Search Results for author:
Found 53 papers, 14 papers with code
Under-Counted Tensor Completion with Neural Incorporation of Attributes
Systematic under-counting effects are observed in data collected across many disciplines, e. g., epidemiology and ecology.
Deep Learning From Crowdsourced Labels: Coupled Cross-entropy Minimization, Identifiability, and Regularization
The contribution of this work is twofold: First, performance guarantees of the CCEM criterion are presented.
Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach
The recent integration of deep learning and pairwise similarity annotation-based constrained clustering -- i. e., $\textit{deep constrained clustering}$ (DCC) -- has proven effective for incorporating weak supervision into massive data clustering: Less than 1% of pair similarity annotations can often substantially enhance the clustering accuracy.
Quantized Radio Map Estimation Using Tensor and Deep Generative Models
Spectrum cartography (SC), also known as radio map estimation (RME), aims at crafting multi-domain (e. g., frequency and space) radio power propagation maps from limited sensor measurements.
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases.
Provable Subspace Identification Under Post-Nonlinear Mixtures
In this work, the post-nonlinear (PNL) mixture model -- where unknown element-wise nonlinear functions are imposed onto a linear mixture -- is revisited.
A Noise-Robust Loss for Unlabeled Entity Problem in Named Entity Recognition
Named Entity Recognition (NER) is an important task in natural language processing.
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
Our framework also takes the learning function's approximation error into consideration, and reveals an intuitive trade-off between the complexity and expressiveness of the employed function learner.
Optimal Solutions for Joint Beamforming and Antenna Selection: From Branch and Bound to Graph Neural Imitation Learning
This work revisits the joint beamforming (BF) and antenna selection (AS) problem, as well as its robust beamforming (RBF) version under imperfect channel state information (CSI).
Fast and Structured Block-Term Tensor Decomposition For Hyperspectral Unmixing
However, existing LL1-based HU algorithms use a three-factor parameterization of the tensor (i. e., the hyperspectral image cube), which leads to a number of challenges including high per-iteration complexity, slow convergence, and difficulties in incorporating structural prior information.
Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation
In this work, we present a novel 3D-to-2D label transfer method, Panoptic NeRF, which aims for obtaining per-pixel 2D semantic and instance labels from easy-to-obtain coarse 3D bounding primitives.
On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR
Based on the above intuition, we first investigate types of end-to-end encoder-decoder based models in the single-input dual-output (SIDO) multi-task framework, after which a novel asynchronous decoding with fuzzy Pinyin sampling method is proposed according to the one-to-one correspondence characteristics between Pinyin and Character.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation Analysis
Compared to the unquantized version, our empirical study shows that the proposed algorithm enjoys a substantial reduction of communication overheads with virtually no loss in accuracy and convergence speed.
Memory-Efficient Convex Optimization for Self-Dictionary Separable Nonnegative Matrix Factorization: A Frank-Wolfe Approach
Our algorithm capitalizes on the special update rules of a classic algorithm from the 1950s, namely, the Frank-Wolfe (FW) algorithm.
Identifiability-Guaranteed Simplex-Structured Post-Nonlinear Mixture Learning via Autoencoder
First, new identifiability conditions are derived under largely relaxed assumptions.
Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization
Unsupervised learning of the Dawid-Skene (D&S) model from noisy, incomplete and crowdsourced annotations has been a long-standing challenge, and is a critical step towards reliably labeling massive data.
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective
Under this model, latent correlation maximization is shown to guarantee the extraction of the shared components across views (up to certain ambiguities).
Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
However, it is often challenging for these approaches to learn in a dynamic environment.
Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
However, such deep learning (DL)-based SC approaches encounter serious challenges in both off-line model learning (training) and completion (generalization), possibly because the latent state space for generating the radio maps is prohibitively large.
Stochastic Block-ADMM for Training Deep Networks
We prove the convergence of our proposed method and justify its capabilities through experiments in supervised and weakly-supervised settings.
Stochastic Mirror Descent for Low-Rank Tensor Decomposition Under Non-Euclidean Losses
This work offers a unified stochastic algorithmic framework for large-scale CPD decomposition under a variety of non-Euclidean loss functions.
Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors
Under the unsupervised DIP framework, it is hypothesized and empirically demonstrated that proper neural network structures are reasonable priors of certain types of images, and the network weights can be learned without training data.
StatEcoNet: Statistical Ecology Neural Networks for Species Distribution Modeling
This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM).
A More Efficient Chinese Named Entity Recognition base on BERT and Syntactic Analysis
We propose a new Named entity recognition (NER) method to effectively make use of the results of Part-of-speech (POS) tagging, Chinese word segmentation (CWS) and parsing while avoiding NER error caused by POS tagging error.
Chinese Named Entity Recognition
Chinese Word Segmentation
+5
Mixed Membership Graph Clustering via Systematic Edge Query
This work aims at learning mixed membership of nodes using queried edges.
Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
We propose to build the notion of continual learning (CL) into the modeling process of learning wireless systems, so that the learning model can incrementally adapt to the new episodes, {\it without forgetting} knowledge learned from the previous episodes.
Recovering Joint Probability of Discrete Random Variables from Pairwise Marginals
Recent work has proposed to recover the joint probability mass function (PMF) of an arbitrary number of RVs from three-dimensional marginals, leveraging the algebraic properties of low-rank tensor decomposition and the (unknown) dependence among the RVs.
Hyperspectral Super-Resolution via Interpretable Block-Term Tensor Modeling
This work employs an idea that models spectral images as tensors following the block-term decomposition model with multilinear rank-$(L_r, L_r, 1)$ terms (i. e., the LL1 model) and formulates the HSR problem as a coupled LL1 tensor decomposition problem.
Computing Large-Scale Matrix and Tensor Decomposition with Structured Factors: A Unified Nonconvex Optimization Perspective
The proposed article aims at offering a comprehensive tutorial for the computational aspects of structured matrix and tensor factorization.
On Recoverability of Randomly Compressed Tensors with Low CP Rank
Our interest lies in the recoverability properties of compressed tensors under the \textit{canonical polyadic decomposition} (CPD) model.
Spectrum Cartography via Coupled Block-Term Tensor Decomposition
Spectrum cartography aims at estimating power propagation patterns over a geographical region across multiple frequency bands (i. e., a radio map)---from limited samples taken sparsely over the region.
Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms
The data deluge comes with high demands for data labeling.
Nonlinear Multiview Analysis: Identifiability and Neural Network-assisted Implementation
In this work, we revisit nonlinear multiview analysis and address both the theoretical and computational aspects.
Hyperspectral Super-Resolution via Global-Local Low-Rank Matrix Estimation
Hyperspectral super-resolution (HSR) is a problem that aims to estimate an image of high spectral and spatial resolutions from a pair of co-registered multispectral (MS) and hyperspectral (HS) images, which have coarser spectral and spatial resolutions, respectively.
Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization
In this work, we propose a stochastic optimization framework for large-scale CPD with constraints/regularizations.
Learning Nonlinear Mixtures: Identifiability and Algorithm
Linear mixture models have proven very useful in a plethora of applications, e. g., topic modeling, clustering, and source separation.
Structured SUMCOR Multiview Canonical Correlation Analysis for Large-Scale Data
In this work, we propose a new computational framework for large-scale SUMCOR GCCA that can easily incorporate a suite of structural regularizers which are frequently used in data analytics.
Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
Third, the majority of the existing methods assume that there are known (or easily estimated) degradation operators applied to the SRI to form the corresponding HSI and MSI--which is hardly the case in practice.
Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications
Perhaps a bit surprisingly, the understanding to its model identifiability---the major reason behind the interpretability in many applications such as topic mining and hyperspectral imaging---had been rather limited until recent years.
Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling
We present a new algorithm for identifying the transition and emission probabilities of a hidden Markov model (HMM) from the emitted data.
Tensors, Learning, and 'Kolmogorov Extension' for Finite-alphabet Random Vectors
This paper shows, perhaps surprisingly, that if the joint PMF of any three variables can be estimated, then the joint PMF of all the variables can be provably recovered under relatively mild conditions.
On Convergence of Epanechnikov Mean Shift
However, since the procedure involves non-smooth kernel density functions, the convergence behavior of Epanechnikov mean shift lacks theoretical support as of this writing---most of the existing analyses are based on smooth functions and thus cannot be applied to Epanechnikov Mean Shift.
On Identifiability of Nonnegative Matrix Factorization
In this letter, we propose a new identification criterion that guarantees the recovery of the low-rank latent factors in the nonnegative matrix factorization (NMF) model, under mild conditions.
Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm
In topic modeling, many algorithms that guarantee identifiability of the topics have been developed under the premise that there exist anchor words -- i. e., words that only appear (with positive probability) in one topic.
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
To recover the `clustering-friendly' latent representations and to better cluster the data, we propose a joint DR and K-means clustering approach in which DR is accomplished via learning a deep neural network (DNN).
Robust Volume Minimization-Based Matrix Factorization for Remote Sensing and Document Clustering
This paper considers \emph{volume minimization} (VolMin)-based structured matrix factorization (SMF).
Tensor Decomposition for Signal Processing and Machine Learning
Tensors or {\em multi-way arrays} are functions of three or more indices $(i, j, k,\cdots)$ -- similar to matrices (two-way arrays), which are functions of two indices $(r, c)$ for (row, column).
Scalable and Flexible Multiview MAX-VAR Canonical Correlation Analysis
Generalized canonical correlation analysis (GCCA) aims at finding latent low-dimensional common structure from multiple views (feature vectors in different domains) of the same entities.
Learning From Hidden Traits: Joint Factor Analysis and Latent Clustering
Dimensionality reduction is usually performed in a preprocessing stage that is separate from subsequent data analysis, such as clustering or classification.
Joint Tensor Factorization and Outlying Slab Suppression with Applications
Convergence of the proposed algorithm is also easy to analyze under the framework of alternating optimization and its variants.
Semiblind Hyperspectral Unmixing in the Presence of Spectral Library Mismatches
The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing (HU) in remote sensing.
Self-Dictionary Sparse Regression for Hyperspectral Unmixing: Greedy Pursuit and Pure Pixel Search are Related
We then perform exact recovery analyses, and prove that the proposed greedy algorithm is robust to noise---including its identification of the (unknown) number of endmembers---under a sufficiently low noise level.
