Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically resorts to sampling-based approximations of the true marginal, requiring noisy gradient estimators (e.g., score function estimator) or continuous relaxations with lower-variance reparameterized gradients (e.g., Gumbel-Softmax). In this paper, we propose a new training strategy which replaces these estimators by an exact yet efficient marginalization. To achieve this, we parameterize discrete distributions over latent assignments using differentiable sparse mappings: sparsemax and its structured counterparts. In effect, the support of these distributions is greatly reduced, which enables efficient marginalization. We report successful results in three tasks covering a range of latent variable modeling applications: a semisupervised deep generative model, a latent communication game, and a generative model with a bit-vector latent representation. In all cases, we obtain good performance while still achieving the practicality of sampling-based approximations.
Mila（米拉研究所）；University de Montreal（蒙特利尔大学）；Meta AI (FAIR)（元人工智能（基础人工智能研究部））
While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity. In this work, we propose the adoption of latent variable policies within the MaxEnt framework, which we show can provably approximate any policy distribution, and additionally, naturally emerges under the use of world models with a latent belief state. We discuss why latent variable policies …
Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models
Manning College of Information and Computer Sciences University of Massachusetts Amherst（信息与计算机科学学院 马萨诸塞大学阿姆赫斯特分校）；Department of Statistics University of British Columbia（统计学系 不列颠哥伦比亚大学）
Temporal Point Processes (TPP) with partial likelihoods involving a latent structure often entail an intractable marginalization, thus making inference hard. We propose a novel approach to Maximum Likelihood Estimation (MLE) involving approximate inference over the latent variables by minimizing a tight upper bound on the approximation gap. Given a discrete latent variable $Z$, the proposed approximation reduces inference complexity from $O(|Z|^c)$ to $O(|Z|)$. We use convex conjugates to determine this upper bound in a closed form and show that its addition to the optimization objective resul…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Mount Holyoke College（曼荷莲学院）
We develop nested automatic differentiation (AD) algorithms for exact inference and learning in integer latent variable models. Recently, Winner, Sujono, and Sheldon showed how to reduce marginalization in a class of integer latent variable models to evaluating a probability generating function which contains many levels of nested high-order derivatives. We contribute faster and more stable AD algorithms for this challenging problem and a novel algorithm to compute exact gradients for learning. These contributions lead to significantly faster and more accurate learning algorithms, and are the …
We consider the problem of covariance matrix estimation in the presence of latent variables. Under suitable conditions, it is possible to learn the marginal covariance matrix of the observed variables via a tractable convex program, where the concentration matrix of the observed variables is decomposed into a sparse matrix (representing the graphical structure of the observed variables) and a low rank matrix (representing the marginalization effect of latent variables). We present an efficient first-order method based on split Bregman to solve the convex problem. The algorithm is guaranteed to…
Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collection of new methods for end-to-end learning in such models that approximate discrete maximum-weight matching using the continuous Sinkhorn operator. Sinkhorn iteration is attractive because it functions as a simple, easy-to-implement analog of the softmax operator. With this, we can…
Mila（米拉人工智能研究所）；DIRO, Université de Montréal（蒙特利尔大学计算机科学与运筹学系）；ServiceNow Research（ServiceNow研究院）；Tübingen AI Center, University of Tübingen（蒂宾根大学蒂宾根人工智能中心）；Google Research（谷歌研究院）
This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the latent factors of interest depend sparsely on past latent factors and/or observed auxiliary variables. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors and the sparse causal graphical model that relates them. We develop a rigorous identifiability theory, building on recent nonlinear independent component analysis (ICA) results, that formalizes this principle and shows how the latent variables ca…
Google AI（谷歌人工智能（Google AI））；VinAI Research（越南人工智能研究院（VinAI Research））
We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us to use the reparameterization trick, and apply end-to-end training with stochastic gradient descent. We show that the proposed method can successfully segment time series data, including videos and 3D human pose, into meaningful ``regimes'' by using the piece-wise nonlinear dynamics.
German Cancer Research Center (DKFZ)（德国癌症研究中心（DKFZ））；German Cancer Consortium (DKTK)（德国癌症联盟（DKTK））；Goethe University Frankfurt（法兰克福歌德大学）；Frankfurt Cancer Institute（法兰克福癌症研究所）
Many real-world systems are described not only by data from a single source but via multiple data views. In genomic medicine, for instance, patients can be characterized by data from different molecular layers. Latent variable models with structured sparsity are a commonly used tool for disentangling variation within and across data views. However, their interpretability is cumbersome since it requires a direct inspection and interpretation of each factor from domain experts. Here, we propose MuVI, a novel multi-view latent variable model based on a modified horseshoe prior for modeling struct…
It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers. For the Poisson gamma belief network (PGBN), a recently proposed deep discrete LVM, we derive an alternative representation that is referred to as deep latent Dirichlet allocation (DLDA). Exploiting data augmentation and marginalization techniques, we derive a block-diagonal Fisher information matrix and its inverse for the simplex-co…
Learning multiple tasks across heterogeneous domains is a challenging problem since the feature space may not be the same for different tasks. We assume the data in multiple tasks are generated from a latent common domain via sparse domain transforms and propose a latent probit model (LPM) to jointly learn the domain transforms, and the shared probit classifier in the common domain. To learn meaningful task relatedness and avoid over-fitting in classification, we introduce sparsity in the domain transforms matrices, as well as in the common classifier. We derive theoretical bounds for the esti…
Michigan State University（密歇根州立大学）；Argonne National Laboratory（阿贡国家实验室）；Google Research（谷歌研究院）
The information bottleneck framework provides a systematic approach to learning representations that compress nuisance information in the input and extract semantically meaningful information about predictions. However, the choice of a prior distribution that fixes the dimensionality across all the data can restrict the flexibility of this approach for learning robust representations. We present a novel sparsity-inducing spike-slab categorical prior that uses sparsity as a mechanism to provide the flexibility that allows each data point to learn its own dimension distribution. In addition, it …
Carnegie Mellon University（卡内基梅隆大学）；Indian Institute of Science（印度科学研究所）；Microsoft Research India（微软印度研究院）
We consider the problem of learning a latent $k$-vertex simplex $K\subset\mathbb{R}^d$, given access to $A\in\mathbb{R}^{d\times n}$, which can be viewed as a data matrix with $n$ points that are obtained by randomly perturbing latent points in the simplex $K$ (potentially beyond $K$). A large class of latent variable models, such as adversarial clustering, mixed membership stochastic block models, and topic models can be cast as learning a latent simplex. Bhattacharyya and Kannan (SODA, 2020) give an algorithm for learning such a latent simplex in time roughly $O(k\cdot\textrm{nnz}(A))$, wher…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学及其应用实验室）
Structuring the latent space in probabilistic deep generative models, e.g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting. One way to achieve this objective is to impose a sparsity constraint on the latent variables, e.g., via a Laplace prior. However, such approaches usually complicate the training phase, and they sacrifice the reconstruction quality to promote sparsity. In this paper, we propose a simple yet effective methodology to structure the latent space via a sparsity-promoting dictionary model,…
We address the problem of compressed sensing using a deep generative prior model and consider both linear and learned nonlinear sensing mechanisms, where the nonlinear one involves either a fully connected neural network or a convolutional neural network. Recently, it has been argued that the distribution of natural images do not lie in a single manifold but rather lie in a union of several submanifolds. We propose a sparsity-driven latent space sampling (SDLSS) framework and develop a proximal meta-learning (PML) algorithm to enforce sparsity in the latent space. SDLSS allows the range-space …
A Sparsity Principle for Partially Observable Causal Representation Learning
University of Amsterdam（阿姆斯特丹大学）；Institute of Science and Technology Austria（奥地利科技学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Samsung - SAIT AI Lab, Montreal（三星SAIT AI实验室（蒙特利尔））；Mila, Université de Montréal（蒙特利尔大学Mila研究所）；ServiceNow Research（ServiceNow研究院）；Seminar for Statistics, ETH Zürich（苏黎世联邦理工学院统计研究所）
Deep latent variable models are powerful tools for representation learning. In this paper, we adopt the deep information bottleneck model, identify its shortcomings and propose a model that circumvents them. To this end, we apply a copula transformation which, by restoring the invariance properties of the information bottleneck method, leads to disentanglement of the features in the latent space. Building on that, we show how this transformation translates to sparsity of the latent space in the new model. We evaluate our method on artificial and real data.
Aston University（阿斯顿大学）；University of Sussex（萨塞克斯大学）；University of Birmingham（伯明翰大学）；Massachusetts Institute of Technology（麻省理工学院）
Ubiquitous linear Gaussian exploratory tools such as principle component analysis (PCA) and factor analysis (FA) remain widely used as tools for: exploratory analysis, pre-processing, data visualization and related tasks. However, due to their rigid assumptions including crowding of high dimensional data, they have been replaced in many settings by more flexible and still interpretable latent feature models. The Feature allocation is usually modelled using discrete latent variables assumed to follow either parametric Beta-Bernoulli distribution or Bayesian nonparametric prior. In this work we …
We study a norm for structured sparsity which leads to sparse linear predictors whose supports are unions of prede ned overlapping groups of variables. We call the obtained formulation latent group Lasso, since it is based on applying the usual group Lasso penalty on a set of latent variables. A detailed analysis of the norm and its properties is presented and we characterize conditions under which the set of groups associated with latent variables are correctly identi ed. We motivate and discuss the delicate choice of weights associated to each group, and illustrate this approach on simulated…
University of California Berkeley（加州大学伯克利分校）；Intel Corporation（英特尔公司）
We describe a stochastic, dynamical system capable of inference and learning in a probabilistic latent variable model. The most challenging problem in such models - sampling the posterior distribution over latent variables - is proposed to be solved by harnessing natural sources of stochasticity inherent in electronic and neural systems. We demonstrate this idea for a sparse coding model by deriving a continuous-time equation for inferring its latent variables via Langevin dynamics. The model parameters are learned by simultaneously evolving according to another continuous-time equation, thus …
Harvard University（哈佛大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
Originally designed to model text, topic modeling has become a powerful tool for uncovering latent structure in domains including medicine, finance, and vision. The goals for the model vary depending on the application: in some cases, the discovered topics may be used for prediction or some other downstream task. In other cases, the content of the topic itself may be of intrinsic scientific interest. Unfortunately, even using modern sparse techniques, the discovered topics are often difficult to interpret due to the high dimensionality of the underlying space. To improve topic interpretability…
Understanding large-scale patterns in student course enrollment is a problem of great interest to university administrators and educational researchers. Yet important decisions are often made without a good quantitative framework of the process underlying student choices. We propose a probabilistic approach to modelling course enrollment decisions, drawing inspiration from multilabel classification and mixture models. We use ten years of anonymized student transcripts from a large university to construct a Gaussian latent variable model that learns the joint distribution over course enrollment…
Université Paris-Est（巴黎东大学）；Ecole des Ponts（国立桥路学校）
The edge structure of the graph defining an undirected graphical model describes precisely the structure of dependence between the variables in the graph. In many applications, the dependence structure is unknown and it is desirable to learn it from data, often because it is a preliminary step to be able to ascertain causal effects. This problem, known as structure learning, is hard in general, but for Gaussian graphical models it is slightly easier because the structure of the graph is given by the sparsity pattern of the precision matrix of the joint distribution, and because independence co…
University of Virginia（弗吉尼亚大学）；Carnegie Mellon University（卡内基梅隆大学）
We study the estimation of the latent variable Gaussian graphical model (LVGGM), where the precision matrix is the superposition of a sparse matrix and a low-rank matrix. In order to speed up the estimation of the sparse plus low-rank components, we propose a sparsity constrained maximum likelihood estimator based on matrix factorization, and an efficient alternating gradient descent algorithm with hard thresholding to solve it. Our algorithm is orders of magnitude faster than the convex relaxation based methods for LVGGM. In addition, we prove that our algorithm is guaranteed to linearly conv…
Several approximate inference methods have been proposed for deep discrete latent variable models. However, non-parametric methods which have previously been successfully employed for classical sparse coding models have largely been unexplored in the context of deep models. We propose a non-parametric iterative algorithm for learning discrete latent representations in such deep models. Additionally, to learn scale invariant discrete features, we propose local data scaling variables. Lastly, to encourage sparsity in our representations, we propose a Beta-Bernoulli process prior on the latent fa…
We propose a non-linear, Bayesian non-parametric latent variable model where the latent space is assumed to be sparse and infinite dimensional a priori using an Indian buffet process prior. A posteriori, the number of instantiated dimensions in the latent space is guaranteed to be finite. The purpose of placing the Indian buffet process on the latent variables is to: 1.) Automatically and probabilistically select the number of latent dimensions. 2.) Impose sparsity in the latent space, where the Indian buffet process will select which elements are exactly zero. Our proposed model allows for sp…
Time Series Domain Adaptation via Latent Invariant Causal Mechanism
School of Computer Science, Guangdong University of Technology（广东工业大学计算机学院）；Peng Cheng Laboratory（鹏城实验室）；School of Computing, Guangdong University of Technology（广东工业大学计算机学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局信息通信研究所）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
National University of Singapore（新加坡国立大学）；Indian Statistical Institute（印度统计研究所）
Group or cluster structure on explanatory variables in machine learning problems is a very general phenomenon, which has attracted broad interest from practitioners and theoreticians alike. In this work we contribute an approach to learning under such group structure, that does not require prior information on the group identities. Our paradigm is motivated by the Laplacian geometry of an underlying network with a related community structure, and proceeds by directly incorporating this into a penalty that is effectively computed via a heat flow-based local network dynamics. In fact, we demonst…
Structural causal models (SCMs), also known as (nonparametric) structural equation models (SEMs), are widely used for causal modeling purposes. In particular, acyclic SCMs, also known as recursive SEMs, form a well-studied subclass of SCMs that generalize causal Bayesian networks to allow for latent confounders. In this paper, we investigate SCMs in a more general setting, allowing for the presence of both latent confounders and cycles. We show that in the presence of cycles, many of the convenient properties of acyclic SCMs do not hold in general: they do not always have a solution; they do n…
Our goal is to recover time-delayed latent causal variables and identify their relations from measured temporal data. Estimating causally-related latent variables from observations is particularly challenging as the latent variables are not uniquely recoverable in the most general case. In this work, we consider both a nonparametric, nonstationary setting and a parametric setting for the latent processes and propose two provable conditions under which temporally causal latent processes can be identified from their nonlinear mixtures. We propose LEAP, a theoretically-grounded framework that ext…
Accelerating Matrix Factorization by Dynamic Pruning for Fast Recommendation
School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）；College of Integrated Circuits and Optoelectronic Chips, School of Computer Engineering and Science, Shenzhen Technology University（深圳科技大学集成电路与光电芯片学院、计算机工程与科学学院）
Latent Logic Tree Extraction for Event Sequence Explanation from LLMs
School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Skywork AI（Skywork AI公司）
Institut de Mathématiques de Toulouse（图卢兹数学研究所）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；UPS IMT（图卢兹第三大学数学研究所）；Institut de Recherche Technologique Saint-Exupéry（圣埃克苏佩里技术研究所）
We consider a deep structured linear network under sparsity constraints. We study sharp conditions guaranteeing the stability of the optimal parameters defining the network. More precisely, we provide sharp conditions on the network architecture and the sample under which the error on the parameters defining the network scales linearly with the reconstruction error (i.e. the risk). Therefore, under these conditions, the weights obtained with a successful algorithms are well defined and only depend on the architecture of the network and the sample. The features in the latent spaces are stably d…
University of Michigan（密歇根大学）；Technicolor Research Center（特艺集团研究中心）
Gaussian graphical models (GGM) have been widely used in many high-dimensional applications ranging from biological and financial data to recommender systems. Sparsity in GGM plays a central role both statistically and computationally. Unfortunately, real-world data often does not fit well to sparse graphical models. In this paper, we focus on a family of latent variable Gaussian graphical models (LVGGM), where the model is conditionally sparse given latent variables, but marginally non-sparse. In LVGGM, the inverse covariance matrix has a low-rank plus sparse structure, and can be learned in …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
Modern social platforms are characterized by the presence of rich user-behavior data associated with the publication, sharing and consumption of textual content. Users interact with content and with each other in a complex and dynamic social environment while simultaneously evolving over time. In order to effectively characterize users and predict their future behavior in such a setting, it is necessary to overcome several challenges. Content heterogeneity and temporal inconsistency of behavior data result in severe sparsity at the user level. In this paper, we propose a novel mutual-enhanceme…
University of California, San Diego（加州大学圣地亚哥分校）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Mixture models are widely used to fit complex and multimodal datasets. In this paper we study mixtures with high dimensional sparse latent parameter vectors and consider the problem of support recovery of those vectors. While parameter learning in mixture models is well-studied, the sparsity constraint remains relatively unexplored. Sparsity of parameter vectors is a natural constraint in variety of settings, and support recovery is a major step towards parameter estimation. We provide efficient algorithms for support recovery that have a logarithmic sample complexity dependence on the dimensi…
