Search Results for author:
Found 225 papers, 64 papers with code
What Makes Good In-Context Examples for GPT-$3$?
Inspired by the recent success of leveraging a retrieval module to augment large-scale neural network models, we propose to retrieve examples that are semantically-similar to a test sample to formulate its corresponding prompt.
Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks
Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations.
Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker.
Certified Adversarial Robustness with Additive Noise
The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning algorithm.
Joint Embedding of Words and Labels for Text Classification
Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences.
Ranked #11 on
Text Classification
on DBpedia
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL 2000
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
In this paper, we propose a novel Contrastive Log-ratio Upper Bound (CLUB) of mutual information.
StoryGAN: A Sequential Conditional GAN for Story Visualization
We therefore propose a new story-to-image-sequence generation model, StoryGAN, based on the sequential conditional GAN framework.
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks.
Deconvolutional Paragraph Representation Learning
Learning latent representations from long text sequences is an important first step in many natural language processing applications.
Graph Optimal Transport for Cross-Domain Alignment
In GOT, cross-domain alignment is formulated as a graph matching problem, by representing entities into a dynamically-constructed graph.
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching.
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions.
Ranked #1 on
Visual Navigation
on Help, Anna! (HANNA)
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
InfoNCE-based contrastive representation learners, such as SimCLR, have been tremendously successful in recent years.
Adversarial Feature Matching for Text Generation
We propose a framework for generating realistic text via adversarial training.
Semantic Compositional Networks for Visual Captioning
The degree to which each member of the ensemble is used to generate an image caption is tied to the image-dependent probability of the corresponding tag.
Gromov-Wasserstein Learning for Graph Matching and Node Embedding
A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes.
Triangle Generative Adversarial Networks
The generators are designed to learn the two-way conditional distributions between the two domains, while the discriminators implicitly define a ternary discriminative function, which is trained to distinguish real data pairs and two kinds of fake data pairs.
On Leveraging Pretrained GANs for Generation with Limited Data
Demonstrated by natural-image generation, we reveal that low-level filters (those close to observations) of both the generator and discriminator of pretrained GANs can be transferred to facilitate generation in a perceptually-distinct target domain with limited training data.
GAN Memory with No Forgetting
As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected.
Dynamic Clustering via Asymptotics of the Dependent Dirichlet Process Mixture
This paper presents a novel algorithm, based upon the dependent Dirichlet process mixture model (DDPMM), for clustering batch-sequential data containing an unknown number of evolving clusters.
Deep Temporal Sigmoid Belief Networks for Sequence Modeling
Deep dynamic generative models are developed to learn sequential dependencies in time-series data.
Learning Autoencoders with Relational Regularization
A new algorithmic framework is proposed for learning autoencoders of data distributions.
Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
Using this concept, we extend our method to multi-graph partitioning and matching by learning a Gromov-Wasserstein barycenter graph for multiple observed graphs; the barycenter graph plays the role of the disconnected graph, and since it is learned, so is the clustering.
Adversarial Time-to-Event Modeling
Modern health data science applications leverage abundant molecular and electronic health data, providing opportunities for machine learning to build statistical models to support clinical practice.
Towards Amortized Ranking-Critical Training for Collaborative Filtering
In this paper we investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to directly optimize the non-differentiable quality metrics of interest.
Ranked #4 on
Recommendation Systems
on Million Song Dataset
RaCT: Toward Amortized Ranking-Critical Training For Collaborative Filtering
We investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to more directly maximize ranking-based objective functions.
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i. e., they remain adversarial even against other models.
Learning Graphons via Structured Gromov-Wasserstein Barycenters
Accordingly, given a set of graphs generated by an underlying graphon, we learn the corresponding step function as the Gromov-Wasserstein barycenter of the given graphs.
Understanding and Accelerating Particle-Based Variational Inference
Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations.
Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
This model reached a classification performance of AUROC greater than 0. 90 for 18 abnormalities, with an average AUROC of 0. 773 for all 83 abnormalities, demonstrating the feasibility of learning from unfiltered whole volume CT data.
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains).
Symmetric Variational Autoencoder and Connections to Adversarial Learning
A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence.
Revisiting the Softmax Bellman Operator: New Benefits and New Perspective
The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator.
Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian analogs to popular stochastic optimization methods; however, this connection is not well studied.
Efficient Feature Transformations for Discriminative and Generative Continual Learning
However, the growth in the number of additional parameters of many of these types of methods can be computationally expensive at larger scales, at times prohibitively so.
Variational Gaussian Copula Inference
We utilize copulas to constitute a unified framework for constructing and optimizing variational proposals in hierarchical Bayesian models.
Adversarial Learning of a Sampler Based on an Unnormalized Distribution
We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples.
Survival Function Matching for Calibrated Time-to-Event Predictions
We present a survival function estimator for probabilistic predictions in time-to-event models, based on a neural network model for draws from the distribution of event times, without explicit assumptions on the form of the distribution.
Survival Cluster Analysis
As a result, there is an unmet need in survival analysis for identifying subpopulations with distinct risk profiles, while jointly accounting for accurate individualized time-to-event predictions.
Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer
Dealing with severe class imbalance poses a major challenge for real-world applications, especially when the accurate classification and generalization of minority classes is of primary interest.
Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
Successful applications of InfoNCE and its variants have popularized the use of contrastive variational mutual information (MI) estimators in machine learning.
Ouroboros: On Accelerating Training of Transformer-Based Language Models
Model parallelism is required if a model is too large to fit in a single computing device.
Dynamic Embedding on Textual Networks via a Gaussian Process
The relative importance of global versus local structure for the embeddings is learned automatically.
Enabling Counterfactual Survival Analysis with Balanced Representations
Balanced representation learning methods have been applied successfully to counterfactual inference from observational data.
Reconsidering Generative Objectives For Counterfactual Reasoning
As a step towards more flexible, scalable and accurate ITE estimation, we present a novel generative Bayesian estimation framework that integrates representation learning, adversarial matching and causal estimation.
Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage
Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models.
Learning Structural Weight Uncertainty for Sequential Decision-Making
Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications.
Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
We investigate time-dependent data analysis from the perspective of recurrent kernel machines, from which models with hidden units and gated memory cells arise naturally.
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing
Semantic hashing has become a powerful paradigm for fast similarity search in many information retrieval systems.
Alternating Minimization Algorithm with Automatic Relevance Determination for Transmission Tomography under Poisson Noise
We propose a globally convergent alternating minimization (AM) algorithm for image reconstruction in transmission tomography, which extends automatic relevance determination (ARD) to Poisson noise models with Beer's law.
Adversarial Text Generation via Feature-Mover's Distance
However, the discrete nature of text hinders the application of GAN to text-generation tasks.
Towards Practical Lottery Ticket Hypothesis for Adversarial Training
Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the original model with commensurate training steps.
Double Robust Representation Learning for Counterfactual Prediction
Causal inference, or counterfactual prediction, is central to decision making in healthcare, policy and social sciences.
GO Gradient for Expectation-Based Objectives
Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$.
On Fenchel Mini-Max Learning
Inference, estimation, sampling and likelihood evaluation are four primary goals of probabilistic modeling.
Explainable multiple abnormality classification of chest CT volumes
We introduce the challenging new task of explainable multiple abnormality classification in volumetric medical images, in which a model must indicate the regions used to predict each abnormality.
Improving Textual Network Learning with Variational Homophilic Embeddings
This paper considers a novel variational formulation of network embeddings, with special focus on textual networks.
Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning
Pretrained Language Models (PLMs) have improved the performance of natural language understanding in recent years.
Negative Binomial Process Count and Mixture Modeling
A gamma process is employed to model the rate measure of a Poisson process, whose normalization provides a random probability measure for mixture modeling and whose marginalization leads to an NB process for count modeling.
GO Hessian for Expectation-Based Objectives
An unbiased low-variance gradient estimator, termed GO gradient, was proposed recently for expectation-based objectives $\mathbb{E}_{q_{\boldsymbol{\gamma}}(\boldsymbol{y})} [f(\boldsymbol{y})]$, where the random variable (RV) $\boldsymbol{y}$ may be drawn from a stochastic computation graph with continuous (non-reparameterizable) internal nodes and continuous/discrete leaves.
Gradient Importance Learning for Incomplete Observations
Though recent works have developed methods that can generate estimates (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assumptions that may not align with real-world applications and could suffer from poor performance in subsequent tasks such as classification.
Diffusion Maps for Textual Network Embedding
Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices.
Nonlocal Low-Rank Tensor Factor Analysis for Image Restoration
Low-rank signal modeling has been widely leveraged to capture non-local correlation in image processing applications.
Topic Compositional Neural Language Model
The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence.
Superposition-Assisted Stochastic Optimization for Hawkes Processes
We consider the learning of multi-agent Hawkes processes, a model containing multiple Hawkes processes with shared endogenous impact functions and different exogenous intensities.
Benefits from Superposed Hawkes Processes
The superposition of Hawkes processes is demonstrated to be beneficial for tightening the upper bound of excess risk under certain conditions, and we show the feasibility of the benefit in typical situations.
Continuous-Time Flows for Efficient Inference and Density Estimation
Distinct from normalizing flows and GANs, CTFs can be adopted to achieve the above two goals in one framework, with theoretical guarantees.
Learning Registered Point Processes from Idiosyncratic Observations
A parametric point process model is developed, with modeling based on the assumption that sequential observations often share latent phenomena, while also possessing idiosyncratic effects.
Multi-Label Learning from Medical Plain Text with Convolutional Residual Models
Since diagnoses are typically correlated, a deep residual network is employed on top of the CNN encoder, to capture label (diagnosis) dependencies and incorporate information directly from the encoded sentence vector.
Stochastic Gradient Monomial Gamma Sampler
A framework is proposed to improve the sampling efficiency of stochastic gradient MCMC, based on Hamiltonian Monte Carlo.
Towards Unifying Hamiltonian Monte Carlo and Slice Sampling
We unify slice sampling and Hamiltonian Monte Carlo (HMC) sampling, demonstrating their connection via the Hamiltonian-Jacobi equation from Hamiltonian mechanics.
On Connecting Stochastic Gradient MCMC and Differential Privacy
Significant success has been realized recently on applying machine learning to real-world applications.
Deconvolutional Latent-Variable Model for Text Sequence Matching
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives.
Zero-Shot Learning via Class-Conditioned Deep Generative Models
We present a deep generative model for learning to predict classes not seen at training time.
Adversarial Symmetric Variational Autoencoder
A new form of variational autoencoder (VAE) is developed, in which the joint distribution of data and codes is considered in two (symmetric) forms: ($i$) from observed data fed through the encoder to yield codes, and ($ii$) from latent codes drawn from a simple prior and propagated through the decoder to manifest data.
VAE Learning via Stein Variational Gradient Descent
A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent.
Adaptive Feature Abstraction for Translating Video to Text
Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features.
An inner-loop free solution to inverse problems using deep neural networks
For matrix inversion in the second sub-problem, we learn a convolutional neural network to approximate the matrix inversion, i. e., the inverse mapping is learned by feeding the input through the learned forward network.
Learning Context-Sensitive Convolutional Filters for Text Processing
The role of meta network is to abstract the contextual information of a sentence or document into a set of input-aware filters.
Ranked #13 on
Text Classification
on DBpedia
A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks
We present a probabilistic framework for nonlinearities, based on doubly truncated Gaussian distributions.
A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC
However, there has been little theoretical analysis of the impact of minibatch size to the algorithm's convergence rate.
Learning Generic Sentence Representations Using Convolutional Neural Networks
We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes.
Deep Generative Models for Relational Data with Side Information
Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks.
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
Recurrent neural networks (RNNs) have shown promising performance for language modeling.
Tensor-Dictionary Learning with Deep Kruskal-Factor Analysis
A multi-way factor analysis model is introduced for tensor-variate data of any order.
Compressive Sensing via Convolutional Factor Analysis
During reconstruction and testing, we project the upper layer dictionary to the data level and only a single layer deconvolution is required.
Nonlinear Statistical Learning with Truncated Gaussian Graphical Models
We introduce the truncated Gaussian graphical model (TGGM) as a novel framework for designing statistical models for nonlinear learning.
Unsupervised Learning with Truncated Gaussian Graphical Models
Gaussian graphical models (GGMs) are widely used for statistical modeling, because of ease of inference and the ubiquitous use of the normal distribution in practical approximations.
Earliness-Aware Deep Convolutional Networks for Early Time Series Classification
Unlike most existing methods for early classification of time series data, that are designed to solve this problem under the assumption of the availability of a good set of pre-defined (often hand-crafted) features, our framework can jointly perform feature learning (by learning a deep hierarchy of \emph{shapelets} capturing the salient characteristics in each time series), along with a dynamic truncation model to help our deep feature learning architecture focus on the early parts of each time series.
On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators
Our theoretical results show faster convergence rates and more accurate invariant measures for SG-MCMCs with higher-order integrators.
Stochastic Gradient MCMC with Stale Gradients
In this paper we develop theory to show that while the bias and MSE of an SG-MCMC algorithm depend on the staleness of stochastic gradients, its estimation variance (relative to the expected estimate, based on a prescribed number of samples) is independent of it.
Variational Autoencoder for Deep Learning of Images, Labels and Captions
A novel variational autoencoder is developed to model images, as well as associated labels or captions.
Factored Temporal Sigmoid Belief Networks for Sequence Learning
Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences.
Classification and Reconstruction of High-Dimensional Signals from Low-Dimensional Features in the Presence of Side Information
These conditions, which are reminiscent of the well-known Slepian-Wolf and Wyner-Ziv conditions, are a function of the number of linear features extracted from the signal of interest, the number of linear features extracted from the side information signal, and the geometry of these signals and their interplay.
Spectrally Grouped Total Variation Reconstruction for Scatter Imaging Using ADMM
We pursue an optimization transfer approach where convex decompositions are used to lift the problem such that all hyper-voxels can be updated in parallel and in closed-form.
Joint System and Algorithm Design for Computationally Efficient Fan Beam Coded Aperture X-ray Coherent Scatter Imaging
In x-ray coherent scatter tomography, tomographic measurements of the forward scatter distribution are used to infer scatter densities within a volume.
Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace and more
High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models
Stochastic gradient MCMC algorithms (SG-MCMC) are a family of diffusion-based sampling methods for large-scale Bayesian learning.
A Deep Generative Deconvolutional Image Model
A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework.
Learning a Hybrid Architecture for Sequence Regression and Annotation
When learning a hidden Markov model (HMM), sequen- tial observations can often be complemented by real-valued summary response variables generated from the path of hid- den states.
Stick-Breaking Policy Learning in Dec-POMDPs
Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs).
Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data
We present a Bayesian non-negative tensor factorization model for count-valued tensor data, and develop scalable inference algorithms (both batch and online) for dealing with massive tensors.
Zero-Truncated Poisson Tensor Factorization for Massive Binary Tensors
We present a scalable Bayesian model for low-rank factorization of massive tensors with binary observations.
Non-Gaussian Discriminative Factor Models via the Max-Margin Rank-Likelihood
A Bayesian model based on the ranks of the data is proposed.
A Generative Model for Deep Convolutional Learning
A generative model is developed for deep (multi-layered) convolutional dictionary learning.
Compressive Hyperspectral Imaging with Side Information
By using RGB images as side information of the compressive sensing system, the proposed approach is extended to learn a coupled dictionary from the joint dataset of the compressed measurements and the corresponding RGB images, to improve reconstruction quality.
Generative Deep Deconvolutional Learning
A generative Bayesian model is developed for deep (multi-layer) convolutional dictionary learning.
Tree-Structure Bayesian Compressive Sensing for Video
A Bayesian compressive sensing framework is developed for video reconstruction based on the color coded aperture compressive temporal imaging (CACTI) system.
Low-Cost Compressive Sensing for Color Video and Depth
A simple and inexpensive (low-power and low-bandwidth) modification is made to a conventional off-the-shelf color video camera, from which we recover {multiple} color frames for each of the original measured frames, and each of the recovered frames can be focused at a different depth.
Multiscale Shrinkage and Lévy Processes
The method we consider in detail, and for which numerical results are presented, is based on increments of a gamma process.
Adaptive Temporal Compressive Sensing for Video
This paper introduces the concept of adaptive temporal compressive sensing (CS) for video.
Generalized Bregman Divergence and Gradient of Mutual Information for Vector Poisson Channels
We investigate connections between information-theoretic and estimation-theoretic quantities in vector Poisson channel models.
Policy Optimization as Wasserstein Gradient Flows
Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate.
Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment
Network embeddings, which learn low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years.
Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory
Particle-optimization-based sampling (POS) is a recently developed effective sampling technique that interactively updates a set of particles.
Predicting Smoking Events with a Time-Varying Semi-Parametric Hawkes Process Model
Health risks from cigarette smoking -- the leading cause of preventable death in the United States -- can be substantially reduced by quitting.
Distilled Wasserstein Learning for Word Embedding and Topic Modeling
When learning the topic model, we leverage a distilled underlying distance matrix to update the topic distributions and smoothly calculate the corresponding optimal transports.
Sequence Generation with Guider Network
Sequence generation with reinforcement learning (RL) has received significant attention recently.
Generative Adversarial Network Training is a Continual Learning Problem
We hypothesize that this is at least in part due to the evolution of the generator distribution and the catastrophic forgetting tendency of neural networks, which leads to the discriminator losing the ability to remember synthesized samples from previous instantiations of the generator.
Scalable Model Selection for Belief Networks
We propose a scalable algorithm for model selection in sigmoid belief networks (SBNs), based on the factorized asymptotic Bayesian (FAB) framework.
Targeting EEG/LFP Synchrony with Neural Nets
We consider the analysis of Electroencephalography (EEG) and Local Field Potential (LFP) datasets, which are “big” in terms of the size of recorded data but rarely have sufficient labels required to train complex models (e. g., conventional deep learning methods).
Cross-Spectral Factor Analysis
To facilitate understanding of network-level synchronization between brain regions, we introduce a novel model of multisite low-frequency neural recordings, such as local field potentials (LFPs) and electroencephalograms (EEGs).
Linear Feature Encoding for Reinforcement Learning
We then develop a supervised linear feature encoding method that is motivated by insights from linear value function approximation theory, as well as empirical successes from deep RL.
GP Kernels for Cross-Spectrum Analysis
An illustrative and motivating example of a multi-task problem is multi-region electrophysiological time-series data, where experimentalists are interested in both power and phase coherence between channels.
Deep Poisson Factor Modeling
We propose a new deep architecture for topic modeling, based on Poisson Factor Analysis (PFA) modules.
Preconditioned Spectral Descent for Deep Learning
These challenges include, but are not limited to, the non-convexity of learning objectives and estimating the quantities needed for optimization algorithms, such as gradients.
Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings
We present a scalable Bayesian multi-label learning model based on learning low-dimensional label embeddings.
Bayesian Nonlinear Support Vector Machines and Discriminative Factor Modeling
A new Bayesian formulation is developed for nonlinear support vector machines (SVMs), based on a Gaussian process and with the SVM hinge loss expressed as a scaled mixture of normals.
On the relations of LFPs & Neural Spike Trains
One of the goals of neuroscience is to identify neural networks that correlate with important behaviors, environments, or genotypes.
Analysis of Brain States from Multi-Region LFP Time-Series
The LFPs are modeled as a mixture of GPs, with state- and region-dependent mixture weights, and with the spectral content of the data encoded in GP spectral mixture covariance kernels.
Dynamic Rank Factor Model for Text Streams
We propose a semi-parametric and dynamic rank factor model for topic modeling, capable of (1) discovering topic prevalence over time, and (2) learning contemporary multi-scale dependence structures, providing topic and word correlations as a byproduct.
Compressive Sensing of Signals from a GMM with Sparse Precision Matrices
This paper is concerned with compressive sensing of signals drawn from a Gaussian mixture model (GMM) with sparse precision matrices.
Designed Measurements for Vector Count Data
We consider design of linear projection measurements for a vector Poisson signal model.
Integrated Non-Factorized Variational Inference
We present a non-factorized variational method for full posterior inference in Bayesian hierarchical models, with the goal of capturing the posterior variable dependencies via efficient and possibly parallel computation.
Real-Time Inference for a Gamma Process Model of Neural Spiking
With simultaneous measurements from ever increasing populations of neurons, there is a growing need for sophisticated tools to recover signals from individual neurons.
Joint Modeling of a Matrix with Associated Text via Latent Binary Features
The model is applied to roll-call data, with the associated documents defined by the legislation.
Augment-and-Conquer Negative Binomial Processes
By developing data augmentation methods unique to the negative binomial (NB) distribution, we unite seemingly disjoint count and mixture models under the NB process framework.
On the Analysis of Multi-Channel Neural Spike Data
Nonparametric Bayesian methods are developed for analysis of multi-channel spike-train data, with the feature learning and spike sorting performed jointly.
The Kernel Beta Process
A new Le ́vy process prior is proposed for an uncountable collection of covariate- dependent feature-learning measures; the model is called the kernel beta process (KBP).
Hierarchical Topic Modeling for Analysis of Time-Evolving Personal Choices
The nested Chinese restaurant process is extended to design a nonparametric topic-model tree for representation of human choices.
Joint Analysis of Time-Evolving Binary Matrices and Associated Documents
An objective of such analysis is to infer structure and inter-relationships underlying the matrices, here defined by latent features associated with each axis of the matrix.
Learning to Explore and Exploit in POMDPs
In this paper we propose a dual-policy method for jointly learning the agent behavior and the balance between exploration exploitation, in partially observable environments.
A Bayesian Model for Simultaneous Image Clustering, Annotation and Object Segmentation
The model clusters the images into classes, and each image is segmented into a set of objects, also allowing the opportunity to assign a word to each object (localized labeling).
Non-Parametric Bayesian Dictionary Learning for Sparse Image Representations
The beta process is employed as a prior for learning the dictionary, and this non-parametric method naturally infers an appropriate dictionary size.
Second-Order Adversarial Attack and Certifiable Robustness
In this paper, we propose a powerful second-order attack method that reduces the accuracy of the defense model by Madry et al. (2017).
On the Use of Word Embeddings Alone to Represent Natural Language Sequences
In this paper, we conduct an extensive comparative study between Simple Word Embeddings-based Models (SWEMs), with no compositional parameters, relative to employing word embeddings within RNN/CNN-based models.
Improving Sequence-to-Sequence Learning via Optimal Transport
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE).
Multi-Shot Imaging: Joint Alignment, Deblurring and Resolution-Enhancement
Registering multiple blurry images is a challenging task due to the presence of blur while deblurring of multiple blurry images requires accurate alignment, leading to an intrinsically coupled problem.
Learning Weight Uncertainty With Stochastic Gradient MCMC for Shape Classification
Learning the representation of shape cues in 2D & 3D objects for recognition is a fundamental task in computer vision.
Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables.
Scalable Thompson Sampling via Optimal Transport
Thompson sampling (TS) is a class of algorithms for sequential decision-making, which requires maintaining a posterior distribution over a model.
Topic-Guided Variational Autoencoders for Text Generation
We propose a topic-guided variational autoencoder (TGVAE) model for text generation.
Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images
We consider preoperative prediction of thyroid cancer based on ultra-high-resolution whole-slide cytopathology images.
Weakly Supervised Instance Learning for Thyroid Malignancy Prediction from Whole Slide Cytopathology Images
The lower bound further allows us to extend the proposed algorithm to simultaneously predict multiple bag and instance-level labels from a single output of a neural network.
Stochastic Blockmodels meet Graph Neural Networks
Although we develop this framework for a particular type of SBM, namely the \emph{overlapping} stochastic blockmodel, the proposed framework can be adapted readily for other types of SBMs.
On Norm-Agnostic Robustness of Adversarial Training
Adversarial examples are carefully perturbed in-puts for fooling machine learning models.
Improving Textual Network Embedding with Global Attention via Optimal Transport
Constituting highly informative network embeddings is an important tool for network analysis.
Syntax-Infused Variational Autoencoder for Text Generation
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences.
Adaptation Across Extreme Variations using Unlabeled Domain Bridges
We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation.
Topic-Guided Variational Auto-Encoder for Text Generation
We propose a topic-guided variational auto-encoder (TGVAE) model for text generation.
Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms
The proposed method achieves clinically-interpretable embeddings of ICD codes, and outperforms state-of-the-art embedding methods in procedure recommendation.
Adversarial Self-Paced Learning for Mixture Models of Hawkes Processes
Instead of learning a mixture model directly from a set of event sequences drawn from different Hawkes processes, the proposed method learns the target model iteratively, which generates "easy" sequences and uses them in an adversarial and self-paced manner.
LMVP: Video Predictor with Leaked Motion Information
We propose a Leaked Motion Video Predictor (LMVP) to predict future frames by capturing the spatial and temporal dependencies from given inputs.
Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains.
Straight-Through Estimator as Projected Wasserstein Gradient Flow
The Straight-Through (ST) estimator is a widely used technique for back-propagating gradients through discrete random variables.
Fused Gromov-Wasserstein Alignment for Hawkes Processes
Accordingly, the learned optimal transport reflects the correspondence between the event types of these two Hawkes processes.
Zero-Shot Recognition via Optimal Transport
{Specifically, we build a conditional generative model to generate features from seen-class attributes, and establish an optimal transport between the distribution of the generated features and that of the real features.}
Learning to Recommend from Sparse Data via Generative User Feedback
To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback.
An End-to-End Generative Architecture for Paraphrase Generation
Generating high-quality paraphrases is a fundamental yet challenging natural language processing task.
Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks.
Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework.
Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection
We show performance of our models on held-out evaluation sets, analyze several design parameters, and demonstrate the potential of such systems for automated detection of threats that can be found in airports.
Nested-Wasserstein Self-Imitation Learning for Sequence Generation
Reinforcement learning (RL) has been widely studied for improving sequence-generation models.
Object Detection as a Positive-Unlabeled Problem
These missing annotations can be problematic, as the standard cross-entropy loss employed to train object detection models treats classification as a positive-negative (PN) problem: unlabeled regions are implicitly assumed to be background.
Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors
Naively trained neural networks tend to experience catastrophic forgetting in sequential task settings, where data from previous tasks are unavailable.
Transferable Perturbations of Deep Feature Distributions
Almost all current adversarial attacks of CNN classifiers rely on information derived from the output layer of the network.
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers.
APo-VAE: Text Generation in Hyperbolic Space
In this paper, we investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations.
Reward Constrained Interactive Recommendation with Natural Language Feedback
Text-based interactive recommendation provides richer user feedback and has demonstrated advantages over traditional interactive recommender systems.
Improving Adversarial Text Generation by Modeling the Distant Future
Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation.
Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations
A modified Y-Net architecture based on the VGG11 encoder is used to simultaneously learn geometric orientation (similarity transform parameters) of the chest and segmentation of radiographic annotations.
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.
Hierarchical Optimal Transport for Robust Multi-View Learning
Traditional multi-view learning methods often rely on two assumptions: ($i$) the samples in different views are well-aligned, and ($ii$) their representations in latent space obey the same distribution.
Towards Understanding Fast Adversarial Training
Current neural-network-based classifiers are susceptible to adversarial examples.
Scalable Control Variates for Monte Carlo Methods via Stochastic Optimization
Control variates are a well-established tool to reduce the variance of Monte Carlo estimators.
Bridging Maximum Likelihood and Adversarial Learning via $α$-Divergence
Maximum likelihood (ML) and adversarial learning are two popular approaches for training generative models, and from many perspectives these techniques are complementary.
WAFFLe: Weight Anonymized Factorization for Federated Learning
Experiments on MNIST, FashionMNIST, and CIFAR-10 demonstrate WAFFLe's significant improvement to local test performance and fairness while simultaneously providing an extra layer of security.
Weakly supervised cross-domain alignment with optimal transport
Cross-domain alignment between image objects and text sequences is key to many visual-language tasks, and it poses a fundamental challenge to both computer vision and natural language processing.
Towards Robust and Efficient Contrastive Textual Representation Learning
There has been growing interest in representation learning for text data, based on theoretical arguments and empirical evidence.
Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images
The data sources described earlier make two "domains": a hand-collected data domain of images with threats, and a real-world domain of images assumed without threats.
Improving Text Generation with Student-Forcing Optimal Transport
An extension is further proposed to improve the OT learning, based on the structural and contextual information of the text sequences.
RetiNerveNet: Using Recursive Deep Learning to Estimate Pointwise 24-2 Visual Field Data based on Retinal Structure
Due to the SAP test's innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field.
Counterfactual Representation Learning with Balancing Weights
A key to causal inference with observational data is achieving balance in predictive features associated with each treatment type.
MixKD: Towards Efficient Distillation of Large-scale Language Models
Large-scale language models have recently demonstrated impressive empirical performance.
AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning
Synchronization is a key step in data-parallel distributed machine learning (ML).
Calibrating CNNs for Lifelong Learning
Further, our approach does not require storing data samples from the old tasks, which is done by many replay based methods.
An Embedding Model for Estimating Legislative Preferences from the Frequency and Sentiment of Tweets
Legislator preferences are typically represented as measures of general ideology estimated from roll call votes on legislation, potentially masking important nuances in legislators{'} political attitudes.
Methods for Numeracy-Preserving Word Embeddings
We propose a new methodology to assign and learn embeddings for numbers.
