arXiv subjects

Furong Huang

Publications and source records attributed to Furong Huang.

At least 199 records · Page 11Linked to original sources

arXiv2020

Convolutional Tensor-Train LSTM for Spatio-temporal Learning

Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation.However, existing methods still perform poorly on challenging video tasks such as long-term forecasting. This is because these kinds of challenging tasks require learning long-term spatio-temporal correlations in the video sequence. In this paper, we propose a higher-order convolutional LSTM model that can efficiently learn these correlations, along with a succinct representations of the history. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. To make this feasible in terms of computation and memory requirements, we propose a novel convolutional tensor-train decomposition of the higher-order model. This decomposition reduces the model complexity by jointly approximating a sequence of convolutional kernels asa low-rank tensor-train factorization. As a result, our model outperforms existing approaches, but uses only a fraction of parameters, including the baseline models.Our results achieve state-of-the-art performance in a wide range of applications and datasets, including the multi-steps video prediction on the Moving-MNIST-2and KTH action datasets as well as early activity recognition on the Something-Something V2 dataset.

cs.LG↗

arXiv2020

ARMA Nets: Expanding Receptive Field for Dense Prediction

Global information is essential for dense prediction problems, whose goal is to compute a discrete or continuous label for each pixel in the images. Traditional convolutional layers in neural networks, initially designed for image classification, are restrictive in these problems since the filter size limits their receptive fields. In this work, we propose to replace any traditional convolutional layer with an autoregressive moving-average (ARMA) layer, a novel module with an adjustable receptive field controlled by the learnable autoregressive coefficients. Compared with traditional convolutional layers, our ARMA layer enables explicit interconnections of the output neurons and learns its receptive field by adapting the autoregressive coefficients of the interconnections. ARMA layer is adjustable to different types of tasks: for tasks where global information is crucial, it is capable of learning relatively large autoregressive coefficients to allow for an output neuron's receptive field covering the entire input; for tasks where only local information is required, it can learn small or near zero autoregressive coefficients and automatically reduces to a traditional convolutional layer. We show both theoretically and empirically that the effective receptive field of networks with ARMA layers (named as ARMA networks) expands with larger autoregressive coefficients. We also provably solve the instability problem of learning and prediction in the ARMA layer through a re-parameterization mechanism. Additionally, we demonstrate that ARMA networks substantially improve their baselines on challenging dense prediction tasks including video prediction and semantic segmentation.

cs.CV↗

arXiv2020

Using Wavelets and Spectral Methods to Study Patterns in Image-Classification Datasets

Deep learning models extract, before a final classification layer, features or patterns which are key for their unprecedented advantageous performance. However, the process of complex nonlinear feature extraction is not well understood, a major reason why interpretation, adversarial robustness, and generalization of deep neural nets are all open research problems. In this paper, we use wavelet transformation and spectral methods to analyze the contents of image classification datasets, extract specific patterns from the datasets and find the associations between patterns and classes. We show that each image can be written as the summation of a finite number of rank-1 patterns in the wavelet space, providing a low rank approximation that captures the structures and patterns essential for learning. Regarding the studies on memorization vs learning, our results clearly reveal disassociation of patterns from classes, when images are randomly labeled. Our method can be used as a pattern recognition approach to understand and interpret learnability of these datasets. It may also be used for gaining insights about the features and patterns that deep classifiers learn from the datasets.

cs.CV↗

arXiv2020

Understanding Generalization in Deep Learning via Tensor Methods

Deep neural networks generalize well on unseen data though the number of parameters often far exceeds the number of training examples. Recently proposed complexity measures have provided insights to understanding the generalizability in neural networks from perspectives of PAC-Bayes, robustness, overparametrization, compression and so on. In this work, we advance the understanding of the relations between the network's architecture and its generalizability from the compression perspective. Using tensor analysis, we propose a series of intuitive, data-dependent and easily-measurable properties that tightly characterize the compressibility and generalizability of neural networks; thus, in practice, our generalization bound outperforms the previous compression-based ones, especially for neural networks using tensors as their weight kernels (e.g. CNNs). Moreover, these intuitive measurements provide further insights into designing neural network architectures with properties favorable for better/guaranteed generalizability. Our experimental results demonstrate that through the proposed measurable properties, our generalization error bound matches the trend of the test error well. Our theoretical analysis further provides justifications for the empirical success and limitations of some widely-used tensor-based compression approaches. We also discover the improvements to the compressibility and robustness of current neural networks when incorporating tensor operations via our proposed layer-wise structure.

cs.LG↗

arXiv2020

Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning

Model-based reinforcement learning algorithms make decisions by building and utilizing a model of the environment. However, none of the existing algorithms attempts to infer the dynamics of any state-action pair from known state-action pairs before meeting it for sufficient times. We propose a new model-based method called Greedy Inference Model (GIM) that infers the unknown dynamics from known dynamics based on the internal spectral properties of the environment. In other words, GIM can "learn by analogy". We further introduce a new exploration strategy which ensures that the agent rapidly and evenly visits unknown state-action pairs. GIM is much more computationally efficient than state-of-the-art model-based algorithms, as the number of dynamic programming operations is independent of the environment size. Lower sample complexity could also be achieved under mild conditions compared against methods without inferring. Experimental results demonstrate the effectiveness and efficiency of GIM in a variety of real-world tasks.

cs.LG↗

arXiv2020

Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers

Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical robustness. In principle, convex relaxation can provide tight bounds if the solution to the relaxed problem is feasible for the original non-convex problem. We propose two regularizers that can be used to train neural networks that yield tighter convex relaxation bounds for robustness. In all of our experiments, the proposed regularizers result in higher certified accuracy than non-regularized baselines.

cs.LG↗

arXiv2020

An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm

We provide an end-to-end differentially private spectral algorithm for learning LDA, based on matrix/tensor decompositions, and establish theoretical guarantees on utility/consistency of the estimated model parameters. The spectral algorithm consists of multiple algorithmic steps, named as "{edges}", to which noise could be injected to obtain differential privacy. We identify \emph{subsets of edges}, named as "{configurations}", such that adding noise to all edges in such a subset guarantees differential privacy of the end-to-end spectral algorithm. We characterize the sensitivity of the edges with respect to the input and thus estimate the amount of noise to be added to each edge for any required privacy level. We then characterize the utility loss for each configuration as a function of injected noise. Overall, by combining the sensitivity and utility characterization, we obtain an end-to-end differentially private spectral algorithm for LDA and identify the corresponding configuration that outperforms others in any specific regime. We are the first to achieve utility guarantees under the required level of differential privacy for learning in LDA. Overall our method systematically outperforms differentially private variational inference.

stat.ML↗

arXiv2019

Guaranteed Simultaneous Asymmetric Tensor Decomposition via Orthogonalized Alternating Least Squares

Tensor CANDECOMP/PARAFAC (CP) decomposition is an important tool that solves a wide class of machine learning problems. Existing popular approaches recover components one by one, not necessarily in the order of larger components first. Recently developed simultaneous power method obtains only a high probability recovery of top $r$ components even when the observed tensor is noiseless. We propose a Slicing Initialized Alternating Subspace Iteration (s-ASI) method that is guaranteed to recover top $r$ components ($ε$-close) simultaneously for (a)symmetric tensors almost surely under the noiseless case (with high probability for a bounded noise) using $O(\log(\log \frac{1}ε))$ steps of tensor subspace iterations. Our s-ASI method introduces a Slice-Based Initialization that runs $O(1/\log(\frac{λ_r}{λ_{r+1}}))$ steps of matrix subspace iterations, where $λ_r$ denotes the r-th top singular value of the tensor. We are the first to provide a theoretical guarantee on simultaneous orthogonal asymmetric tensor decomposition. Under the noiseless case, we are the first to provide an \emph{almost sure} theoretical guarantee on simultaneous orthogonal tensor decomposition. When tensor is noisy, our algorithm for asymmetric tensor is robust to noise smaller than $\min\{O(\frac{(λ_r - λ_{r+1})ε}{\sqrt{r}}), O(δ_0\frac{λ_r -λ_{r+1}}{\sqrt{d}})\}$, where $δ_0$ is a small constant proportional to the probability of bad initializations in the noisy setting.

stat.ML↗

arXiv2019

Guaranteed Scalable Learning of Latent Tree Models

We present an integrated approach for structure and parameter estimation in latent tree graphical models. Our overall approach follows a "divide-and-conquer" strategy that learns models over small groups of variables and iteratively merges onto a global solution. The structure learning involves combinatorial operations such as minimum spanning tree construction and local recursive grouping; the parameter learning is based on the method of moments and on tensor decompositions. Our method is guaranteed to correctly recover the unknown tree structure and the model parameters with low sample complexity for the class of linear multivariate latent tree models which includes discrete and Gaussian distributions, and Gaussian mixtures. Our bulk asynchronous parallel algorithm is implemented in parallel and the parallel computation complexity increases only logarithmically with the number of variables and linearly with dimensionality of each variable.

cs.LG↗

arXiv2019

Sampling-Free Learning of Bayesian Quantized Neural Networks

Bayesian learning of model parameters in neural networks is important in scenarios where estimates with well-calibrated uncertainty are important. In this paper, we propose Bayesian quantized networks (BQNs), quantized neural networks (QNNs) for which we learn a posterior distribution over their discrete parameters. We provide a set of efficient algorithms for learning and prediction in BQNs without the need to sample from their parameters or activations, which not only allows for differentiable learning in QNNs, but also reduces the variance in gradients. We evaluate BQNs on MNIST, Fashion-MNIST, KMNIST and CIFAR10 image classification datasets, compared against bootstrap ensemble of QNNs (E-QNN). We demonstrate BQNs achieve both lower predictive errors and better-calibrated uncertainties than E-QNN (with less than 20% of the negative log-likelihood).

cs.LG↗

arXiv2019

MLSys: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains a significant obstacle, in large part due to the radically different development and deployment profile of modern ML methods, and the range of practical concerns that come with broader adoption. We propose to foster a new systems machine learning research community at the intersection of the traditional systems and ML communities, focused on topics such as hardware systems for ML, software systems for ML, and ML optimized for metrics beyond predictive accuracy. To do this, we describe a new conference, MLSys, that explicitly targets research at the intersection of systems and machine learning with a program committee split evenly between experts in systems and ML, and an explicit focus on topics at the intersection of the two.

cs.LG↗

arXiv2019

Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?

Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. The expense of producing these examples during training often precludes adversarial training from use on complex image datasets. In this study, we explore the mechanisms by which adversarial training improves classifier robustness, and show that these mechanisms can be effectively mimicked using simple regularization methods, including label smoothing and logit squeezing. Remarkably, using these simple regularization methods in combination with Gaussian noise injection, we are able to achieve strong adversarial robustness -- often exceeding that of adversarial training -- using no adversarial examples.

cs.LG↗

arXiv2018

Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression

We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging, as it corresponds to hierarchical nonlinear tensor decomposition. We propose to solve the learning problem using stochastic gradient descent by deriving nontrivial backpropagation rules in generalized tensor algebra we introduce. Our proposed TNNs has three advantages over existing neural networks: (1) TNNs naturally apply to high order input object and thus preserve the multi-dimensional structure in the input, as there is no need to flatten the data. (2) TNNs interpret designs of existing neural network architectures. (3) Mapping a neural network to TNNs with the same expressive power results in a TNN of fewer parameters. TNN based compression of neural network improves existing low-rank approximation based compression methods as TNNs exploit two other types of invariant structures, periodicity and modulation, in addition to the low rankness. Experiments on LeNet-5 (MNIST), ResNet-32 (CIFAR10) and ResNet-50 (ImageNet) demonstrate that our TNN based compression outperforms (5% test accuracy improvement universally on CIFAR10) the state-of-the-art low-rank approximation based compression methods under the same compression rate, besides achieving orders of magnitude faster convergence rates due to the efficiency of TNNs.

stat.ML↗

arXiv2018

Learning Deep ResNet Blocks Sequentially using Boosting Theory

Deep neural networks are known to be difficult to train due to the instability of back-propagation. A deep \emph{residual network} (ResNet) with identity loops remedies this by stabilizing gradient computations. We prove a boosting theory for the ResNet architecture. We construct $T$ weak module classifiers, each contains two of the $T$ layers, such that the combined strong learner is a ResNet. Therefore, we introduce an alternative Deep ResNet training algorithm, \emph{BoostResNet}, which is particularly suitable in non-differentiable architectures. Our proposed algorithm merely requires a sequential training of $T$ "shallow ResNets" which are inexpensive. We prove that the training error decays exponentially with the depth $T$ if the \emph{weak module classifiers} that we train perform slightly better than some weak baseline. In other words, we propose a weak learning condition and prove a boosting theory for ResNet under the weak learning condition. Our results apply to general multi-class ResNets. A generalization error bound based on margin theory is proved and suggests ResNet's resistant to overfitting under network with $l_1$ norm bounded weights.

cs.LG↗

arXiv2018

Unsupervised Learning of Word-Sequence Representations from Scratch via Convolutional Tensor Decomposition

Unsupervised text embeddings extraction is crucial for text understanding in machine learning. Word2Vec and its variants have received substantial success in mapping words with similar syntactic or semantic meaning to vectors close to each other. However, extracting context-aware word-sequence embedding remains a challenging task. Training over large corpus is difficult as labels are difficult to get. More importantly, it is challenging for pre-trained models to obtain word-sequence embeddings that are universally good for all downstream tasks or for any new datasets. We propose a two-phased ConvDic+DeconvDec framework to solve the problem by combining a word-sequence dictionary learning model with a word-sequence embedding decode model. We propose a convolutional tensor decomposition mechanism to learn good word-sequence phrase dictionary in the learning phase. It is proved to be more accurate and much more efficient than the popular alternating minimization method. In the decode phase, we introduce a deconvolution framework that is immune to the problem of varying sentence lengths. The word-sequence embeddings we extracted using ConvDic+DeconvDec are universally good for a few downstream tasks we test on. The framework requires neither pre-training nor prior/outside information.

cs.CL↗

arXiv2016

Non-negative Factorization of the Occurrence Tensor from Financial Contracts

We propose an algorithm for the non-negative factorization of an occurrence tensor built from heterogeneous networks. We use l0 norm to model sparse errors over discrete values (occurrences), and use decomposed factors to model the embedded groups of nodes. An efficient splitting method is developed to optimize the nonconvex and nonsmooth objective. We study both synthetic problems and a new dataset built from financial documents, resMBS.

cs.CE↗

arXiv2016

Unsupervised learning of transcriptional regulatory networks via latent tree graphical models

Gene expression is a readily-observed quantification of transcriptional activity and cellular state that enables the recovery of the relationships between regulators and their target genes. Reconstructing transcriptional regulatory networks from gene expression data is a problem that has attracted much attention, but previous work often makes the simplifying (but unrealistic) assumption that regulator activity is represented by mRNA levels. We use a latent tree graphical model to analyze gene expression without relying on transcription factor expression as a proxy for regulator activity. The latent tree model is a type of Markov random field that includes both observed gene variables and latent (hidden) variables, which factorize on a Markov tree. Through efficient unsupervised learning approaches, we determine which groups of genes are co-regulated by hidden regulators and the activity levels of those regulators. Post-processing annotates many of these discovered latent variables as specific transcription factors or groups of transcription factors. Other latent variables do not necessarily represent physical regulators but instead reveal hidden structure in the gene expression such as shared biological function. We apply the latent tree graphical model to a yeast stress response dataset. In addition to novel predictions, such as condition-specific binding of the transcription factor Msn4, our model recovers many known aspects of the yeast regulatory network. These include groups of co-regulated genes, condition-specific regulator activity, and combinatorial regulation among transcription factors. The latent tree graphical model is a general approach for analyzing gene expression data that requires no prior knowledge of which possible regulators exist, regulator activity, or where transcription factors physically bind.

q-bio.MN↗

arXiv2016

Discovering Neuronal Cell Types and Their Gene Expression Profiles Using a Spatial Point Process Mixture Model

Cataloging the neuronal cell types that comprise circuitry of individual brain regions is a major goal of modern neuroscience and the BRAIN initiative. Single-cell RNA sequencing can now be used to measure the gene expression profiles of individual neurons and to categorize neurons based on their gene expression profiles. While the single-cell techniques are extremely powerful and hold great promise, they are currently still labor intensive, have a high cost per cell, and, most importantly, do not provide information on spatial distribution of cell types in specific regions of the brain. We propose a complementary approach that uses computational methods to infer the cell types and their gene expression profiles through analysis of brain-wide single-cell resolution in situ hybridization (ISH) imagery contained in the Allen Brain Atlas (ABA). We measure the spatial distribution of neurons labeled in the ISH image for each gene and model it as a spatial point process mixture, whose mixture weights are given by the cell types which express that gene. By fitting a point process mixture model jointly to the ISH images, we infer both the spatial point process distribution for each cell type and their gene expression profile. We validate our predictions of cell type-specific gene expression profiles using single cell RNA sequencing data, recently published for the mouse somatosensory cortex. Jointly with the gene expression profiles, cell features such as cell size, orientation, intensity and local density level are inferred per cell type.

q-bio.NC↗