arXiv subjects

Yifan Xu

Publications and source records attributed to Yifan Xu.

153 records · Page 9Linked to original sources

arXiv2020

Thompson Sampling for Combinatorial Semi-bandits with Sleeping Arms and Long-Term Fairness Constraints

We study the combinatorial sleeping multi-armed semi-bandit problem with long-term fairness constraints~(CSMAB-F). To address the problem, we adopt Thompson Sampling~(TS) to maximize the total rewards and use virtual queue techniques to handle the fairness constraints, and design an algorithm called \emph{TS with beta priors and Bernoulli likelihoods for CSMAB-F~(TSCSF-B)}. Further, we prove TSCSF-B can satisfy the fairness constraints, and the time-averaged regret is upper bounded by $\frac{N}{2η} + O\left(\frac{\sqrt{mNT\ln T}}{T}\right)$, where $N$ is the total number of arms, $m$ is the maximum number of arms that can be pulled simultaneously in each round~(the cardinality constraint) and $η$ is the parameter trading off fairness for rewards. By relaxing the fairness constraints (i.e., let $η\rightarrow \infty$), the bound boils down to the first problem-independent bound of TS algorithms for combinatorial sleeping multi-armed semi-bandit problems. Finally, we perform numerical experiments and use a high-rating movie recommendation application to show the effectiveness and efficiency of the proposed algorithm.

cs.LG↗

arXiv2020

Guided Variational Autoencoder for Disentanglement Learning

We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. The learning objective is achieved by providing signals to the latent encoding/embedding in VAE without changing its main backbone architecture, hence retaining the desirable properties of the VAE. We design an unsupervised strategy and a supervised strategy in Guided-VAE and observe enhanced modeling and controlling capability over the vanilla VAE. In the unsupervised strategy, we guide the VAE learning by introducing a lightweight decoder that learns latent geometric transformation and principal components; in the supervised strategy, we use an adversarial excitation and inhibition mechanism to encourage the disentanglement of the latent variables. Guided-VAE enjoys its transparency and simplicity for the general representation learning task, as well as disentanglement learning. On a number of experiments for representation learning, improved synthesis/sampling, better disentanglement for classification, and reduced classification errors in meta-learning have been observed.

cs.CV↗

arXiv2020

Rethinking Exposure Bias In Language Modeling

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training corpus. Recently, several generative adversarial networks (GANs) and reinforcement learning (RL) methods have been introduced to alleviate this problem. Nonetheless, a common issue in RL and GANs training is the sparsity of reward signals. In this paper, we adopt two simple strategies, multi-range reinforcing, and multi-entropy sampling, to amplify and denoise the reward signal. Our model produces an improvement over competing models with regards to BLEU scores and road exam, a new metric we designed to measure the robustness against exposure bias in language models.

cs.CL↗

arXiv2019

Neural Program Synthesis By Self-Learning

Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the CPU and RAM. We develop a neural program synthesis algorithm, AutoAssemblet, learned via self-learning reinforcement learning that explores the large code space efficiently. Policy networks and value networks are learned to reduce the breadth and depth of the Monte Carlo Tree Search, resulting in better synthesis performance. We also propose an effective multi-entropy policy sampling technique to alleviate online update correlations. We apply AutoAssemblet to basic programming tasks and show significant higher success rates compared to several competing baselines.

cs.LG↗

arXiv2019

EEG-Based Driver Drowsiness Estimation Using Feature Weighted Episodic Training

Drowsy driving is pervasive, and also a major cause of traffic accidents. Estimating a driver's drowsiness level by monitoring the electroencephalogram (EEG) signal and taking preventative actions accordingly may improve driving safety. However, individual differences among different drivers make this task very challenging. A calibration session is usually required to collect some subject-specific data and tune the model parameters before applying it to a new subject, which is very inconvenient and not user-friendly. Many approaches have been proposed to reduce the calibration effort, but few can completely eliminate it. This paper proposes a novel approach, feature weighted episodic training (FWET), to completely eliminate the calibration requirement. It integrates two techniques: feature weighting to learn the importance of different features, and episodic training for domain generalization. Experiments on EEG-based driver drowsiness estimation demonstrated that both feature weighting and episodic training are effective, and their integration can further improve the generalization performance. FWET does not need any labelled or unlabelled calibration data from the new subject, and hence could be very useful in plug-and-play brain-computer interfaces.

cs.HC↗

arXiv2019

Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos

Time-lapse is a technology used to record the development of embryos during in-vitro fertilization (IVF). Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF. This paper proposes a multi-task deep learning with dynamic programming (MTDL-DP) approach for this purpose. It first uses MTDL to pre-classify each frame in the time-lapse video to an embryo development stage, and then DP to optimize the stage sequence so that the stage number is monotonically non-decreasing, which usually holds in practice. Different MTDL frameworks, e.g., one-to-many, many-to-one, and many-to-many, are investigated. It is shown that the one-to-many MTDL framework achieved the best compromise between performance and computational cost. To our knowledge, this is the first study that applies MTDL to embryo early development stage classification from time-lapse videos.

eess.IV↗

arXiv2019

LISA: a MATLAB package for Longitudinal Image Sequence Analysis

Large sequences of images (or movies) can now be obtained on an unprecedented scale, which poses fundamental challenges to the existing image analysis techniques. The challenges include heterogeneity, (automatic) alignment, multiple comparisons, potential artifacts, and hidden noises. This paper introduces our MATLAB package, Longitudinal Image Sequence Analysis (LISA), as a one-stop ensemble of image processing and analysis tool for comparing a general class of images from either different times, sessions, or subjects. Given two contrasting sequences of images, the image processing in LISA starts with selecting a region of interest in two representative images, followed by automatic or manual segmentation and registration. Automatic segmentation de-noises an image using a mixture of Gaussian distributions of the pixel intensity values, while manual segmentation applies a user-chosen intensity cut-off value to filter out noises. Automatic registration aligns the contrasting images based on a mid-line regression whereas manual registration lines up the images along a reference line formed by two user-selected points. The processed images are then rendered for simultaneous statistical comparisons to generate D, S, T, and P-maps. The D map represents a curated difference of contrasting images, the S map is the non-parametrically smoothed differences, the T map presents the variance-adjusted, smoothed differences, and the P-map provides multiplicity-controlled p-values. These maps reveal the regions with significant differences due to either longitudinal, subject-specific, or treatment changes. A user can skip the image processing step to dive directly into the statistical analysis step if the images have already been processed. Hence, LISA offers flexibility in applying other image pre-processing tools. LISA also has a parallel computing option for high definition images.

stat.CO↗

arXiv2019

A NUMA-Aware Provably-Efficient Task-Parallel Platform Based on the Work-First Principle

Task parallelism is designed to simplify the task of parallel programming. When executing a task parallel program on modern NUMA architectures, it can fail to scale due to the phenomenon called work inflation, where the overall processing time that multiple cores spend on doing useful work is higher compared to the time required to do the same amount of work on one core, due to effects experienced only during parallel executions such as additional cache misses, remote memory accesses, and memory bandwidth issues. It's possible to mitigate work inflation by co-locating the computation with the data, but this is nontrivial to do with task parallel programs. First, by design, the scheduling for task parallel programs is automated, giving the user little control over where the computation is performed. Second, the platforms tend to employ work stealing, which provides strong theoretical guarantees, but its randomized protocol for load balancing does not discern between work items that are far away versus ones that are closer. In this work, we propose NUMA-WS, a NUMA-aware task parallel platform engineering based on the work-first principle. By abiding by the work-first principle, we are able to obtain a platform that is work efficient, provides the same theoretical guarantees as the classic work stealing scheduler, and mitigates work inflation. Furthermore, we implemented a prototype platform by modifying Intel's Cilk Plus runtime system and empirically demonstrate that the resulting system is work efficient and scalable.

cs.DC↗

arXiv2018

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel convolutional architecture, termed SpiderCNN, to efficiently extract geometric features from point clouds. SpiderCNN is comprised of units called SpiderConv, which extend convolutional operations from regular grids to irregular point sets that can be embedded in R^n, by parametrizing a family of convolutional filters. We design the filter as a product of a simple step function that captures local geodesic information and a Taylor polynomial that ensures the expressiveness. SpiderCNN inherits the multi-scale hierarchical architecture from classical CNNs, which allows it to extract semantic deep features. Experiments on ModelNet40 demonstrate that SpiderCNN achieves state-of-the-art accuracy 92.4% on standard benchmarks, and shows competitive performance on segmentation task.

cs.CV↗