Search Results for author:
Found 192 papers, 68 papers with code
Generating, Reconstructing, and Representing Discrete and Continuous Data: Generalized Diffusion with Learnable Encoding-Decoding
The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and continuous images.
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
"Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development.
LLM360: Towards Fully Transparent Open-Source LLMs
The recent surge in open-source Large Language Models (LLMs), such as LLaMA, Falcon, and Mistral, provides diverse options for AI practitioners and researchers.
LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
Our approach uses an iterative algorithm to decompose each pretrained matrix into a high-precision low-rank component and a memory-efficient quantized component.
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task.
Contextualized Machine Learning
Contextualized ML estimates heterogeneous functions by applying deep learning to the meta-relationship between contextual information and context-specific parametric models.
Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning
Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models fall short by forcing a tradeoff between accuracy and interpretability.
DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training
FlashAttention (Dao, 2023) effectively reduces the quadratic peak memory usage to linear in training transformer-based large language models (LLMs) on a single GPU.
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
Studying how people interact with large language models (LLMs) in real-world scenarios is increasingly important due to their widespread use in various applications.
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences.
Ranked #3 on
Long-Context Understanding
on Ada-LEval (TSort)
Understanding Masked Autoencoders via Hierarchical Latent Variable Models
In this work, we formally characterize and justify existing empirical insights and provide theoretical guarantees of MAE.
Cuttlefish: Low-Rank Model Training without All the Tuning
Cuttlefish leverages the observation that after a few epochs of full-rank training, the stable rank (i. e., an approximation of the true rank) of each layer stabilizes at a constant value.
Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach
A recent alternative formulation instead treats federated learning as a distributed inference problem, where the goal is to infer a global posterior from partitioned client data (Al-Shedivat et al., 2021).
Does compressing activations help model parallel training?
Finally, we provide insights for future development of model parallelism compression algorithms.
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks.
Ranked #1 on
Classifier calibration
on CIFAR-100
On Optimizing the Communication of Model Parallelism
This pattern emerges when the two paradigms of model parallelism - intra-operator and inter-operator parallelism - are combined to support large models on large clusters.
MPCFormer: fast, performant and private Transformer inference with MPC
Through extensive evaluations, we show that MPCFORMER significantly speeds up Transformer inference in MPC settings while achieving similar ML performance to the input model.
ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models
In the data disambiguation stage, we employ the prompted GPT-3 model to understand possibly ambiguous triples from the input data and convert each into a short sentence with reduced ambiguity.
Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation
Despite its success, the said paradigm is still constrained by several factors, such as (i) low-quality region proposals for novel classes and (ii) negligence of the inter-class correlation among different classes.
Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection.
Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning
We introduce the initial release of our software Robustar, which aims to improve the robustness of vision classification machine learning models through a data-driven perspective.
MRCLens: an MRC Dataset Bias Detection Toolkit
Many recent neural models have shown remarkable empirical results in Machine Reading Comprehension, but evidence suggests sometimes the models take advantage of dataset biases to predict and fail to generalize on out-of-sample data.
BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models
The resulting KGs as a symbolic interpretation of the source LMs also reveal new insights into the LMs' knowledge capacities.
Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
Finally, we test this simple technique we identify (worst-case data augmentation with squared l2 norm alignment regularization) and show that the benefits of this method outrun those of the specially designed methods.
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
RLPrompt formulates a parameter-efficient policy network that generates the desired discrete prompt after training with reward.
The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation
Previous works on Treatment Effect Estimation (TEE) are not in widespread use because they are predominantly theoretical, where strong parametric assumptions are made but untractable for practical application.
Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations.
The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
Towards Principled Disentanglement for Domain Generalization
To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG).
NOTMAD: Estimating Bayesian Networks with Sample-Specific Structures and Parameters
We encode the acyclicity constraint as a smooth regularization loss which is back-propagated to the mixing function; in this way, NOTMAD shares information between context-specific acyclic graphs, enabling the estimation of Bayesian network structures and parameters at even single-sample resolution.
Cooperative Multi-Agent Actor-Critic for Privacy-Preserving Load Scheduling in a Residential Microgrid
As a scalable data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving the cooperative residential load scheduling problems.
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation
Based on the nature of information change from input to output, we classify NLG tasks into compression (e. g., summarization), transduction (e. g., text rewriting), and creation (e. g., dialog).
Knowledge-Aware Meta-learning for Low-Resource Text Classification
Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task.
Toward a `Standard Model' of Machine Learning
Machine learning (ML) is about computational methods that enable machines to learn concepts from experience.
Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation
With the surge in the number of hyperparameters and training times of modern machine learning models, hyperparameter tuning is becoming increasingly expensive.
Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
We apply the approach to a wide range of novel text generation tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Therefore, we propose a Geometric Question Answering dataset GeoQA, containing 4, 998 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems.
Ranked #4 on
Mathematical Reasoning
on PGPS9K
A Data-Centric Framework for Composable NLP Workflows
Empirical natural language processing (NLP) systems in application domains (e. g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis, generation, and visualization.
Technology Readiness Levels for Machine Learning Systems
The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end.
Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data
To bridge the methodological gaps in partially supervised learning (PSL) under data scarcity, we propose Vicinal Labels Under Uncertainty (VLUU), a simple yet efficient framework utilizing the human structure similarity for partially supervised medical image segmentation.
Squared $\ell_2$ Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
Data augmentation is one of the most popular techniques for improving the robustness of neural networks.
Validate and Enable Machine Learning in Industrial AI
However, manufacturers and solution partners need to understand how to implement and integrate an AI model into the existing industrial control system.
Iterative Graph Self-Distillation
Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs.
Word Shape Matters: Robust Machine Translation with Visual Embedding
Neural machine translation has achieved remarkable empirical performance over standard benchmark datasets, yet recent evidence suggests that the models can still fail easily dealing with substandard inputs such as misspelled words, To overcome this issue, we introduce a new encoding heuristic of the input symbols for character-level NLP models: it encodes the shape of each character through the images depicting the letters when printed.
Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach
Given a document and a target aspect (e. g., a topic of interest), aspect-based abstractive summarization attempts to generate a summary with respect to the aspect.
Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning
Some recent schedulers choose job resources for users, but do so without awareness of how DL training can be re-optimized to better utilize the provided resources.
Self-Challenging Improves Cross-Domain Generalization
We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data.
Ranked #27 on
Domain Generalization
on PACS
Dropout as a Regularizer of Interaction Effects
We examine Dropout through the perspective of interactions.
Progressive Generation of Long Text with Pretrained Language Models
However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passages of text (e. g., 1000 tokens), especially when the models are fine-tuned to the target domain on a small corpus.
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation.
Ranked #2 on
Text Generation
on EMNLP2017 WMT
Distributed, partially collapsed MCMC for Bayesian Nonparametrics
Bayesian nonparametric (BNP) models provide elegant methods for discovering underlying latent features within a data set, but inference in such models can be slow.
Smooth Kernels Improve Adversarial Robustness and Perceptually-Aligned Gradients
Recent research has shown that CNNs are often overly sensitive to high-frequency textural patterns.
Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering
The learned SSCM gives the specific causal knowledge for each individual as well as the general trend over the population.
Discourse in Multimedia: A Case Study in Extracting Geometry Knowledge from Textbooks
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
Learning Data Manipulation for Augmentation and Weighting
In this work, we propose a new method that supports learning different manipulation schemes with the same gradient-based algorithm.
Learning Sample-Specific Models with Low-Rank Personalized Regression
Modern applications of machine learning (ML) deal with increasingly heterogeneous datasets comprised of data collected from overlapping latent subpopulations.
Learning Sparse Nonparametric DAGs
We develop a framework for learning sparse nonparametric directed acyclic graphs (DAGs) from data.
ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations
In applications such as molecule design or drug discovery, it is desirable to have an algorithm which recommends new candidate molecules based on the results of past tests.
Learning Robust Global Representations by Penalizing Local Predictive Power
Despite their renowned predictive power on i. i. d.
Ranked #104 on
Domain Generalization
on PACS
Target-Guided Open-Domain Conversation
We study the problem of imposing conversational goals on open-domain chat agents.
Adversarial Domain Adaptation Being Aware of Class Relationships
In this paper, we propose a novel relationship-aware adversarial domain adaptation (RADA) algorithm, which first utilizes a single multi-class domain discriminator to enforce the learning of inter-class dependency structure during domain-adversarial training and then aligns this structure with the inter-class dependencies that are characterized from training the label predictor on source domain.
High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN).
Graph Transformer
Graph neural networks (GNN) have gained increasing research interests as a mean to the challenging goal of robust and universal graph learning.
Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation
Generating long and semantic-coherent reports to describe medical images poses great challenges towards bridging visual and linguistic modalities, incorporating medical domain knowledge, and generating realistic and accurate descriptions.
Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO.
Learning Robust Representations by Projecting Superficial Statistics Out
We test our method on the battery of standard domain generalization data sets and, interestingly, achieve comparable or better performance as compared to other domain generalization methods that explicitly require samples from the target distribution for training.
Ranked #113 on
Domain Generalization
on PACS
Theoretically Principled Trade-off between Robustness and Accuracy
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples.
Ranked #3 on
Adversarial Attack
on CIFAR-10
The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture Models
We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional distributions.
Symbolic Graph Reasoning Meets Convolutions
To cooperate with local convolutions, each SGR is constituted by three modules: a) a primal local-to-semantic voting module where the features of all symbolic nodes are generated by voting from local representations; b) a graph reasoning module propagates information over knowledge graph to achieve global semantic coherency; c) a dual semantic-to-local mapping module learns new associations of the evolved symbolic nodes with local representations, and accordingly enhances local features.
Ranked #81 on
Semantic Segmentation
on ADE20K val
Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems
Finally, we also show how Nuts&Bolts can be used to achieve improvements on a relation extraction task and on the end task of answering Newtonian physics problems.
Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
In this work, we give new results on the benefits of multi-generator architecture of GANs.
Discourse in Multimedia: A Case Study in Information Extraction
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
Fault Tolerance in Iterative-Convergent Machine Learning
In this paper, we develop a general framework to quantify the effects of calculation errors on iterative-convergent algorithms and use this framework to design new strategies for checkpoint-based fault tolerance.
Toward Understanding the Impact of Staleness in Distributed Machine Learning
Many distributed machine learning (ML) systems adopt the non-synchronous execution in order to alleviate the network communication bottleneck, resulting in stale parameters that do not reflect the latest updates.
Connecting the Dots Between MLE and RL for Sequence Generation
We present a generalized entropy regularized policy optimization formulation, and show that the apparently divergent algorithms can all be reformulated as special instances of the framework, with the only difference being the configurations of reward function and a couple of hyperparameters.
Differentiable Expected BLEU for Text Generation
Neural text generation models such as recurrent networks are typically trained by maximizing data log-likelihood based on cross entropy.
Sample Complexity of Nonparametric Semi-Supervised Learning
We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional distributions.
What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks
In this paper, we further investigate the statistical irregularities, what we refer as confounding factors, of the NLI data sets.
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
The versatile toolkit also fosters technique sharing across different text generation tasks.
Hybrid Subspace Learning for High-Dimensional Data
One way to achieve this goal is to perform subspace learning to estimate a small set of latent features that capture the majority of the variance in the original data.
Reinforced Auto-Zoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Whole-slide Images
Motivated by the zoom-in operation of a pathologist using a digital microscope, RAZN learns a policy network to decide whether zooming is required in a given region of interest.
Query-Conditioned Three-Player Adversarial Network for Video Summarization
Video summarization plays an important role in video understanding by selecting key frames/shots.
Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio
Specifically, we propose a model that enforces our intuition that prediction masks should be domain independent.
Unsupervised Text Style Transfer using Language Models as Discriminators
Binary classifiers are often employed as discriminators in GAN-based unsupervised style transfer systems to ensure that transferred sentences are similar to sentences in the target domain.
Rethinking Knowledge Graph Propagation for Zero-Shot Learning
Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning.
Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation
Experiments show that our approach achieves the state-of-the-art results on two medical report datasets, generating well-balanced structured sentences with robust coverage of heterogeneous medical report contents.
Image-derived generative modeling of pseudo-macromolecular structures - towards the statistical assessment of Electron CryoTomography template matching
Cellular Electron CryoTomography (CECT) is a 3D imaging technique that captures information about the structure and spatial organization of macromolecular complexes within single cells, in near-native state and at sub-molecular resolution.
Dilated Temporal Relational Adversarial Network for Generic Video Summarization
Specifically, DTR-GAN learns a dilated temporal relational generator and a discriminator with three-player loss in an adversarial manner.
ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
We argue that semantic salient segmentation can instead be effectively resolved by reformulating it as a simple yet intuitive pixel-pair based connectivity prediction task.
Removing Confounding Factors Associated Weights in Deep Neural Networks Improves the Prediction Accuracy for Healthcare Applications
The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis.
DAGs with NO TEARS: Continuous Optimization for Structure Learning
This is achieved by a novel characterization of acyclicity that is not only smooth but also exact.
Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis
In this paper, we address these three issues by (1) seeking convex relaxations of the original nonconvex problems so that the global optimal is guaranteed to be achievable; (2) providing a formal analysis on OPR's capability of promoting balancedness; (3) providing a theoretical analysis that directly reveals the relationship between OPR and generalization performance.
DiCE: The Infinitely Differentiable Monte-Carlo Estimator
Lastly, to match the first-order gradient under differentiation, SL treats part of the cost as a fixed sample, which we show leads to missing and wrong terms for estimators of higher-order derivatives.
Identifiability of Nonparametric Mixture Models and Bayes Optimal Clustering
Motivated by problems in data clustering, we establish general conditions under which families of nonparametric mixture models are identifiable, by introducing a novel framework involving clustering overfitted \emph{parametric} (i. e. misspecified) mixture models.
Personalized Survival Prediction with Contextual Explanation Networks
Accurate and transparent prediction of cancer survival times on the level of individual patients can inform and improve patient care and treatment practices.
The Intriguing Properties of Model Explanations
Linear approximations to the decision boundary of a complex model have become one of the most popular tools for interpreting predictions.
Transformation Autoregressive Networks
Further, through a comprehensive study over both real world and synthetic data, we show for that jointly leveraging transformations of variables and autoregressive conditional models, results in a considerable improvement in performance.
Ranked #1 on
Density Estimation
on BSDS300
Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
It presents two main contributions to traditional GANs: 1) a soft gradient-sensitive objective for keeping semantic boundaries; 2) a semantic-aware discriminator for validating the fidelity of personalized adaptions with respect to each semantic region.
Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder
Unsupervised video summarization plays an important role on digesting, browsing, and searching the ever-growing videos every day, and the underlying fine-grained semantic and motion information (i. e., objects of interest and their key motions) in online videos has been barely touched.
Stability Selection for Structured Variable Selection
Recently, a meta-algorithm called Stability Selection was proposed that can provide reliable finite-sample control of the number of false positives.
Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks
Recent deep learning (DL) models have moved beyond static network architectures to dynamic ones, handling data where the network structure changes every example, such as sequences of variable lengths, trees, and graphs.
State Space LSTM Models with Particle MCMC Inference
Long Short-Term Memory (LSTM) is one of the most powerful sequence models.
Learning Less-Overlapping Representations
In representation learning (RL), how to make the learned representations easy to interpret and less overfitted to training data are two important but challenging issues.
Diversity-Promoting Bayesian Learning of Latent Variable Models
We also extend our approach to "diversify" Bayesian nonparametric models where the number of components is infinite.
Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition
We also show that BiLM weight transfer leads to a faster model training and the pretrained model requires fewer training examples to achieve a particular F1 score.
Techniques for proving Asynchronous Convergence results for Markov Chain Monte Carlo methods
Markov Chain Monte Carlo (MCMC) methods such as Gibbs sampling are finding widespread use in applied statistics and machine learning.
Medical Diagnosis From Laboratory Tests by Combining Generative and Discriminative Learning
In hospital, physicians rely on massive clinical data to make diagnosis decisions, among which laboratory tests are one of the most important resources.
Towards Automated ICD Coding Using Deep Learning
Considering the complicated and dedicated process to assign correct codes to each patient admission based on overall diagnosis, we propose a hierarchical deep learning model with attention mechanism which can automatically assign ICD diagnostic codes given written diagnosis.
Structured Generative Adversarial Networks
We study the problem of conditional generative modeling based on designated semantics or structures.
Deep Determinantal Point Process for Large-Scale Multi-Label Classification
Experiments on the two datasets demonstrate the efficacy and efficiency of the proposed methods.
Dual Motion GAN for Future-Flow Embedded Video Prediction
To make both synthesized future frames and flows indistinguishable from reality, a dual adversarial training method is proposed to ensure that the future-flow prediction is able to help infer realistic future-frames, while the future-frame prediction in turn leads to realistic optical flows.
Generative Semantic Manipulation with Contrasting GAN
Generative Adversarial Networks (GANs) have recently achieved significant improvement on paired/unpaired image-to-image translation, such as photo$\rightarrow$ sketch and artist painting style transfer.
Ranked #4 on
Facial Expression Translation
on CelebA
Learning Latent Space Models with Angular Constraints
The large model capacity of latent space models (LSMs) enables them to achieve great performance on various applications, but meanwhile renders LSMs to be prone to overfitting.
Uncorrelation and Evenness: a New Diversity-Promoting Regularizer
Latent space models (LSMs) provide a principled and effective way to extract hidden patterns from observed data.
Towards Visual Explanations for Convolutional Neural Networks via Input Resampling
The predictive power of neural networks often costs model interpretability.
Efficient Multiple Instance Metric Learning Using Weakly Supervised Data
Classic approaches alternate the optimization over the learned metric and the assignment of similar instances.
Efficient Correlated Topic Modeling with Topic Embedding
Correlated topic modeling has been limited to small model and problem sizes due to their high computational cost and poor scaling.
Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters
We show that Poseidon enables Caffe and TensorFlow to achieve 15. 5x speed-up on 16 single-GPU machines, even with limited bandwidth (10GbE) and the challenging VGG19-22K network for image classification.
On Unifying Deep Generative Models
Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for generative model learning, have largely been considered as two distinct paradigms and received extensive independent studies respectively.
Contextual Explanation Networks
Our results on image and text classification and survival analysis tasks demonstrate that CENs are not only competitive with the state-of-the-art methods but also offer additional insights behind each prediction, that can be valuable for decision support.
Ranked #19 on
Sentiment Analysis
on IMDb
Image Classification
Interpretability Techniques for Deep Learning
+5
Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition.
SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays
Through this adversarial process the critic network learns the higher order structures and guides the segmentation model to achieve realistic segmentation outcomes.
Recurrent Topic-Transition GAN for Visual Paragraph Generation
The proposed Recurrent Topic-Transition Generative Adversarial Network (RTT-GAN) builds an adversarial framework between a structured paragraph generator and multi-level paragraph discriminators.
Generative Adversarial Network
Image Paragraph Captioning
+1
ZM-Net: Real-time Zero-shot Image Manipulation Network
We cast this problem as manipulating an input image according to a parametric model whose key parameters can be conditionally generated from any guiding signal (even unseen ones).
Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
To capture such global interdependency, we propose a deep Variation-structured Reinforcement Learning (VRL) framework to sequentially discover object relationships and attributes in the whole image.
Interpretable Structure-Evolving LSTM
Instead of learning LSTM models over the pre-fixed structures, we propose to further learn the intermediate interpretable multi-level graph structures in a progressive and stochastic way from data during the LSTM network optimization.
Toward Controlled Generation of Text
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain.
Variance Reduction in Stochastic Gradient Langevin Dynamics
In this paper, we present techniques for reducing variance in stochastic gradient Langevin dynamics, yielding novel stochastic Monte Carlo methods that improve performance by reducing the variance in the stochastic gradient.
SeDMiD for Confusion Detection: Uncovering Mind State from Time Series Brain Wave Data
In this paper, we propose an extension of State Space Model to work with different sources of information together with its learning and inference algorithms.
Stochastic Variational Deep Kernel Learning
We propose a novel deep kernel learning model and stochastic variational inference procedure which generalizes deep kernel learning approaches to enable classification, multi-task learning, additive covariance structures, and stochastic gradient training.
Learning Scalable Deep Kernels with Recurrent Structure
To model such structure, we propose expressive closed-form kernel functions for Gaussian processes.
Learning HMMs with Nonparametric Emissions via Spectral Decompositions of Continuous Matrices
Recently, there has been a surge of interest in using spectral methods for estimating latent variable models.
Select-Additive Learning: Improving Generalization in Multimodal Sentiment Analysis
In this paper, we propose a Select-Additive Learning (SAL) procedure that improves the generalizability of trained neural networks for multimodal sentiment analysis.
Learning Concept Taxonomies from Multi-modal Data
We study the problem of automatically building hypernym taxonomies from textual and visual data.
Closed-Form Training of Mahalanobis Distance for Supervised Clustering
Clustering is the task of grouping a set of objects so that objects in the same cluster are more similar to each other than to those in other clusters.
They Are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers
Complex event detection on unconstrained Internet videos has seen much progress in recent years.
Science Question Answering using Instructional Materials
We provide a solution for elementary science test using instructional materials.
Strategies and Principles of Distributed Machine Learning on Big Data
Taking the view that Big ML systems can benefit greatly from ML-rooted statistical and algorithmic insights --- and that ML researchers should therefore not shy away from such systems design --- we discuss a series of principles and strategies distilled from our recent efforts on industrial-scale ML solutions.
Scalable Modeling of Conversational-role based Self-presentation Characteristics in Large Online Forums
Online discussion forums are complex webs of overlapping subcommunities (macrolevel structure, across threads) in which users enact different roles depending on which subcommunity they are participating in within a particular time point (microlevel structure, within threads).
Distributed Training of Deep Neural Networks with Theoretical Analysis: Under SSP Setting
We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines.
Deep Kernel Learning
We introduce scalable deep kernels, which combine the structural properties of deep learning architectures with the non-parametric flexibility of kernel methods.
The Human Kernel
Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity.
Bayesian Nonparametric Kernel-Learning
In this paper we introduce Bayesian nonparmetric kernel-learning (BaNK), a generic, data-driven framework for scalable learning of kernels.
LightLDA: Big Topic Models on Modest Compute Clusters
When building large-scale machine learning (ML) programs, such as big topic models or deep neural nets, one usually assumes such tasks can only be attempted with industrial-sized clusters with thousands of nodes, which are out of reach for most practitioners or academic researchers.
On Model Parallelization and Scheduling Strategies for Distributed Machine Learning
Distributed machine learning has typically been approached from a data parallel perspective, where big data are partitioned to multiple workers and an algorithm is executed concurrently over different data subsets under various synchronization schemes to ensure speed-up and/or correctness.
Dependent nonparametric trees for dynamic hierarchical clustering
Hierarchical clustering methods offer an intuitive and powerful way to model a wide variety of data sets.
Model-Parallel Inference for Big Topic Models
In real world industrial applications of topic modeling, the ability to capture gigantic conceptual space by learning an ultra-high dimensional topical representation, i. e., the so-called "big model", is becoming the next desideratum after enthusiasms on "big data", especially for fine-grained downstream tasks such as online advertising, where good performances are usually achieved by regression-based predictors built on millions if not billions of input features.
High-Performance Distributed ML at Scale through Parameter Server Consistency Models
As Machine Learning (ML) applications increase in data size and model complexity, practitioners turn to distributed clusters to satisfy the increased computational and memory demands.
Screening Rules for Overlapping Group Lasso
However, screening for overlapping group lasso remains an open challenge because the overlaps between groups make it infeasible to test each group independently.
Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms
We develop parallel and distributed Frank-Wolfe algorithms; the former on shared memory machines with mini-batching, and the latter in a delayed update framework.
Primitives for Dynamic Big Model Parallelism
When training large machine learning models with many variables or parameters, a single machine is often inadequate since the model may be too large to fit in memory, while training can take a long time even with stochastic updates.
Hierarchical Feature Hashing for Fast Dimensionality Reduction
Curse of dimensionality is a practical and challenging problem in image categorization, especially in cases with a large number of classes.
Joint Summarization of Large-scale Collections of Web Images and Videos for Storyline Reconstruction
The reconstruction of storyline graphs is formulated as the inference of sparse time-varying directed graphs from a set of photo streams with assistance of videos.
Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos
In this paper, we investigate an approach for reconstructing storyline graphs from large-scale collections of Internet images, and optionally other side information such as friendship graphs.
Quasi Real-Time Summarization for Consumer Videos
With the widespread availability of video cameras, we are facing an ever-growing enormous collection of unedited and unstructured video data.
Dynamic Language Models for Streaming Text
We present a probabilistic language model that captures temporal dynamics and conditions on arbitrary non-linguistic context features.
Petuum: A New Platform for Distributed Machine Learning on Big Data
What is a systematic way to efficiently apply a wide spectrum of advanced ML programs to industrial scale problems, using Big Models (up to 100s of billions of parameters) on Big Data (up to terabytes or petabytes)?
Consistent Bounded-Asynchronous Parameter Servers for Distributed ML
Many ML algorithms fall into the category of \emph{iterative convergent algorithms} which start from a randomly chosen initial point and converge to optima by repeating iteratively a set of procedures.
Language Modeling with Power Low Rank Ensembles
We present power low rank ensembles (PLRE), a flexible framework for n-gram language modeling where ensembles of low rank matrices and tensors are used to obtain smoothed probability estimates of words in context.
Structure-Aware Dynamic Scheduler for Parallel Machine Learning
Training large machine learning (ML) models with many variables or parameters can take a long time if one employs sequential procedures even with stochastic updates.
More Effective Distributed ML via a Stale Synchronous Parallel Parameter Server
We propose a parameter server system for distributed ML, which follows a Stale Synchronous Parallel (SSP) model of computation that maximizes the time computational workers spend doing useful work on ML algorithms, while still providing correctness guarantees.
Restricting exchangeable nonparametric distributions
Distributions over exchangeable matrices with infinitely many columns are useful in constructing nonparametric latent variable models.
Variance Reduction for Stochastic Gradient Optimization
We demonstrate how to construct the control variate for two practical problems using stochastic gradient optimization.
A Scalable Approach to Probabilistic Latent Space Inference of Large-Scale Networks
We propose a scalable approach for making inference about latent spaces of large networks.
Integrating Document Clustering and Topic Modeling
Document clustering and topic modeling are two closely related tasks which can mutually benefit each other.
Sharp Threshold for Multivariate Multi-Response Linear Regression via Block Regularized Lasso
The goal is to recover the support union of all regression vectors using $l_1/l_2$-regularized Lasso.
Sparse Output Coding for Large-Scale Visual Recognition
Many vision tasks require a multi-class classifier to discriminate multiple categories, on the order of hundreds or thousands.
Jointly Aligning and Segmenting Multiple Web Photo Streams for the Inference of Collective Photo Storylines
To this end, we design a scalable message-passing based optimization framework to jointly achieve both tasks for the whole input image set at once.
Monte Carlo Methods for Maximum Margin Supervised Topic Models
An effective strategy to exploit the supervising side information for discovering predictive topic representations is to impose discriminative constraints induced by such information on the posterior distributions under a topic model.
On Triangular versus Edge Representations --- Towards Scalable Modeling of Networks
A triangular motif is a vertex triple containing 2 or 3 edges, and the number of such motifs is $\Theta(\sum_{i}D_{i}^{2})$ (where $D_i$ is the degree of vertex $i$), which is much smaller than $N^2$ for low-maximum-degree networks.
Symmetric Correspondence Topic Models for Multilingual Text Analysis
Topic modeling is a widely used approach to analyzing large text collections.
Graph Estimation From Multi-attribute Data
Many real world network problems often concern multivariate nodal attributes such as image, textual, and multi-view feature vectors on nodes, rather than simple univariate nodal attributes.
Diffusion of Lexical Change in Social Media
Computer-mediated communication is driving fundamental changes in the nature of written language.
Bayesian Inference with Posterior Regularization and applications to Infinite Latent SVMs
When the regularization is induced from a linear operator on the posterior distributions, such as the expectation operator, we present a general convex-analysis theorem to characterize the solution of RegBayes.
High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso
We first show that, with particular choices of kernel functions, non-redundant features with strong statistical dependence on output values can be found in terms of kernel-based independence measures.
Infinite Latent SVM for Classification and Multi-task Learning
Unlike existing nonparametric Bayesian models, which rely solely on specially conceived priors to incorporate domain knowledge for discovering improved latent representations, we study nonparametric Bayesian inference with regularization on the desired posterior distributions.
Kernel Embeddings of Latent Tree Graphical Models
Latent tree graphical models are natural tools for expressing long range and hierarchical dependencies among many variables which are common in computer vision, bioinformatics and natural language processing problems.
Large-Scale Category Structure Aware Image Categorization
With the emergence of structured large-scale dataset such as the ImageNet, rich information about the conceptual relationships between images, such as a tree hierarchy among various image categories, become available.
Adaptive Multi-Task Lasso: with Application to eQTL Detection
To understand the relationship between genomic variations among population and complex diseases, it is essential to detect eQTLs which are associated with phenotypic effects.
Object Bank: A High-Level Image Representation for Scene Classification & Semantic Feature Sparsification
Robust low-level image features have been proven to be effective representations for a variety of visual recognition tasks such as object recognition and scene classification; but pixels, or even local image patches, carry little semantic meanings.
Large Margin Learning of Upstream Scene Understanding Models
This paper presents a joint max-margin and max-likelihood learning method for upstream scene understanding models, in which latent topic discovery and prediction model estimation are closely coupled and well-balanced.
Predictive Subspace Learning for Multi-view Data: a Large Margin Approach
Learning from multi-view data is important in many applications, such as image classification and annotation.
Heterogeneous multitask learning with joint sparsity constraints
In this paper we consider the problem learning multiple related tasks where tasks consist of both continuous and discrete outputs from a common set of input variables that lie in a high-dimensional space.
Time-Varying Dynamic Bayesian Networks
In this paper, we propose a time-varying dynamic Bayesian network (TV-DBN) for modeling the structurally varying directed dependency structures underlying non-stationary biological/neural time series.
Sparsistent Learning of Varying-coefficient Models with Structural Changes
In this paper, we investigate sparsistent learning of a sub-family of this model --- piecewise constant VCVS models.
Sparsistent Estimation of Time-Varying Discrete Markov Random Fields
Network models have been popular for modeling and representing complex relationships and dependencies between observed variables.
A state-space mixed membership blockmodel for dynamic network tomography
In a dynamic social or biological environment, the interactions between the actors can undergo large and systematic changes.
Partially Observed Maximum Entropy Discrimination Markov Networks
Learning graphical models with hidden variables can offer semantic insights to complex data and lead to salient structured predictors without relying on expensive, sometime unattainable fully annotated training data.
Mixed Membership Stochastic Blockmodels
Observations consisting of measurements on relationships for pairs of objects arise in many settings, such as protein interaction and gene regulatory networks, collections of author-recipient email, and social networks.
HM-BiTAM: Bilingual Topic Exploration, Word Alignment, and Translation
We present a novel paradigm for statistical machine translation (SMT), based on joint modeling of word alignment and the topical aspects underlying bilingual document pairs via a hidden Markov Bilingual Topic AdMixture (HM-BiTAM).
