arXiv subjects

Yi Zhou

Publications and source records attributed to Yi Zhou.

At least 415 records · Page 23Linked to original sources

arXiv2021

Group Whitening: Balancing Learning Efficiency and Representational Capacity

Batch normalization (BN) is an important technique commonly incorporated into deep learning models to perform standardization within mini-batches. The merits of BN in improving a model's learning efficiency can be further amplified by applying whitening, while its drawbacks in estimating population statistics for inference can be avoided through group normalization (GN). This paper proposes group whitening (GW), which exploits the advantages of the whitening operation and avoids the disadvantages of normalization within mini-batches. In addition, we analyze the constraints imposed on features by normalization, and show how the batch size (group number) affects the performance of batch (group) normalized networks, from the perspective of model's representational capacity. This analysis provides theoretical guidance for applying GW in practice. Finally, we apply the proposed GW to ResNet and ResNeXt architectures and conduct experiments on the ImageNet and COCO benchmarks. Results show that GW consistently improves the performance of different architectures, with absolute gains of $1.02\%$ $\sim$ $1.49\%$ in top-1 accuracy on ImageNet and $1.82\%$ $\sim$ $3.21\%$ in bounding box AP on COCO.

cs.LG↗

arXiv2021

Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity

Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control. Recently, the finite-time analysis of Greedy-GQ has been developed under linear function approximation and Markovian sampling, and the algorithm is shown to achieve an $ε$-stationary point with a sample complexity in the order of $\mathcal{O}(ε^{-3})$. Such a high sample complexity is due to the large variance induced by the Markovian samples. In this paper, we propose a variance-reduced Greedy-GQ (VR-Greedy-GQ) algorithm for off-policy optimal control. In particular, the algorithm applies the SVRG-based variance reduction scheme to reduce the stochastic variance of the two time-scale updates. We study the finite-time convergence of VR-Greedy-GQ under linear function approximation and Markovian sampling and show that the algorithm achieves a much smaller bias and variance error than the original Greedy-GQ. In particular, we prove that VR-Greedy-GQ achieves an improved sample complexity that is in the order of $\mathcal{O}(ε^{-2})$. We further compare the performance of VR-Greedy-GQ with that of Greedy-GQ in various RL experiments to corroborate our theoretical findings.

cs.LG↗

arXiv2021

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing

Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks. Although several heuristic defenses are proposed to enhance the robustness of federated learning, they do not provide certifiable robustness guarantees. In this paper, we incorporate randomized smoothing techniques into federated adversarial training to enable data-private distributed learning with certifiable robustness to test-time adversarial perturbations. Our experiments show that such an advanced federated adversarial learning framework can deliver models as robust as those trained by the centralized training. Further, this enables provably-robust classifiers to $\ell_2$-bounded adversarial perturbations in a distributed setup. We also show that one-point gradient estimation based training approach is $2-3\times$ faster than popular stochastic estimator based approach without any noticeable certified robustness differences.

cs.LG↗

arXiv2021

Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity

The finite-time convergence of off-policy TD learning has been comprehensively studied recently. However, such a type of convergence has not been well established for off-policy TD learning in the multi-agent setting, which covers broader applications and is fundamentally more challenging. This work develops two decentralized TD with correction (TDC) algorithms for multi-agent off-policy TD learning under Markovian sampling. In particular, our algorithms preserve full privacy of the actions, policies and rewards of the agents, and adopt mini-batch sampling to reduce the sampling variance and communication frequency. Under Markovian sampling and linear function approximation, we proved that the finite-time sample complexity of both algorithms for achieving an $ε$-accurate solution is in the order of $\mathcal{O}(ε^{-1}\ln ε^{-1})$, matching the near-optimal sample complexity of centralized TD(0) and TDC. Importantly, the communication complexity of our algorithms is in the order of $\mathcal{O}(\ln ε^{-1})$, which is significantly lower than the communication complexity $\mathcal{O}(ε^{-1}\ln ε^{-1})$ of the existing decentralized TD(0). Experiments corroborate our theoretical findings.

cs.LG↗

arXiv2021

Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification

Chest X-rays are an important and accessible clinical imaging tool for the detection of many thoracic diseases. Over the past decade, deep learning, with a focus on the convolutional neural network (CNN), has become the most powerful computer-aided diagnosis technology for improving disease identification performance. However, training an effective and robust deep CNN usually requires a large amount of data with high annotation quality. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. Thus, existing public chest X-ray datasets usually adopt language pattern based methods to automatically mine labels from reports. However, this results in label uncertainty and inconsistency. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods from two perspectives to improve a single model's disease identification performance, rather than focusing on an ensemble of models. MODL integrates multiple models to obtain a soft label distribution for optimizing the single target model, which can reduce the effects of original label uncertainty. Moreover, KNNS aims to enhance the robustness of the target model to provide consistent predictions on images with similar medical findings. Extensive experiments on the public NIH Chest X-ray and CheXpert datasets show that our model achieves consistent improvements over the state-of-the-art methods.

cs.CV↗

arXiv2021

Event-based Stereo Visual Odometry

Event-based cameras are bio-inspired vision sensors whose pixels work independently from each other and respond asynchronously to brightness changes, with microsecond resolution. Their advantages make it possible to tackle challenging scenarios in robotics, such as high-speed and high dynamic range scenes. We present a solution to the problem of visual odometry from the data acquired by a stereo event-based camera rig. Our system follows a parallel tracking-and-mapping approach, where novel solutions to each subproblem (3D reconstruction and camera pose estimation) are developed with two objectives in mind: being principled and efficient, for real-time operation with commodity hardware. To this end, we seek to maximize the spatio-temporal consistency of stereo event-based data while using a simple and efficient representation. Specifically, the mapping module builds a semi-dense 3D map of the scene by fusing depth estimates from multiple local viewpoints (obtained by spatio-temporal consistency) in a probabilistic fashion. The tracking module recovers the pose of the stereo rig by solving a registration problem that naturally arises due to the chosen map and event data representation. Experiments on publicly available datasets and on our own recordings demonstrate the versatility of the proposed method in natural scenes with general 6-DoF motion. The system successfully leverages the advantages of event-based cameras to perform visual odometry in challenging illumination conditions, such as low-light and high dynamic range, while running in real-time on a standard CPU. We release the software and dataset under an open source licence to foster research in the emerging topic of event-based SLAM.

cs.CV↗

arXiv2021

Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry

The gradient descent-ascent (GDA) algorithm has been widely applied to solve minimax optimization problems. In order to achieve convergent policy parameters for minimax optimization, it is important that GDA generates convergent variable sequences rather than convergent sequences of function values or gradient norms. However, the variable convergence of GDA has been proved only under convexity geometries, and there lacks understanding for general nonconvex minimax optimization. This paper fills such a gap by studying the convergence of a more general proximal-GDA for regularized nonconvex-strongly-concave minimax optimization. Specifically, we show that proximal-GDA admits a novel Lyapunov function, which monotonically decreases in the minimax optimization process and drives the variable sequence to a critical point. By leveraging this Lyapunov function and the KŁ geometry that parameterizes the local geometries of general nonconvex functions, we formally establish the variable convergence of proximal-GDA to a critical point $x^*$, i.e., $x_t\to x^*, y_t\to y^*(x^*)$. Furthermore, over the full spectrum of the KŁ-parameterized geometry, we show that proximal-GDA achieves different types of convergence rates ranging from sublinear convergence up to finite-step convergence, depending on the geometry associated with the KŁ parameter. This is the first theoretical result on the variable convergence for nonconvex minimax optimization.

math.OC↗

arXiv2021

Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning

Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks. This paper focuses on characterizing and understanding its impact on backdooring attacks in federated learning through comprehensive experiments using synthetic and the LEAF benchmarks. The initial impression driven by our experimental results suggests that data heterogeneity is the dominant factor in the effectiveness of attacks and it may be a redemption for defending against backdooring as it makes the attack less efficient, more challenging to design effective attack strategies, and the attack result also becomes less predictable. However, with further investigations, we found data heterogeneity is more of a curse than a redemption as the attack effectiveness can be significantly boosted by simply adjusting the client-side backdooring timing. More importantly,data heterogeneity may result in overfitting at the local training of benign clients, which can be utilized by attackers to disguise themselves and fool skewed-feature based defenses. In addition, effective attack strategies can be made by adjusting attack data distribution. Finally, we discuss the potential directions of defending the curses brought by data heterogeneity. The results and lessons learned from our extensive experiments and analysis offer new insights for designing robust federated learning methods and systems

cs.LG↗

arXiv2021

Global existence for semilinear wave equations with scaling invariant damping in 3-D

Global existence for small data Cauchy problem of semilinear wave equations with scaling invariant damping in 3-D is established in this work, assuming that the data are radial and the constant in front of the damping belongs to $[1.5, 2)$. The proof is based on a weighted $L^2-L^2$ estimate for inhomogeneous wave equation, which is established by interpolating between energy estimate and Morawetz type estimate.

math.AP↗

arXiv2021

Graph topology invariant gradient and sampling complexity for decentralized and stochastic optimization

One fundamental problem in decentralized multi-agent optimization is the trade-off between gradient/sampling complexity and communication complexity. We propose new algorithms whose gradient and sampling complexities are graph topology invariant while their communication complexities remain optimal. For convex smooth deterministic problems, we propose a primal dual sliding (PDS) algorithm that computes an $ε$-solution with $O((\tilde{L}/ε)^{1/2})$ gradient and $O((\tilde{L}/ε)^{1/2}+\|\mathcal{A}\|/ε)$ communication complexities, where $\tilde{L}$ is the smoothness parameter of the objective and $\mathcal{A}$ is related to either the graph Laplacian or the transpose of the oriented incidence matrix of the communication network. The results can be improved to $O((\tilde{L}/μ)^{1/2}\log(1/ε))$ and $O((\tilde{L}/μ)^{1/2}\log(1/ε) + \|\mathcal{A}\|/ε^{1/2})$ respectively with $μ$-strong convexity. We also propose a stochastic variant, the primal dual sliding (SPDS) algorithm for problems with stochastic gradients. The SPDS algorithm utilizes the mini-batch technique and enables the agents to perform sampling and communication simultaneously. It computes a stochastic $ε$-solution with $O((\tilde{L}/ε)^{1/2} + (σ/ε)^2)$ sampling complexity, which can be improved to $O((\tilde{L}/μ)^{1/2}\log(1/ε) + σ^2/ε)$ with strong convexity. Here $σ^2$ is the variance. The communication complexities of SPDS remain the same as that of the deterministic case. All the aforementioned gradient and sampling complexities match the lower complexity bounds for centralized convex smooth optimization and are independent of the network structure. To the best of our knowledge, these gradient and sampling complexities have not been obtained before for decentralized optimization over a constraint feasible set.

math.OC↗

arXiv2021

Transfer Learning from Speech Synthesis to Voice Conversion with Non-Parallel Training Data

This paper presents a novel framework to build a voice conversion (VC) system by learning from a text-to-speech (TTS) synthesis system, that is called TTS-VC transfer learning. We first develop a multi-speaker speech synthesis system with sequence-to-sequence encoder-decoder architecture, where the encoder extracts robust linguistic representations of text, and the decoder, conditioned on target speaker embedding, takes the context vectors and the attention recurrent network cell output to generate target acoustic features. We take advantage of the fact that TTS system maps input text to speaker independent context vectors, and reuse such a mapping to supervise the training of latent representations of an encoder-decoder voice conversion system. In the voice conversion system, the encoder takes speech instead of text as input, while the decoder is functionally similar to TTS decoder. As we condition the decoder on speaker embedding, the system can be trained on non-parallel data for any-to-any voice conversion. During voice conversion training, we present both text and speech to speech synthesis and voice conversion networks respectively. At run-time, the voice conversion network uses its own encoder-decoder architecture. Experiments show that the proposed approach outperforms two competitive voice conversion baselines consistently, namely phonetic posteriorgram and variational autoencoder methods, in terms of speech quality, naturalness, and speaker similarity.

eess.AS↗

arXiv2020

Enhancing Balanced Graph Edge Partition with Effective Local Search

Graph partition is a key component to achieve workload balance and reduce job completion time in parallel graph processing systems. Among the various partition strategies, edge partition has demonstrated more promising performance in power-law graphs than vertex partition and thereby has been more widely adopted as the default partition strategy by existing graph systems. The graph edge partition problem, which is to split the edge set into multiple balanced parts to minimize the total number of copied vertices, has been widely studied from the view of optimization and algorithms. In this paper, we study local search algorithms for this problem to further improve the partition results from existing methods. More specifically, we propose two novel concepts, namely adjustable edges and blocks. Based on these, we develop a greedy heuristic as well as an improved search algorithm utilizing the property of the max-flow model. To evaluate the performance of our algorithms, we first provide adequate theoretical analysis in terms of the approximation quality. We significantly improve the previously known approximation ratio for this problem. Then we conduct extensive experiments on a large number of benchmark datasets and state-of-the-art edge partition strategies. The results show that our proposed local search framework can further improve the quality of graph partition by a wide margin.

cs.DS↗

arXiv2020

Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment

The present paper reviews the classical problem of free-form curve registration and applies it to an efficient RGBD visual odometry system called Canny-VO, as it efficiently tracks all Canny edge features extracted from the images. Two replacements for the distance transformation commonly used in edge registration are proposed: Approximate Nearest Neighbour Fields and Oriented Nearest Neighbour Fields. 3D2D edge alignment benefits from these alternative formulations in terms of both efficiency and accuracy. It removes the need for the more computationally demanding paradigms of datato-model registration, bilinear interpolation, and sub-gradient computation. To ensure robustness of the system in the presence of outliers and sensor noise, the registration is formulated as a maximum a posteriori problem, and the resulting weighted least squares objective is solved by the iteratively re-weighted least squares method. A variety of robust weight functions are investigated and the optimal choice is made based on the statistics of the residual errors. Efficiency is furthermore boosted by an adaptively sampled definition of the nearest neighbour fields. Extensive evaluations on public SLAM benchmark sequences demonstrate state-of-the-art performance and an advantage over classical Euclidean distance fields.

cs.CV↗

arXiv2020

A thermal bonding method for manufacturing Micromegas detectors

For manufacturing Micromegas detectors, the "bulk" method based on photoetching, was successfully developed and widely used in nuclear and particle physics experiments. However, the complexity of the method requires a considerable number of advanced instruments and processing, limiting the accessibility of this method for production of Micromegas detectors. In view of these limitations with the bulk method, a new method based on thermal bonding technique (TBM) has been developed to manufacture Micromegas detectors in a much simplified and efficient way without etching. This paper describes the TBM in detail and presents performance of the Micromegas detectors built with the TBM. The effectiveness of this method was investigated by testing Micromegas detector prototypes built with the method. Both X-rays and electron beams were used to characterize the prototypes in a gas mixture of argon and CO2 (7%). A typical energy resolution of ~16% (full width at half maximum, FWHM) and an absolute gain greater than 10^4 were obtained with 5.9 keV X-rays. Detection efficiency greater than 98% and a spatial resolution of ~65 μm were achieved using a 5 GeV electron beam at the DESY test-beam facility. The gas gain of a Micromegas detector could reach up to 10^5 with a uniformity of better than 10% when the size of the avalanche gap was optimized thanks to the flexibility of the TBM in defining the gap. Additionally, the TBM facilitates the exploration of new detector structures based on Micromegas owing to the much-simplified operation with the method.

physics.ins-det↗

arXiv2020

Adaptive Histogram-Based Gradient Boosted Trees for Federated Learning

Federated Learning (FL) is an approach to collaboratively train a model across multiple parties without sharing data between parties or an aggregator. It is used both in the consumer domain to protect personal data as well as in enterprise settings, where dealing with data domicile regulation and the pragmatics of data silos are the main drivers. While gradient boosted tree implementations such as XGBoost have been very successful for many use cases, its federated learning adaptations tend to be very slow due to using cryptographic and privacy methods and have not experienced widespread use. We propose the Party-Adaptive XGBoost (PAX) for federated learning, a novel implementation of gradient boosting which utilizes a party adaptive histogram aggregation method, without the need for data encryption. It constructs a surrogate representation of the data distribution for finding splits of the decision tree. Our experimental results demonstrate strong model performance, especially on non-IID distributions, and significantly faster training run-time across different data sets than existing federated implementations. This approach makes the use of gradient boosted trees practical in enterprise federated learning.

cs.LG↗

arXiv2020

Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation

Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic segmentation, which requires pixel-level annotations. This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths, which can be used for training more accurate segmentation models. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes, and the underlying relations between a pair of images are characterized by an efficient co-attention mechanism. Moreover, in order to prevent the model from paying excessive attention to common semantics only, we further propose a graph dropout layer, encouraging the model to learn more accurate and complete object responses. The whole network is end-to-end trainable by iterative message passing, which propagates interaction cues over the images to progressively improve the performance. We conduct experiments on the popular PASCAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. Our code is available at: https://github.com/Lixy1997/Group-WSSS.

cs.CV↗

arXiv2020

Multimodal Learning for Hateful Memes Detection

Memes are used for spreading ideas through social networks. Although most memes are created for humor, some memes become hateful under the combination of pictures and text. Automatically detecting the hateful memes can help reduce their harmful social impact. Unlike the conventional multimodal tasks, where the visual and textual information is semantically aligned, the challenge of hateful memes detection lies in its unique multimodal information. The image and text in memes are weakly aligned or even irrelevant, which requires the model to understand the content and perform reasoning over multiple modalities. In this paper, we focus on multimodal hateful memes detection and propose a novel method that incorporates the image captioning process into the memes detection process. We conduct extensive experiments on multimodal meme datasets and illustrated the effectiveness of our approach. Our model achieves promising results on the Hateful Memes Detection Challenge.

cs.CV↗

arXiv2020

Mitigating Bias in Federated Learning

As methods to create discrimination-aware models develop, they focus on centralized ML, leaving federated learning (FL) unexplored. FL is a rising approach for collaborative ML, in which an aggregator orchestrates multiple parties to train a global model without sharing their training data. In this paper, we discuss causes of bias in FL and propose three pre-processing and in-processing methods to mitigate bias, without compromising data privacy, a key FL requirement. As data heterogeneity among parties is one of the challenging characteristics of FL, we conduct experiments over several data distributions to analyze their effects on model performance, fairness metrics, and bias learning patterns. We conduct a comprehensive analysis of our proposed techniques, the results demonstrating that these methods are effective even when parties have skewed data distributions or as little as 20% of parties employ the methods.

cs.LG↗