arXiv research

Alternative optimizer outperforms gradient descent in weakly-supervised CNN segmentation.

Efficiently solves MRF inference problems with semidefinite programming.

The Gibbs sampler is one of the most popular algorithms for inference in statistical models. In this paper, we introduce a herding variant of this algorithm, called herded Gibbs, that is entirely deterministic. We prove that herded Gibbs has an $O(1/T)$ convergence rate for models with independent variables and for ful…

New algorithm improves CRF inference and learning.

New method controls false discovery rate in learning Gaussian MRF structures.

Efficiently infers time-varying sparse MRFs with strong statistical guarantees.

New method controls gradient error for sparse MRFs.

We apply mixup regularization to RNNs for improved performance.

Conditional Random Fields (CRF) have been widely used in a variety of computer vision tasks. Conventional CRFs typically define edges on neighboring image pixels, resulting in a sparse graph such that efficient inference can be performed. However, these CRFs fail to model long-range contextual relationships. Fully-conn…

Hidden Markov Chains and Linear-chain CRFs are equivalent.

LC-CRFs are equivalent to HMMs, and MPM/MAP classifiers can be reformulated as CRFs.

CAT is a new ASR toolkit using CRF and CTC for state-of-the-art speech recognition.

We consider the class of optimization problems arising from computationally intensive L1-regularized M-estimators, where the function or gradient values are very expensive to compute. A particular instance of interest is the L1-regularized MLE for learning Conditional Random Fields (CRFs), which are a popular class of …

AdVIL improves inference and learning for MRFs with minimal assumptions.

Proposes a new method for learning MRFs without sampling.

Graphical models for structured domains are powerful tools, but the computational complexities of combinatorial prediction spaces can force restrictions on models, or require approximate inference in order to be tractable. Instead of working in a combinatorial space, we use hinge-loss Markov random fields (HL-MRFs), an…

Proposes MRF for consistency and privacy in RF.

Paper introduces combinatorial Ricci flows on infinite disk triangulations.

NCRF transducers improve sequence labeling across tasks.

Learning the structure of Markov random fields (MRFs) plays an important role in multivariate analysis. The importance has been increasing with the recent rise of statistical relational models since the MRF serves as a building block of these models such as Markov logic networks. There are two fundamental ways to learn…

New method speeds up sampling of Markov random fields.

Method quantifies uncertainties in complex MRF models.

We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maximum likelihood is the most common approach to training CRFs, it ignores the inherent structure of the task's loss function. We describe alte…

A neural network model minimizes region-based free energy for faster inference in MRFs.

Markov random fields (MRFs) are difficult to evaluate as generative models because computing the test log-probabilities requires the intractable partition function. Annealed importance sampling (AIS) is widely used to estimate MRF partition functions, and often yields quite accurate results. However, AIS is prone to ov…

Locally-contextual CRFs improve sequence labeling performance.

We present Vector-Space Markov Random Fields (VS-MRFs), a novel class of undirected graphical models where each variable can belong to an arbitrary vector space. VS-MRFs generalize a recent line of work on scalar-valued, uni-parameter exponential family and mixed graphical models, thereby greatly broadening the class o…

Markov random field (MRF) learning is intractable, and its approximation algorithms are computationally expensive. We target a small subset of MRF that is used frequently in computer vision. We characterize this subset with three concepts: Lattice, Homogeneity, and Inertia; and design a non-markov model as an alternati…

Deep learning reduces memory and computation for MRF recovery.

We give several equivalent characterizations of orthogonal subbundles of the generalized tangent bundle defined, up to B-field transform, by almost product and local product structures. We also introduce a pure spinor formalism for generalized CRF-structure and investigate the resulting decomposition of the de Rham ope…

Method uses random forest with distance covariance for transfer learning in healthcare.

New CRF model segments music into chords with rich features.

Optimizes ASL-MRF scan design for precise brain hemodynamics quantification.

A fundamental challenge in developing high-impact machine learning technologies is balancing the need to model rich, structured domains with the ability to scale to big data. Many important problem areas are both richly structured and large scale, from social and biological networks, to knowledge graphs and the Web, to…

CAT toolkit combines hybrid and E2E approaches for efficient speech recognition.

The theory of learning under the uniform distribution is rich and deep, with connections to cryptography, computational complexity, and the analysis of boolean functions to name a few areas. This theory however is very limited due to the fact that the uniform distribution and the corresponding Fourier basis are rarely …

Real world systems typically feature a variety of different dependency types and topologies that complicate model selection for probabilistic graphical models. We introduce the ensemble-of-forests model, a generalization of the ensemble-of-trees model. Our model enables structure learning of Markov random fields (MRF) …

FLDCRF improves sequence labeling performance with latent dynamics interactions.

CRF model improves protein secondary structure prediction.

The paper uses MRFs to improve recommendation accuracy in collaborative filtering.

In this paper, we study a nonconvex continuous relaxation of MAP inference in discrete Markov random fields (MRFs). We show that for arbitrary MRFs, this relaxation is tight, and a discrete stationary point of it can be easily reached by a simple block coordinate descent algorithm. In addition, we study the resolution …

New Polish word embeddings improve temporal expression recognition.

A generalized F-structure is a complex, isotropic subbundle $E$ of $T_cM\oplus T^*_cM$ ($T_cM=TM\otimes_{\mathds{R}}\mathds{C}$ and the metric is defined by pairing) such that $E\cap\bar E^{\perp}=0$. If $E$ is also closed by the Courant bracket, $E$ is a generalized CRF-structure. We show that a generalized F-structur…

A new method reduces feature size in CRFs for faster training.

The article confirms Thurston's conjecture for a specific class of 3-manifolds using combinatorial Ricci flow.

We learn higher-order Markov random fields from evolving data, bypassing computational barriers.

In this paper we address the problem of finding the most probable state of a discrete Markov random field (MRF), also known as the MRF energy minimization problem. The task is known to be NP-hard in general and its practical importance motivates numerous approximate algorithms. We propose a submodular relaxation approa…

In this work, we introduce a deep-structured conditional random field (DS-CRF) model for the purpose of state-based object silhouette tracking. The proposed DS-CRF model consists of a series of state layers, where each state layer spatially characterizes the object silhouette at a particular point in time. The interact…