VFG model embeds flow-based models with hierarchical structures using variational inference.
problem Flow-based models struggle with high-dimensional latent spaces and lack of tractable inference for graphical structures.
method Integrates flow-based functions through variational inference with aggregation nodes for hierarchical information integration.
result VFG models achieve improved ELBO and likelihood values on multiple datasets.
Extends VAEs to handle complex Bayesian network structures.
problem Handling complex dependency structures in Bayesian networks.
method Extends VAEs with graphical residual flows to model arbitrary dependency structures.
result Demonstrates improved performance on synthetic datasets.
A new framework uses matrix flows to unify frequentist and Bayesian approaches for sparse GGMs.
problem Challenges in studying conditional independence among many variables with few observations.
method General framework for variational inference with matrix-variate Normalizing Flow in Gaussian Graphical Models.
result Unified benefits of frequentist and Bayesian frameworks for sparse GGMs.
Graphical normalizing flows use Bayesian networks to improve normalizing flows' interpretability and performance.
problem Improving the interpretability and performance of normalizing flows.
method Revisiting normalizing flows as probabilistic graphical models, proposing graphical normalizing flows with either prescribed or learnable graph structures.
result Graphical conditioners lead to competitive white box density estimators.
Consider a mean curvature flow of hypersurfaces in Euclidean space, that is initially graphical inside a cylinder. There exists a period of time during which the flow is graphical inside the cylinder of half the radius. Here we prove a lower bound on this period depending on the Lipschitz-constant of the initial graphi…
Aiming at a comprehensive and concise tutorial survey, recap of variational inference and reinforcement learning with Probabilistic Graphical Models are given with detailed derivations. Reviews and comparisons on recent advances in deep reinforcement learning are made from various aspects. We offer detailed derivations…
The study proves stability of various graphical translators in mean curvature flow.
problem Stability of graphical translators in mean curvature flow.
method Existence of longtime solution to mean curvature flow, dynamical stability results for various graphical translators.
result Dynamical stability of various types of graphical translators.
We propose a general modeling and inference framework that composes probabilistic graphical models with deep learning methods and combines their respective strengths. Our model family augments graphical structure in latent variables with neural network observation models. For inference, we extend variational autoencode…
Study preserves planar and graphical properties of curves under elastic flow.
problem Maintaining planar and graphical properties of non-compact curves under elastic flow.
method Extended recent work on adapted elastic energy to derive thresholds for planar and graphical embeddedness.
result Derived new Li--Yau type inequality for complete planar curves.
We prove rigidity of any properly immersed noncompact Lagrangian shrinker with single valued Lagrangian angle for Lagrangian mean curvature flows. Our pointwise approach also provides an ele- mentary proof to the known rigidity results for graphical and almost graphical shrinkers of mean curvature flows.
New estimate for Curve Shortening Flow improves graphical solutions.
problem Improving regularity estimates for Curve Shortening Flow.
method Generalizing delayed parabolic regularity for Curve Shortening Flow.
result Interior graphical estimate for Curve Shortening Flow.
We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational inference. This allows us to both perform reasoning (e.g. classification) under the structural constraints…
Study on rigidity of translating hypersurfaces not in graphical direction.
problem Rigidity of translating hypersurfaces not in graphical direction.
method Proved rigidity results for complete graphical translating hypersurfaces under specific conditions.
result Entire graphical translating surfaces are flat under certain conditions.
We study graphical mean curvature flow of complete solutions defined on subsets of Euclidean space. We obtain smooth long time existence. The projections of the evolving graphs also solve mean curvature flow. Hence this approach allows to smoothly flow through singularities by studying graphical mean curvature flow wit…
Sharp estimate for flow in any dimension.
problem Interior gradient estimate for graphical mean curvature flow.
method Proving sharp interior gradient estimate for area decreasing graphical mean curvature flow in arbitrary codimension.
result Generalized result in arbitrary codimension.
The study examines the graphical mean curvature flow on compact manifolds with bounded bi-Ricci curvature.
problem Analyzing the graphical mean curvature flow of maps between manifolds with bounded bi-Ricci curvature.
method Proving long-time existence and preserving the strictly area decreasing property under bounded bi-Ricci curvature conditions.
result Smooth convergence to a minimal map under certain conditions on Ricci curvature.
Derives VMP for LDA, simplifying inference for topic modeling.
problem Manual derivation of VMP equations for LDA is challenging and time-consuming.
method Detailed derivation of VMP update equations for LDA.
result Enables easier implementation of VMP for LDA models.
Adaptive approximations improve variational inference for complex models.
problem Efficiently approximate marginal distributions and partition functions in complex probabilistic models.
method Two classes of adaptive approximations that include Bethe, tree-reweighted, and convex free energies.
result Proposed approximations automatically adapt to a given model and outperform existing methods.
Deep networks can approximate score functions in high-dimensional graphical models efficiently.
problem Approximation efficiency of score functions by deep neural networks in high-dimensional graphical models like Markov random fields.
method Variational inference denoising algorithms and efficient neural network representation.
result Efficient sample complexity bound for diffusion-based generative modeling when score functions are learned by deep neural networks.
Pen-and-paper exercises cover various machine learning topics.
problem None explicitly stated, focuses on learning through exercises.
method Pen-and-paper exercises on machine learning topics.
result Comprehensive coverage of machine learning concepts through exercises.
Bayesian structure learning improved using GFlowNets.
problem Inferring Bayesian network structure from data.
method Using Generative Flow Networks (GFlowNets) for approximating posterior DAG distributions.
result DAG-GFlowNet provides an accurate approximation of the posterior over DAGs.
Recent efforts on combining deep models with probabilistic graphical models are promising in providing flexible models that are also easy to interpret. We propose a variational message-passing algorithm for variational inference in such models. We make three contributions. First, we propose structured inference network…
Normalizing flows are shown to be equivalent to Bayesian networks, revealing new insights.
problem Understanding the limitations and capabilities of normalizing flows.
method Revisiting normalizing flows as probabilistic graphical models and analyzing their structure.
result Normalizing flows can be reduced to Bayesian networks, revealing new insights into their structure and capabilities.
The paper studies a flow of spacelike curves in a Lorentz-Minkowski plane, showing convergence to a constant function.
problem Evolution of spacelike graphic curves in Lorentz-Minkowski plane.
method Anisotropic inverse mean curvature flow with vanishing Neumann boundary condition.
result The evolving curves converge to a constant function as time tends to infinity.
A new model learns latent spaces for graph data.
problem Scalability and expressivity limitations in graph generative models.
method Sequential Graph Variational Autoencoder (SGVAE) that learns latent spaces directly from graph data.
result Promising results on a cycle dataset, but need for permutation relaxation.
We analyze variational inference for highly symmetric graphical models such as those arising from first-order probabilistic models. We first show that for these graphical models, the tree-reweighted variational objective lends itself to a compact lifted formulation which can be solved much more efficiently than the sta…
New Harnack inequality for curve shortening flow without convexity.
problem Proving a Harnack inequality for curve shortening flow without convexity.
method Developed a new Harnack inequality for one-dimensional mean curvature flow (curve shortening flow) that doesn't require convexity.
result Explicit time by which an initial curve becomes graphical under curve shortening flow.
Two algorithms learn Gaussian graphical models from Glauber dynamics trajectories.
problem Learning Gaussian graphical models from dependent data.
method Two complementary approaches: local edge-testing and burn-in/thinning reduction.
result Both approaches provide finite-sample recovery guarantees and empirical comparisons.
Proves strong solutions for graphical Brakke flows with L2 normal velocity.
problem Proving strong solutions for graphical Brakke flows with specific velocity conditions.
method Combining L2 normal velocity with parabolic regularity theory. result Graphical Brakke flows with forcing term in Lp,q and C0,α are strong and classical solutions. Recent research has made significant progress on the problem of bounding log partition functions for exponential family graphical models. Such bounds have associated dual parameters that are often used as heuristic estimates of the marginal probabilities required in inference and learning. However these variational est…
Belief Propagation algorithms are instruments used broadly to solve graphical model optimization and statistical inference problems. In the general case of a loopy Graphical Model, Belief Propagation is a heuristic which is quite successful in practice, even though its empirical success, typically, lacks theoretical gu…
We derive pointwise curvature estimates for graphical mean curvature flows in higher codimensions. To the best of our knowledge, this is the first such estimates without assuming smallness of first derivatives of the defining map. An immediate application is a convergence theorem of the mean curvature flow of the graph…
Traffic flow forecasting, especially the short-term case, is an important topic in intelligent transportation systems (ITS). This paper does a lot of research on network-scale modeling and forecasting of short-term traffic flows. Firstly, we propose the concepts of single-link and multi-link models of traffic flow fore…
The paper studies a flow of spacelike surfaces in Lorentz-Minkowski space, proving convergence to a hyperbolic plane.
problem Evolution of spacelike graphic hypersurfaces in Lorentz-Minkowski space.
method Anisotropic inverse mean curvature flow with Neumann boundary condition.
result The flow converges to a hyperbolic plane as time tends to infinity.
We show that (a) any entire graphic self-shrinking solution to the Lagrangian mean curvature flow in Cm with the Euclidean metric is flat; (b) any space-like entire graphic self-shrinking solution to the Lagrangian mean curvature flow in Cm with the pseudo-Euclidean metric is flat if the H…
The paper studies how certain spacelike surfaces evolve over time in a specific space.
problem Evolution of spacelike graphic hypersurfaces in Lorentz-Minkowski space.
method Inverse mean curvature flow with vanishing Neumann boundary condition.
result The evolving surfaces converge to a hyperbolic plane as time goes to infinity.
Many problems in machine learning are naturally expressed in the language of undirected graphical models. Here, we propose black-box learning and inference algorithms for undirected models that optimize a variational approximation to the log-likelihood of the model. Central to our approach is an upper bound on the log-…
Smooth convergence to an enveloping cylinder proved for mean curvature flow of complete graphical hypersurfaces.
problem Proving smooth convergence of mean curvature flow to an enveloping cylinder.
method Analyzing mean curvature flow of complete graphical hypersurfaces over domains Ωt, proving convergence under certain circumstances. result Smooth convergence of Mt−hen+1 to the enveloping cylinder under specific conditions. We study approximations of the partition function of dense graphical models. Partition functions of graphical models play a fundamental role is statistical physics, in statistics and in machine learning. Two of the main methods for approximating the partition function are Markov Chain Monte Carlo and Variational Method…
GmGM models multi-axis data for faster analysis.
problem Efficiently modeling multi-axis data across multiple tensors.
method Generalizes Gaussian Graphical Model to learn sparse graph representations across shared axes.
result Achieves significant speedup (order of magnitude) for large multi-modal datasets.
New method infers graph from dependent matrix data.
problem Inferring graph from dependent matrix data.
method Sparse-group lasso-based frequency-domain formulation with ADMM approach.
result Local convergence of inverse PSD estimators to true value.
The purpose of this paper is twofold: firstly, to establish sufficient conditions under which the mean curvature flow supported on a hypersphere with exterior Dirichlet boundary exists globally in time and converges to a minimal surface, and secondly, to illustrate the application of Killing vector fields in the preser…
Undirected graphical models are applied in genomics, protein structure prediction, and neuroscience to identify sparse interactions that underlie discrete data. Although Bayesian methods for inference would be favorable in these contexts, they are rarely used because they require doubly intractable Monte Carlo sampling…
BASS efficiently learns time-varying graphs with low complexity and automatic tuning.
problem Estimating time-varying graphical models with efficient and automatic parameter tuning.
method BASS uses temporally-dependent spike-and-slab priors and variational inference to learn graph structures efficiently.
result BASS outperforms existing methods in recovering true graphs, especially for high-dimensional cases.
Study on mean curvature flow of graphs in higher dimensions.
problem Analyzing the evolution of graphs under mean curvature flow.
method Derives estimates using a new maximum principle for submanifolds, applies to uniformly area decreasing maps.
result Graphicality and area decreasing property are preserved for uniformly area decreasing maps.
Study of mean curvature flow in de Sitter space, showing convergence to flat slicing.
problem Mean curvature flow in de Sitter space.
method Analysis of mean convex mean curvature flow of local spacelike graphs in de Sitter space.
result As s goes to infinity, Ms becomes graphical in expanding balls, converging to the flat slicing of de Sitter space. Study of mean curvature flow in warped products preserving equivariance.
problem Analyzing mean curvature flow in warped products.
method Deriving flow equation and proving existence for infinite time.
result Mean curvature flow exists for infinite time under specific conditions.
AutoBayes automates Bayesian graph exploration for robust machine learning.
problem Learning representations invariant to nuisance variations in machine learning.
method Automated Bayesian inference framework exploring different graphical models.
result Significant performance improvement with nuisance-invariant machine learning pipelines.