Robot Collaboration

Recent years have seen human robot collaboration (HRC) quickly emerged as a hot research area at the intersection of control, robotics, and psychology. While most of the existing work in HRC focused on either low-level human-aware motion planning or HRC interface design, we are particularly interested in a formal design of HRC with respect to high-level complex missions, where it is of critical importance to obtain an accurate and meanwhile tractable human model. Instead of assuming the human model is given, we ask whether it is reasonable to learn human models from observed perception data, such as the gesture, eye movements, head motions of the human in concern. As our initial step, we adopt a partially observable Markov decision process (POMDP) model in this work as mounting evidences have suggested Markovian properties of human behaviors from psychology studies. In addition, POMDP provides a general modeling framework for sequential decision making where states are hidden and actions have stochastic outcomes. Distinct from the majority of POMDP model learning literature, we do not assume that the state, the transition structure or the bound of the number of states in POMDP model is given. Instead, we use a Bayesian non-parametric learning approach to decide the potential human states from data. Then we adopt an approach inspired by probably approximately correct (PAC) learning to obtain not only an estimation of the transition probability but also a confidence interval associated to the estimation. Then, the performance of applying the control policy derived from the estimated model is guaranteed to be sufficiently close to the true model. Finally, data collected from a driver-assistance test-bed are used to train the model, which illustrates the effectiveness of the proposed learning method.

cs.HC↗
arXiv2018

Optimizing Sponsored Search Ranking Strategy by Deep Reinforcement Learning

Sponsored search is an indispensable business model and a major revenue contributor of almost all the search engines. From the advertisers' side, participating in ranking the search results by paying for the sponsored search advertisement to attract more awareness and purchase facilitates their commercial goal. From the users' side, presenting personalized advertisement reflecting their propensity would make their online search experience more satisfactory. Sponsored search platforms rank the advertisements by a ranking function to determine the list of advertisements to show and the charging price for the advertisers. Hence, it is crucial to find a good ranking function which can simultaneously satisfy the platform, the users and the advertisers. Moreover, advertisements showing positions under different queries from different users may associate with advertisement candidates of different bid price distributions and click probability distributions, which requires the ranking functions to be optimized adaptively to the traffic characteristics. In this work, we proposed a generic framework to optimize the ranking functions by deep reinforcement learning methods. The framework is composed of two parts: an offline learning part which initializes the ranking functions by learning from a simulated advertising environment, allowing adequate exploration of the ranking function parameter space without hurting the performance of the commercial platform. An online learning part which further optimizes the ranking functions by adapting to the online data distribution. Experimental results on a large-scale sponsored search platform confirm the effectiveness of the proposed method.

cs.IR↗
arXiv2018

Privacy Preserving Controller Synthesis via Belief Abstraction

Privacy is a crucial concern in many systems in addition to their given tasks. We consider a new notion of privacy based on beliefs of the system states, which is closely related to opacity in discrete event systems. To guarantee the privacy requirement, we propose to abstract the belief space whose dynamics is shown to be mixed monotone where efficient abstraction algorithm exists. Based on the abstraction, we propose two different approaches to synthesize controllers of the system to preserve privacy with an illustrative example.

cs.CR↗
arXiv2018

Synthesis of Insertion Functions to Enforce Decentralized and Joint Opacity Properties of Discrete-event Systems

Opacity is a confidentiality property that characterizes the non-disclosure of specified secret information of a system to an outside observer. In this paper, we consider the enforcement of opacity within the discrete-event system formalism in the presence of multiple intruders. We study two cases, one without coordination among the intruders and the other with coordination. We propose appropriate notions of opacity corresponding to the two cases, respectively, and propose enforcement mechanisms for these opacity properties based on the implementation of insertion functions, which manipulates the output of the system by inserting fictitious observable events whenever necessary. The insertion mechanism is adapted to the decentralized framework to enforce opacity when no coordination exists. Furthermore, we present a coordination and refinement procedure to synthesize appropriate insertion functions to enforce opacity when intruders may coordinate with each other by following an intersection-based coordination protocol. The effectiveness of the proposed opacity-enforcement approaches is validated through illustrative examples.

cs.CR↗
arXiv2018

Parameter and Insertion Function Co-synthesis for Opacity Enhancement in Parametric Stochastic Discrete Event Systems

Opacity is a property that characterizes the system's capability to keep its "secret" from being inferred by an intruder that partially observes the system's behavior. In this paper, we are concerned with enhancing the opacity using insertion functions, while at the same time, enforcing the task specification in a parametric stochastic discrete event system. We first obtain the parametric Markov decision process that encodes all the possible insertions. Based on which, we convert this parameter and insertion function co-synthesis problem into a nonlinear program. We prove that if the output of this program satisfies all the constraints, it will be a valid solution to our problem. Therefore, the security and the capability of enforcing the task specification can be simultaneously guaranteed.

cs.CR↗