Search Results for author:
Found 220 papers, 45 papers with code
Combinatorial Pure Exploration for Dueling Bandit
For Borda winner, we establish a reduction of the problem to the original CPE-MAB setting and design PAC and exact algorithms that achieve both the sample complexity similar to that in the CPE-MAB setting (which is nearly optimal for a subclass of problems) and polynomial running time per round.
Dual Refinement Underwater Object Detection Network
Due to the complex underwater environment, underwater imaging often encounters some problems such as blur, scale variation, color shift, and texture distortion.
Online Influence Maximization with Node-level Feedback Using Standard Offline Oracles
So we focus on how to use the standard offline influence maximization oracle which finds the best seed set given the edge parameters as input.
End-to-End Conversational Search for Online Shopping with Utterance Transfer
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers.
The Singular Angle of Nonlinear Systems
It is, thus, different from the recently appeared nonlinear system phase which adopts the complexification of real-valued signals using the Hilbert transform.
Real-Time Visual Analysis of High-Volume Social Media Posts
In contrast to previous work, our system also works with non-geolocated posts and avoids extensive preprocessing such as detecting events.
Causally Invariant Predictor with Shift-Robustness
Instead of imposing regularizations to constrain the invariance of the predictor, we propose to predict by the intervened conditional expectation based on the do-operator and then prove that it is invariant across domains.
Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit
However, it is in general unknown how to deriveefficient and effective EE trade-off methods for non-linearcomplex tasks, suchas contextual bandit with deep neural network as the reward function.
R-Drop: Regularized Dropout for Neural Networks
Dropout is a powerful and widely used technique to regularize the training of deep neural networks.
Ranked #1 on
Abstractive Text Summarization
on CNN / Daily Mail
Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factors
In addition, an interpretable latent space is obtained to draw insights into the effect of categorical factors, such as those associated with building blocks of architectures and element choices in metamaterial and materials design.
Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation
It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data.
Large Scale Private Learning via Low-rank Reparametrization
We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious dimensional dependence.
Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV Minimization
Such methods, however, cannot guarantee that the input measurements are satisfied in the recovered image, since the learned parameters by the network are applied to every test image.
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density.
Data-Driven Multiscale Design of Cellular Composites with Multiclass Microstructures for Natural Frequency Maximization
After integrating LVGP with the density-based TO, an efficient data-driven cellular composite optimization process is developed to enable concurrent exploration of microstructure concepts and the associated volume fractions for natural frequency optimization.
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
For the online learning setting, neither the network structure nor the node weights are known initially.
Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics
Specifically, beyond learning directly from the trajectory samples, we pre-train a neural differential operator (NDO) to output an estimation of the derivatives to serve as an additional supervised signal.
PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design
Engineering design tasks often require synthesizing new designs that meet desired performance requirements.
Network Inference and Influence Maximization from Samples
We study the task of influence maximization from these cascade samples (IMS), and present constant approximation algorithms for this task under mild conditions on the seed set distribution.
DINs: Deep Interactive Networks for Neurofibroma Segmentation in Neurofibromatosis Type 1 on Whole-Body MRI
In this study, we propose deep interactive networks (DINs) to address the above limitations.
Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network
Specifically, we first structure the sequence of EMR into a hierarchical graph network and then obtain the causal relationship between multi-granularity features and diagnosis results through counterfactual intervention on the graph.
UAV Aided Over-the-Air Computation
Over-the-air computation (AirComp) seamlessly integrates communication and computation by exploiting the waveform superposition property of multiple-access channels.
Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
The hierarchical features help the model highlight the decision boundary and focus on hard pixels, and the structural information learned from base classes is treated as the prior knowledge for novel classes.
Adversarial Training with Rectified Rejection
Adversarial training (AT) is one of the most effective strategies for promoting model robustness, whereas even the state-of-the-art adversarially trained models struggle to exceed 60% robust test accuracy on CIFAR-10 without additional data, which is far from practical.
Machine-Learning Non-Conservative Dynamics for New-Physics Detection
Energy conservation is a basic physics principle, the breakdown of which often implies new physics.
Learning a Model-Driven Variational Network for Deformable Image Registration
We then propose two neural layers (i. e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i. e. generalized denoising layer).
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling.
A Graph Neural Network Approach for Product Relationship Prediction
By representing products as nodes and their relationships as edges of a graph, we show how an inductive graph neural network approach, named GraphSAGE, can efficiently learn continuous representations for nodes and edges.
Over-the-Air Computation via Reconfigurable Intelligent Surface
Over-the-air computation (AirComp) is a disruptive technique for fast wireless data aggregation in Internet of Things (IoT) networks via exploiting the waveform superposition property of multiple-access channels.
Geometrical Characterization of Sensor Placement for Cone-Invariant and Multi-Agent Systems against Undetectable Zero-Dynamics Attacks
Undetectable attacks are an important class of malicious attacks threatening the security of cyber-physical systems, which can modify a system's state but leave the system output measurements unaffected, and hence cannot be detected from the output.
A Phase Theory of MIMO LTI Systems
In this paper, we introduce a definition of phase response for a class of multi-input multi-output (MIMO) linear time-invariant (LTI) systems whose frequency responses are (semi-)sectorial at all frequencies.
Pure Exploration Bandit Problem with General Reward Functions Depending on Full Distributions
In this paper, we study the pure exploration bandit model on general distribution functions, which means that the reward function of each arm depends on the whole distribution, not only its mean.
Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval
Moreover, feature encoders (as a generator) project uni-modal features into a commonly shared space and attempt to fool the discriminator by maximizing its output information entropy.
WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognition
Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR).
automatic-speech-recognition
End-To-End Speech Recognition
+1
Delay Analysis of Wireless Federated Learning Based on Saddle Point Approximation and Large Deviation Theory
Federated learning (FL) is a collaborative machine learning paradigm, which enables deep learning model training over a large volume of decentralized data residing in mobile devices without accessing clients' private data.
FRITL: A Hybrid Method for Causal Discovery in the Presence of Latent Confounders
The first step of our method uses the FCI procedure, which allows confounders and is able to produce asymptotically correct results.
Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains.
FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image.
Magnetoelectric torque and edge currents in spin-orbit coupled graphene nanoribbons
Even without the magnetization, an out-of-plane polarized chiral edge spin current is produced, resembling that in the quantum spin Hall effect.
Mesoscale and Nanoscale Physics
Two Mirroring And Interpolating Methods To Estimate Peak Position For Symmetric Signals With Single Peak
Signals with single peak and symmetry property are very common in various fields, such as probability density function of normal distribution.
PREPRINT: Comparison of deep learning and hand crafted features for mining simulation data
The output of such simulations, in particular the calculated flow fields, are usually very complex and hard to interpret for realistic three-dimensional real-world applications, especially if time-dependent simulations are investigated.
Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks
In this work we propose a weight soft-regularization method based on the Oblique manifold.
Range-GAN: Range-Constrained Generative Adversarial Network for Conditioned Design Synthesis
This work laid the foundation for data-driven inverse design problems where we consider range constraints and there are sparse regions in the condition space.
A Sequential Variational Mode Decomposition Method
And in such a way, the mode number also can be determined during the separation procedure.
A Note on the Boundedness of Doob Maximal Operators on a Filtered Measure Space
However, we show that $$\lim\limits_{p\rightarrow+\infty}p^{\frac{1}{p-1}}=\lim\limits_{p\rightarrow+\infty}(\min\limits_{a>1}a^{\frac{2}{p}}\eta^{(p^{\prime}-1)})=1.$$
Probability 60G46
Realizing Majorana fermion modes in the Kitaev model
We show that in both cases, the system binds a vortex with the defect and a robust Majorana zero mode in the ground state at a weak uniform conical magnetic field.
Strongly Correlated Electrons
IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures
Variable-density cellular structures can overcome connectivity and manufacturability issues of topologically-optimized, functionally graded structures, particularly when those structures are represented as discrete density maps.
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism.
Combinatorial Pure Exploration with Bottleneck Reward Function and its Extension to General Reward Functions
In this paper, we study the Combinatorial Pure Exploration problem with the bottleneck reward function (CPE-B) under the fixed-confidence and fixed-budget settings.
Multi-Scale Cost Volumes Cascade Network for Stereo Matching
This is because different cost volumes play a crucial role in balancing speed and accuracy.
Aharonov-Bohm Effect in Three-dimensional Higher-order Topological Insulator
Unlike AB interferometer of 3D topological insulator(TI), we find that there are different AB oscillation frequencies for a given direction of magnetic field in 3D HOTI.
Mesoscale and Nanoscale Physics
Deep Image Retrieval: A Survey
More specifically, we focus on image retrieval with deep learning and organize the state of the art methods according to the types of deep network structure, deep features, feature enhancement methods, and network fine-tuning strategies.
UAV-Assisted Over-the-Air Computation
Over-the-air computation (AirComp) provides a promising way to support ultrafast aggregation of distributed data.
Search for the elusive jet-induced diffusion wake in $Z/γ$-jets with 2D jet tomography in high-energy heavy-ion collisions
Diffusion wake is an unambiguous part of the jet-induced medium response in high-energy heavy-ion collisions that leads to a depletion of soft hadrons in the opposite direction of the jet propagation.
High Energy Physics - Phenomenology
Towards Accelerating Training of Batch Normalization: A Manifold Perspective
Then, gradient descent and stochastic gradient descent on the PSI manifold are also constructed.
BN-invariant sharpness regularizes the training model to better generalization
However, it has been pointed out that the usual definitions of sharpness, which consider either the maxima or the integral of loss over a $\delta$ ball of parameters around minima, cannot give consistent measurement for scale invariant neural networks, e. g., networks with batch normalization layer.
Deep Generative Model for Efficient 3D Airfoil Parameterization and Generation
We demonstrate FFD-GAN's performance using a wing shape design example.
On the Stability of Multi-branch Network
More importantly, we propose a new design ``STAM aggregation" that can guarantee to STAbilize the forward/backward process of Multi-branch networks irrespective of the number of branches.
FDMT: A Benchmark Dataset for Fine-grained Domain Adaptation in Machine Translation
To motivate a wide investigation in such settings, we present a real-world fine-grained domain adaptation task in machine translation (FDMT).
A Plug-and-Play Priors Framework for Hyperspectral Unmixing
Spectral unmixing is a widely used technique in hyperspectral image processing and analysis.
Time Series Domain Adaptation via Sparse Associative Structure Alignment
To reduce the difficulty in the discovery of causal structure, we relax it to the sparse associative structure and propose a novel sparse associative structure alignment model for domain adaptation.
Identifying Invariant Texture Violation for Robust Deepfake Detection
To learn such an invariance for deepfake detection, our InTeLe introduces an auto-encoder framework with different decoders for pristine and fake images, which are further appended with a shallow classifier in order to separate out the obvious artifact-effect.
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Except GD, adaptive algorithms such as AdaGrad, RMSProp and Adam are popular owing to their rapid training process.
Multitask machine learning of collective variables for enhanced sampling of rare events
Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics.
Maximizing Social Welfare in a Competitive Diffusion Model
Competitive IM focuses on the propagation of competing items in the network.
Phase of Nonlinear Systems
A nonlinear small phase theorem is then established for feedback stability analysis of semi-sectorial systems.
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results.
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
(2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains.
Ranked #1 on
Domain Adaptation
on DomainNet
A universal simulating framework for quantum key distribution systems
Our framework focuses on realistic characters of optical devices and system structures.
Quantum Physics Optics
Online Influence Maximization under Linear Threshold Model
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.
Federated Learning via Intelligent Reflecting Surface
To optimize the learning performance, we formulate an optimization problem that jointly optimizes the device selection, the aggregation beamformer at the base station (BS), and the phase shifts at the IRS to maximize the number of devices participating in the model aggregation of each communication round under certain mean-squared-error (MSE) requirements.
Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillance
Video surveillance is gaining increasing popularity to assist in railway intrusion detection in recent years.
Latent Causal Invariant Model
To avoid spurious correlation, we propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction.
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
Establishing the first hidden-charm pentaquark with strangeness
We study the $P_{cs}(4459)^0$ recently observed by LHCb using the method of QCD sum rules.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Fast Convergence Algorithm for Analog Federated Learning
In this paper, we consider federated learning (FL) over a noisy fading multiple access channel (MAC), where an edge server aggregates the local models transmitted by multiple end devices through over-the-air computation (AirComp).
Solving Sparse Linear Inverse Problems in Communication Systems: A Deep Learning Approach With Adaptive Depth
Sparse signal recovery problems from noisy linear measurements appear in many areas of wireless communications.
New Ideas and Trends in Deep Multimodal Content Understanding: A Review
The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
Hyperspectral Unmixing via Nonnegative Matrix Factorization with Handcrafted and Learnt Priors
In our work, we propose an NMF based unmixing framework which jointly uses a handcrafting regularizer and a learnt regularizer from data.
Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net
With the advance of deep learning, various neural network models have gained great success in image analysis including the recognition of intervertebral discs.
ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit
Meanwhile, human choreographers design dance motions from music in a two-stage manner: they firstly devise multiple choreographic dance units (CAUs), each with a series of dance motions, and then arrange the CAU sequence according to the rhythm, melody and emotion of the music.
MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization
Despite their success in capturing complex distributions, existing generative models face three challenges when used for design problems: 1) generated designs have limited design space coverage, 2) the generator ignores design performance, and 3)~the new parameterization is unable to represent designs beyond training data.
GraphFederator: Federated Visual Analysis for Multi-party Graphs
This paper presents GraphFederator, a novel approach to construct joint representations of multi-party graphs and supports privacy-preserving visual analysis of graphs.
Human-Computer Interaction Cryptography and Security Graphics
New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design
In this paper, we first highlight three major challenges to large-scale adoption of deep learning at the edge: (i) Hardware-constrained IoT devices, (ii) Data security and privacy in the IoT era, and (iii) Lack of network-aware deep learning algorithms for distributed inference across multiple IoT devices.
Global Context Aware Convolutions for 3D Point Cloud Understanding
We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive.
Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.
Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics
Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks.
SMAP: A Joint Dimensionality Reduction Scheme for Secure Multi-Party Visualization
We build a prototype system based on our method, SMAP, to support the organization, computation, and exploration of secure joint embedding.
Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
The linear inverse problem is fundamental to the development of various scientific areas.
How Does Data Augmentation Affect Privacy in Machine Learning?
Even further, we show that the proposed approach can achieve higher MI attack success rates on models trained with some data augmentation than the existing methods on models trained without data augmentation.
MO-PaDGAN: Generating Diverse Designs with Multivariate Performance Enhancement
Deep generative models have proven useful for automatic design synthesis and design space exploration.
Optimization from Structured Samples for Coverage Functions
We revisit the optimization from samples (OPS) model, which studies the problem of optimizing objective functions directly from the sample data.
Robust Neural Machine Translation with ASR Errors
In this paper, we propose a method to handle the two problems so as to generate robust translation to ASR errors.
Molecular Latent Space Simulators
Small integration time steps limit molecular dynamics (MD) simulations to millisecond time scales.
Data-Driven Topology Optimization with Multiclass Microstructures using Latent Variable Gaussian Process
With this model, we can easily obtain a continuous and differentiable transition between different microstructure concepts that can render gradient information for multiscale topology optimization.
Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
For microstructure design, the tuning of mechanical properties and complex manipulations of microstructures are easily achieved by simple vector operations in the latent space.
Dynamic of Stochastic Gradient Descent with State-Dependent Noise
Specifically, we show that the covariance of the noise of SGD in the local region of the local minima is a quadratic function of the state.
Online Competitive Influence Maximization
We provide a nontrivial proof showing that the Triggering Probability Modulated (TPM) condition for CMAB still holds in OCIM, which is instrumental for our proposed algorithms OCIM-TS and OCIM-OFU to achieve logarithmic Bayesian regret and frequentist regret, respectively.
Combinatorial Pure Exploration of Dueling Bandit
For Borda winner, we establish a reduction of the problem to the original CPE-MAB setting and design PAC and exact algorithms that achieve both the sample complexity similar to that in the CPE-MAB setting (which is nearly optimal for a subclass of problems) and polynomial running time per round.
Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks
The resulted new parameterization can accelerate design optimization convergence by improving the representation compactness while maintaining sufficient representation capacity.
Combinatorial Pure Exploration with Full-Bandit or Partial Linear Feedback
In this paper, we first study the problem of combinatorial pure exploration with full-bandit feedback (CPE-BL), where a learner is given a combinatorial action space $\mathcal{X} \subseteq \{0, 1\}^d$, and in each round the learner pulls an action $x \in \mathcal{X}$ and receives a random reward with expectation $x^{\top} \theta$, with $\theta \in \mathbb{R}^d$ a latent and unknown environment vector.
Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes.
METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
In answer, we posit that a smaller yet diverse set of unit cells leads to scalable search and unbiased learning.
(Locally) Differentially Private Combinatorial Semi-Bandits
In this paper, we study Combinatorial Semi-Bandits (CSB) that is an extension of classic Multi-Armed Bandits (MAB) under Differential Privacy (DP) and stronger Local Differential Privacy (LDP) setting.
Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech.
Sound Audio and Speech Processing
Quda: Natural Language Queries for Visual Data Analytics
To address this challenge, we present a new dataset, called Quda, that aims to help V-NLIs recognize analytic tasks from free-form natural language by training and evaluating cutting-edge multi-label classification models.
EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation
Aiming at generating responses that approximate the ground-truth and receive high ranking scores from the discriminator, the two generators learn to generate improved highly relevant responses and competitive unobserved candidates respectively, while the discriminative ranker is trained to identify true responses from adversarial ones, thus featuring the merits of both generator counterparts.
Lightweight Mask R-CNN for Long-Range Wireless Power Transfer Systems
The proposed approach makes the object detection much easier to be transplanted on mobile devices and reduce the burden of hardware computation.
Efficient Approximation Algorithms for Adaptive Influence Maximization
In this paper, we propose the first practical algorithm for the adaptive IM problem that could provide the worst-case approximation guarantee of $1-\mathrm{e}^{\rho_b(\varepsilon-1)}$, where $\rho_b=1-(1-1/b)^b$ and $\varepsilon \in (0, 1)$ is a user-specified parameter.
Social and Information Networks
Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surface
Intelligent Internet-of-Things (IoT) will be transformative with the advancement of artificial intelligence and high-dimensional data analysis, shifting from "connected things" to "connected intelligence".
MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning
This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.
FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning
In this paper, we identify a new phenomenon called activation-divergence which occurs in Federated Learning (FL) due to data heterogeneity (i. e., data being non-IID) across multiple users.
Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation
In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence.
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation.
PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs
With this new loss function, we develop a variant of the Generative Adversarial Network, named "Performance Augmented Diverse Generative Adversarial Network" or PaDGAN, which can generate novel high-quality designs with good coverage of the design space.
Combinatorial Semi-Bandit in the Non-Stationary Environment
In a special case where the reward function is linear and we have an exact oracle, we design a parameter-free algorithm that achieves nearly optimal regret both in the switching case and in the dynamic case without knowing the parameters in advance.
Adaptive Expansion Bayesian Optimization for Unbounded Global Optimization
Bayesian optimization is normally performed within fixed variable bounds.
Gradient Perturbation is Underrated for Differentially Private Convex Optimization
By using the \emph{expected curvature}, we show that gradient perturbation can achieve a significantly improved utility guarantee that can theoretically justify the advantage of gradient perturbation over other perturbation methods.
Adaptive Greedy versus Non-adaptive Greedy for Influence Maximization
On the other side, we prove that in any submodular cascade, the adaptive greedy algorithm always outputs a $(1-1/e)$-approximation to the expected number of adoptions in the optimal non-adaptive seed choice.
Social and Information Networks
Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting
The problem is more challenging than the standard online learning scenario since the private value distribution is non-stationary, meaning that the distribution of bidders' private values may change over time, and we need to use the \emph{non-stationary regret} to measure the performance of our algorithm.
Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding
Transformer has shown promising results in many sequence to sequence transformation tasks recently.
Interpreting Basis Path Set in Neural Networks
Based on basis path set, G-SGD algorithm significantly outperforms conventional SGD algorithm in optimizing neural networks.
A Conditional Generative Model for Predicting Material Microstructures from Processing Methods
Microstructures of a material form the bridge linking processing conditions - which can be controlled, to the material property - which is the primary interest in engineering applications.
Bayesian Optimization for Materials Design with Mixed Quantitative and Qualitative Variables
We present in this paper the integration of a novel latent-variable (LV) approach for mixed-variable GP modeling with the BO framework for materials design.
A Natural-language-based Visual Query Approach of Uncertain Human Trajectories
Visual querying is essential for interactively exploring massive trajectory data.
Data-Centric Mixed-Variable Bayesian Optimization For Materials Design
To this end, we present a data-centric, mixed-variable Bayesian Optimization framework that integrates data from literature, experiments, and simulations for knowledge discovery and computational materials design.
On Adaptivity Gaps of Influence Maximization under the Independent Cascade Model with Full Adoption Feedback
In this paper, we study the adaptivity gap of the influence maximization problem under independent cascade model when full-adoption feedback is available.
Social and Information Networks
Stochastic One-Sided Full-Information Bandit
In this paper, we study the stochastic version of the one-sided full information bandit problem, where we have $K$ arms $[K] = \{1, 2, \ldots, K\}$, and playing arm $i$ would gain reward from an unknown distribution for arm $i$ while obtaining reward feedback for all arms $j \ge i$.
High-resolution Markov state models for the dynamics of Trp-cage miniprotein constructed over slow folding modes identified by state-free reversible VAMPnets
State-free reversible VAMPnets (SRVs) are a neural network-based framework capable of learning the leading eigenfunctions of the transfer operator of a dynamical system from trajectory data.
Factorization Bandits for Online Influence Maximization
We capitalize on an important property of the influence maximization problem named network assortativity, which is ignored by most existing works in online influence maximization.
Self-Activation Influence Maximization
We incorporate self activation into influence propagation and propose the self-activation independent cascade (SAIC) model: nodes may be self activated besides being selected as seeds, and influence propagates from both selected seeds and self activated nodes.
Social and Information Networks
Capabilities and Limitations of Time-lagged Autoencoders for Slow Mode Discovery in Dynamical Systems
We also compare the TAE results with those obtained using state-free reversible VAMPnets (SRVs) as a variational-based neural network approach for slow modes discovery, and show that SRVs can correctly discover slow modes where TAEs fail.
Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data
Our theory captures how the convergence of distributed algorithms behaves as the number of machines and the size of local data vary.
Adaptive Influence Maximization with Myopic Feedback
We study the adaptive influence maximization problem with myopic feedback under the independent cascade model: one sequentially selects k nodes as seeds one by one from a social network, and each selected seed returns the immediate neighbors it activates as the feedback available for later selections, and the goal is to maximize the expected number of total activated nodes, referred as the influence spread.
Social and Information Networks
An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE
Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid.
G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Then, a natural question is: \emph{can we construct a new vector space that is positively scale-invariant and sufficient to represent ReLU neural networks so as to better facilitate the optimization process }?
Optimization on Multiple Manifolds
Optimization on manifold has been widely used in machine learning, to handle optimization problems with constraint.
The Roadmap to 6G -- AI Empowered Wireless Networks
The recent upsurge of diversified mobile applications, especially those supported by Artificial Intelligence (AI), is spurring heated discussions on the future evolution of wireless communications.
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
If the initial image is not well initialized, the following processes can hardly refine the image to a satisfactory quality.
Ranked #2 on
Text-to-Image Generation
on COCO
(SOA-C metric)
Convergence Theory of Learning Over-parameterized ResNet: A Full Characterization
Specifically, with hiding logarithmic factor and constant coefficients, we show that for $\tau\le 1/\sqrt{L}$ gradient descent is guaranteed to converge to the global minma, and especially when $\tau\le 1/L$ the convergence is irrelevant of the network depth.
Reinforcement Learning with Dynamic Boltzmann Softmax Updates
In this paper, we propose to update the value function with dynamic Boltzmann softmax (DBS) operator, which has good convergence property in the setting of planning and learning.
Positively Scale-Invariant Flatness of ReLU Neural Networks
That is to say, the minimum with balanced values of basis paths will more likely to be flatter and generalize better.
Stochastic Online Learning with Probabilistic Graph Feedback
We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$.
Improved Algorithm on Online Clustering of Bandits
We generalize the setting of online clustering of bandits by allowing non-uniform distribution over user frequencies.
Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
The success of enhanced sampling molecular simulations that accelerate along collective variables (CVs) is predicated on the availability of variables coincident with the slow collective motions governing the long-time conformational dynamics of a system.
Vector and Line Quantization for Billion-scale Similarity Search on GPUs
The inverted index structure is amenable to GPU-based implementations, and the state-of-the-art systems such as Faiss are able to exploit the massive parallelism offered by GPUs.
On the Local Hessian in Back-propagation
We study the Hessian of the local back-matching loss (local Hessian) and connect it to the efficiency of BP.
Learning to Predict the Cosmological Structure Formation
We build a deep neural network, the Deep Density Displacement Model (hereafter D$^3$M), to predict the non-linear structure formation of the Universe from simple linear perturbation theory.
Community Exploration: From Offline Optimization to Online Learning
We introduce the community exploration problem that has many real-world applications such as online advertising.
Exploring RNN-Transducer for Chinese Speech Recognition
End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system.
Modality Attention for End-to-End Audio-visual Speech Recognition
In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance.
Audio-Visual Speech Recognition
Robust Speech Recognition
+1
An Online Attention-based Model for Speech Recognition
In previous work, researchers have shown that such architectures can acquire comparable results to state-of-the-art ASR systems, especially when using a bidirectional encoder and global soft attention (GSA) mechanism.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Improving the Robustness of Speech Translation
Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source.
Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting
(2) The convergence rate is determined by the step size, with the mixing time of the Markov process as the coefficient.
Capacity Control of ReLU Neural Networks by Basis-path Norm
Motivated by this, we propose a new norm \emph{Basis-path Norm} based on a group of linearly independent paths to measure the capacity of neural networks more accurately.
BézierGAN: Automatic Generation of Smooth Curves from Interpretable Low-Dimensional Parameters
Many real-world objects are designed by smooth curves, especially in the domain of aerospace and ship, where aerodynamic shapes (e. g., airfoils) and hydrodynamic shapes (e. g., hulls) are designed.
A DEEP ADVERSARIAL LEARNING METHODOLOGY FOR DESIGNING MICROSTRUCTURAL MATERIAL SYSTEMS
Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics.
Semi-Supervised Disfluency Detection
While the disfluency detection has achieved notable success in the past years, it still severely suffers from the data scarcity.
A Latent Variable Approach to Gaussian Process Modeling with Qualitative and Quantitative Factors
Computer simulations often involve both qualitative and numerical inputs.
Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin
End-to-end models have been showing superiority in Automatic Speech Recognition (ASR).
automatic-speech-recognition
End-To-End Speech Recognition
+2
Towards Binary-Valued Gates for Robust LSTM Training
Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling.
SupportNet: solving catastrophic forgetting in class incremental learning with support data
A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting.
Peperomia at SemEval-2018 Task 2: Vector Similarity Based Approach for Emoji Prediction
First the distributed representation (tweet vector) for each tweet is generated, then the similarity between this tweet vector and each emoji{'}s embedding is evaluated.
Differential Equations for Modeling Asynchronous Algorithms
Then we conduct theoretical analysis on the convergence rates of ASGD algorithm based on the continuous approximation.
Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version)
Each decision has a reward according to the distributions of arms.
Unsupervised Neural Machine Translation with Weight Sharing
Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data.
Ranked #5 on
Machine Translation
on WMT2016 German-English
Thompson Sampling for Combinatorial Semi-Bandits
When the reward function is linear, the regret of the TS algorithm achieves a better bound $O(m\log K_{\max}\log T / \Delta_{\min})$.
Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation
This inconsistence of gradient magnitude across different layers renders optimization of deep neural network with a single learning rate problematic.
Scalable Influence Maximization with General Marketing Strategies
In this paper, we study scalable algorithms for influence maximization with general marketing strategies (IM-GMS), in which a marketing strategy mix is modeled as a vector $\mathbf{x}=(x_1, \ldots, x_d)$ and could activate a node $v$ in the social network with probability $h_v(\mathbf{x})$.
Social and Information Networks Data Structures and Algorithms