Research papers and code for "Yuan Yu":
Detecting a change point is a crucial task in statistics that has been recently extended to the quantum realm. A source state generator that emits a series of single photons in a default state suffers an alteration at some point and starts to emit photons in a mutated state. The problem consists in identifying the point where the change took place. In this work, we consider a learning agent that applies Bayesian inference on experimental data to solve this problem. This learning machine adjusts the measurement over each photon according to the past experimental results finds the change position in an online fashion. Our results show that the local-detection success probability can be largely improved by using such a machine learning technique. This protocol provides a tool for improvement in many applications where a sequence of identical quantum states is required.

* Phys. Rev. A 98, 040301 (2018)
Click to Read Paper and Get Code
With the aim to improve the performance of feature matching, we present an unsupervised approach to fuse various local descriptors in the space of homographies. Inspired by the observation that the homographies of correct feature correspondences vary smoothly along the spatial domain, our approach stands on the unsupervised nature of feature matching, and can select a good descriptor for matching each feature point. Specifically, the homography space serves as the common domain, in which a correspondence obtained by any descriptor is considered as a point, for integrating various heterogeneous descriptors. Both geometric coherence and spatial continuity among correspondences are considered via computing their geodesic distances in the space. In this way, mutual verification across different descriptors is allowed, and correct correspondences will be highlighted with a high degree of consistency (i.e., short geodesic distances here). It follows that one-class SVM can be applied to identifying these correct correspondences, and boosts the performance of feature matching. The proposed approach is comprehensively compared with the state-of-the-art approaches, and evaluated on four benchmarks of image matching. The promising results manifest its effectiveness.

Click to Read Paper and Get Code
In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. The user initiates the process by uploading a sequence of photos. Dixit first extracts text terms from each photo which describe the objects (e.g., boy, bike) or actions (e.g., sleep) in the photo, and then allows the user to add new terms or remove existing terms. Dixit then generates a short story based on these terms. Behind the scenes, Dixit uses an LSTM-based model trained on image caption data and FrameNet to distill terms from each image and utilizes a transformer decoder to compose a context-coherent story. Users change images or terms iteratively with Dixit to create the most ideal story. Dixit also allows users to manually edit and rate stories. The proposed procedure opens up possibilities for interpretable and controllable visual storytelling, allowing users to understand the story formation rationale and to intervene in the generation process.

* WWW'19 Demo, demo video: https://www.youtube.com/watch?v=CUu1MOwnveI
Click to Read Paper and Get Code
Variance plays a crucial role in risk-sensitive reinforcement learning, and most risk measures can be analyzed via variance. In this paper, we consider two law-invariant risks as examples: mean-variance risk and exponential utility risk. With the aid of the state-augmentation transformation (SAT), we show that, the two risks can be estimated in Markov decision processes (MDPs) with a stochastic transition-based reward and a randomized policy. To relieve the enlarged state space, a novel definition of isotopic states is proposed for state lumping, considering the special structure of the transformed transition probability. In the numerical experiment, we illustrate state lumping in the SAT, errors from a naive reward simplification, and the validity of the SAT for the two risk estimations.

* 7 pages, 7 figures, SMC 2019 accepted. arXiv admin note: text overlap with arXiv:1907.04269
Click to Read Paper and Get Code
Although the general deterministic reward function in MDPs takes three arguments - current state, action, and next state; it is often simplified to a function of two arguments - current state and action. The former is called a transition-based reward function, whereas the latter is called a state-based reward function. When the objective is a function of the expected cumulative reward only, this simplification works perfectly. However, when the objective is risk-sensitive - e.g., depends on the reward distribution, this simplification leads to incorrect values of the objective. This paper studies the distribution estimation of the cumulative discounted reward in infinite-horizon MDPs with finite state and action spaces. First, by taking the Value-at-Risk (VaR) objective as an example, we illustrate and analyze the error from the above simplification on the reward distribution. Next, we propose a transformation for MDPs to preserve the reward distribution and convert transition-based reward functions to deterministic state-based reward functions. This transformation works whether the transition-based reward function is deterministic or stochastic. Lastly, we show how to estimate the reward distribution after applying the proposed transformation in different settings, provided that the distribution is approximately normal.

Click to Read Paper and Get Code
The culture of sharing instead of ownership is sharply increasing in individuals behaviors. Particularly in transportation, concepts of sharing a ride in either carpooling or ridesharing have been recently adopted. An efficient optimization approach to match passengers in real-time is the core of any ridesharing system. In this paper, we model ridesharing as an online matching problem on general graphs such that passengers do not drive private cars and use shared taxis. We propose an optimization algorithm to solve it. The outlined algorithm calculates the optimal waiting time when a passenger arrives. This leads to a matching with minimal overall overheads while maximizing the number of partnerships. To evaluate the behavior of our algorithm, we used NYC taxi real-life data set. Results represent a substantial reduction in overall overheads.

Click to Read Paper and Get Code
This paper studies Value-at-Risk (VaR) problems in short- and long-horizon Markov decision processes (MDPs) with finite state space and two different reward functions. Firstly we examine the effects of two reward functions under two criteria in a short-horizon MDP. We show that under the VaR criterion, when the original reward function is on both current and next states, the reward simplification will change the VaR. Secondly, for long-horizon MDPs, we estimate the Pareto front of the total reward distribution set with the aid of spectral theory and the central limit theorem. Since the estimation is for a Markov process with the simplified reward function only, we present a transformation algorithm for the Markov process with the original reward function, in order to estimate the Pareto front with an intact total reward distribution.

* 23 pages, 5 figures
Click to Read Paper and Get Code
Instead of studying the properties of social relationship from an objective view, in this paper, we focus on individuals' subjective and asymmetric opinions on their interrelationships. Inspired by the theories from sociolinguistics, we investigate two individuals' opinions on their interrelationship with their interactive language features. Eliminating the difference of personal language style, we clarify that the asymmetry of interactive language feature values can indicate individuals' asymmetric opinions on their interrelationship. We also discuss how the degree of opinions' asymmetry is related to the individuals' personality traits. Furthermore, to measure the individuals' asymmetric opinions on interrelationship concretely, we develop a novel model synthetizing interactive language and social network features. The experimental results with Enron email dataset provide multiple evidences of the asymmetric opinions on interrelationship, and also verify the effectiveness of the proposed model in measuring the degree of opinions' asymmetry.

Click to Read Paper and Get Code
We consider the problem of online linear regression on individual sequences. The goal in this paper is for the forecaster to output sequential predictions which are, after T time rounds, almost as good as the ones output by the best linear predictor in a given L1-ball in R^d. We consider both the cases where the dimension d is small and large relative to the time horizon T. We first present regret bounds with optimal dependencies on the sizes U, X and Y of the L1-ball, the input data and the observations. The minimax regret is shown to exhibit a regime transition around the point d = sqrt(T) U X / (2 Y). Furthermore, we present efficient algorithms that are adaptive, i.e., they do not require the knowledge of U, X, and Y, but still achieve nearly optimal regret bounds.

Click to Read Paper and Get Code
Recently most popular tracking frameworks focus on 2D image sequences. They seldom track the 3D object in point clouds. In this paper, we propose PointIT, a fast, simple tracking method based on 3D on-road instance segmentation. Firstly, we transform 3D LiDAR data into the spherical image with the size of 64 x 512 x 4 and feed it into instance segment model to get the predicted instance mask for each class. Then we use MobileNet as our primary encoder instead of the original ResNet to reduce the computational complexity. Finally, we extend the Sort algorithm with this instance framework to realize tracking in the 3D LiDAR point cloud data. The model is trained on the spherical images dataset with the corresponding instance label masks which are provided by KITTI 3D Object Track dataset. According to the experiment results, our network can achieve on Average Precision (AP) of 0.617 and the performance of multi-tracking task has also been improved.

Click to Read Paper and Get Code
An excellent self-driving car is expected to take its passengers safely and efficiently from one place to another. However, different ways of defining safety and efficiency may significantly affect the conclusion we make. In this paper, we give formal definitions to the safe state of a road and safe state of a vehicle using the syntax of linear temporal logic (LTL). We then propose the concept of safe driving throughput (SDT) and safe driving capacity (SDC) which measure the amount of vehicles in the safe state on a road. We analyze how SDT is affected by different factors. We show the analytic difference of SDC between the road with perception-based vehicles (PBV) and the road with cooperative-based vehicles (CBV). We claim that through proper design, the SDC of the road filled with PBVs will be upper-bounded by the SDC of the road filled with CBVs.

* 5 pages, VTC 2018
Click to Read Paper and Get Code
The performance of face detection has been largely improved with the development of convolutional neural network. However, the occlusion issue due to mask and sunglasses, is still a challenging problem. The improvement on the recall of these occluded cases usually brings the risk of high false positives. In this paper, we present a novel face detector called Face Attention Network (FAN), which can significantly improve the recall of the face detection problem in the occluded case without compromising the speed. More specifically, we propose a new anchor-level attention, which will highlight the features from the face region. Integrated with our anchor assign strategy and data augmentation techniques, we obtain state-of-art results on public face detection benchmarks like WiderFace and MAFA. The code will be released for reproduction.

Click to Read Paper and Get Code
We introduce the functional bandit problem, where the objective is to find an arm that optimises a known functional of the unknown arm-reward distributions. These problems arise in many settings such as maximum entropy methods in natural language processing, and risk-averse decision-making, but current best-arm identification techniques fail in these domains. We propose a new approach, that combines functional estimation and arm elimination, to tackle this problem. This method achieves provably efficient performance guarantees. In addition, we illustrate this method on a number of important functionals in risk management and information theory, and refine our generic theoretical results in those cases.

Click to Read Paper and Get Code
We present a scheme for sequential decision making with a risk-sensitive objective and constraints in a dynamic environment. A neural network is trained as an approximator of the mapping from parameter space to space of risk and policy with risk-sensitive constraints. For a given risk-sensitive problem, in which the objective and constraints are, or can be estimated by, functions of the mean and variance of return, we generate a synthetic dataset as training data. Parameters defining a targeted process might be dynamic, i.e., they might vary over time, so we sample them within specified intervals to deal with these dynamics. We show that: i). Most risk measures can be estimated using return variance; ii). By virtue of the state-augmentation transformation, practical problems modeled by Markov decision processes with stochastic rewards can be solved in a risk-sensitive scenario; and iii). The proposed scheme is validated by a numerical experiment.

* 20 pages, 3 figures
Click to Read Paper and Get Code
We aim to study the multi-scale receptive fields of a single convolutional neural network to detect faces of varied scales. This paper presents our Multi-Scale Receptive Field Face Detector (MSFD), which has superior performance on detecting faces at different scales and enjoys real-time inference speed. MSFD agglomerates context and texture by hierarchical structure. More additional information and rich receptive field bring significant improvement but generate marginal time consumption. We simultaneously propose an anchor assignment strategy which can cover faces with a wide range of scales to improve the recall rate of small faces and rotated faces. To reduce the false positive rate, we train our detector with focal loss which keeps the easy samples from overwhelming. As a result, MSFD reaches superior results on the FDDB, Pascal-Faces and WIDER FACE datasets, and can run at 31 FPS on GPU for VGA-resolution images.

* Accepted by ICPR 2018
Click to Read Paper and Get Code
To overcome the limitations of Neural Programmer-Interpreters (NPI) in its universality and learnability, we propose the incorporation of combinator abstraction into neural programing and a new NPI architecture to support this abstraction, which we call Combinatory Neural Programmer-Interpreter (CNPI). Combinator abstraction dramatically reduces the number and complexity of programs that need to be interpreted by the core controller of CNPI, while still allowing the CNPI to represent and interpret arbitrary complex programs by the collaboration of the core with the other components. We propose a small set of four combinators to capture the most pervasive programming patterns. Due to the finiteness and simplicity of this combinator set and the offloading of some burden of interpretation from the core, we are able construct a CNPI that is universal with respect to the set of all combinatorizable programs, which is adequate for solving most algorithmic tasks. Moreover, besides supervised training on execution traces, CNPI can be trained by policy gradient reinforcement learning with appropriately designed curricula.

* Published as a conference paper at ICLR 2018
Click to Read Paper and Get Code
In many "smart city" applications, congestion arises in part due to the nature of signals received by individuals from a central authority. In the model of Marecek et al. [arXiv:1406.7639, Int. J. Control 88(10), 2015], each agent uses one out of multiple resources at each time instant. The per-use cost of a resource depends on the number of concurrent users. A central authority has up-to-date knowledge of the congestion across all resources and uses randomisation to provide a scalar or an interval for each resource at each time. In this paper, the interval to broadcast per resource is obtained by taking the minima and maxima of costs observed within a time window of length r, rather than by randomisation. We show that the resulting distribution of agents across resources also converges in distribution, under plausible assumptions about the evolution of the population over time.

* International Journal of Control (2016) 89(10): 1972-1984
Click to Read Paper and Get Code
For vehicle sharing schemes, where drop-off positions are not fixed, we propose a pricing scheme, where the price depends in part on the distance between where a vehicle is being dropped off and where the closest shared vehicle is parked. Under certain restrictive assumptions, we show that this pricing leads to a socially optimal spread of the vehicles within a region.

Click to Read Paper and Get Code
We consider one-way vehicle sharing systems where customers can rent a car at one station and drop it off at another. The problem we address is to optimize the distribution of cars, and quality of service, by pricing rentals appropriately. We propose a bidding approach that is inspired from auctions and takes into account the significant uncertainty inherent in the problem data (e.g., pick-up and drop-off locations, time of requests, and duration of trips). Specifically, in contrast to current vehicle sharing systems, the operator does not set prices. Instead, customers submit bids and the operator decides whether to rent or not. The operator can even accept negative bids to motivate drivers to rebalance available cars to unpopular destinations within a city. We model the operator's sequential decision-making problem as a \emph{constrained Markov decision problem} (CMDP) and propose and rigorously analyze a novel two phase $Q$-learning algorithm for its solution. Numerical experiments are presented and discussed.

* Submitted to AISTATS 2016
Click to Read Paper and Get Code
We propose a quantum data fitting algorithm for non-sparse matrices, which is based on the Quantum Singular Value Estimation (QSVE) subroutine and a novel efficient method for recovering the signs of eigenvalues. Our algorithm generalizes the quantum data fitting algorithm of Wiebe, Braun, and Lloyd for sparse and well-conditioned matrices by adding a regularization term to avoid the over-fitting problem, which is a very important problem in machine learning. As a result, the algorithm achieves a sparsity-independent runtime of $O(\kappa^2\sqrt{N}\mathrm{polylog}(N)/(\epsilon\log\kappa))$ for an $N\times N$ dimensional Hermitian matrix $\bm{F}$, where $\kappa$ denotes the condition number of $\bm{F}$ and $\epsilon$ is the precision parameter. This amounts to a polynomial speedup on the dimension of matrices when compared with the classical data fitting algorithms, and a strictly less than quadratic dependence on $\kappa$.

* 5 pages
Click to Read Paper and Get Code