Papers Variational Inference
“Variational Inference” 태그가 달린 논문 2,274편 · 필터 해제
Variational Inference for Latent Variable Models in High Dimensions
Variational inference (VI) is a popular method for approximating intractable posterior distributions in Bayesian inference and probabilistic machine learning. In this paper, we introduce a general framework for quantifyi…
Bayesian InferenceVariational InferenceConstrained Stein Variational Gradient Descent for Robot Perception, Planning, and Identification
Many core problems in robotics can be framed as constrained optimization problems. Often on these problems, the robotic system has uncertainty, or it would be advantageous to identify multiple high quality feasible solut…
Variational InferenceModel Informed Flows for Bayesian Inference of Probabilistic Programs
Variational inference often struggles with the posterior geometry exhibited by complex hierarchical Bayesian models. Recent advances in flow-based variational families and Variationally Inferred Parameters (VIP) each add…
Bayesian InferenceTranslationVariational InferenceLearning Distributions over Permutations and Rankings with Factorized Representations
Learning distributions over permutations is a fundamental problem in machine learning, with applications in ranking, combinatorial optimization, structured prediction, and data association. Existing methods rely on mixtu…
Combinatorial OptimizationRe-RankingStructured PredictionVariational InferenceSynonymous Variational Inference for Perceptual Image Compression
Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this paper, we propose a synonymous variatio…
Image CompressionVariational InferenceNearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
We prove that, given a mean-field location-scale variational family, black-box variational inference (BBVI) with the reparametrization gradient converges at an almost dimension-independent rate. Specifically, for strongl…
Variational InferenceVariational Deep Learning via Implicit Regularization
Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization impose…
Deep LearningInductive BiasSequential Decision MakingUncertainty Quantification+1Bayesian Meta-Reinforcement Learning with Laplace Variational Recurrent Networks
Meta-reinforcement learning trains a single reinforcement learning agent on a distribution of tasks to quickly generalize to new tasks outside of the training set at test time. From a Bayesian perspective, one can interp…
Meta Reinforcement Learningreinforcement-learningReinforcement LearningVariational InferenceScalable Gaussian Processes with Low-Rank Deep Kernel Decomposition
Kernels are key to encoding prior beliefs and data structures in Gaussian process (GP) models. The design of expressive and scalable kernels has garnered significant research attention. Deep kernel learning enhances kern…
Computational EfficiencyGaussian ProcessesUncertainty QuantificationVariational InferenceExponential Convergence of CAVI for Bayesian PCA
Probabilistic principal component analysis (PCA) and its Bayesian variant (BPCA) are widely used for dimension reduction in machine learning and statistics. The main advantage of probabilistic PCA over the traditional fo…
Dimensionality ReductionUncertainty QuantificationVariational InferenceEfficient Training of Neural SDEs Using Stochastic Optimal Control
We present a hierarchical, control theory inspired method for variational inference (VI) for neural stochastic differential equations (SDEs). While VI for neural SDEs is a promising avenue for uncertainty-aware reasoning…
Variational InferencePersonalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation
Personalized Bayesian federated learning (PBFL) handles non-i.i.d. client data and quantifies uncertainty by combining personalization with Bayesian inference. However, existing PBFL methods face two limitations: restric…
Bayesian InferenceFederated LearningVariational InferenceTraining Latent Diffusion Models with Interacting Particle Algorithms
We introduce a novel particle-based algorithm for end-to-end training of latent diffusion models. We reformulate the training task as minimizing a free energy functional and obtain a gradient flow that does so. By approx…
Variational InferenceNash: Neural Adaptive Shrinkage for Structured High-Dimensional Regression
Sparse linear regression is a fundamental tool in data analysis. However, traditional approaches often fall short when covariates exhibit structure or arise from heterogeneous sources. In biomedical applications, covaria…
regressionVariational InferencePhiNet v2: A Mask-Free Brain-Inspired Vision Foundation Model from Video
Recent advances in self-supervised learning (SSL) have revolutionized computer vision through innovative architectures and learning objectives, yet they have not fully leveraged insights from biological visual processing…
Data AugmentationSelf-Supervised LearningVariational InferenceFlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering
Multi-modal and high-dimensional posteriors present significant challenges for variational inference, causing mode-seeking behavior and collapse despite the theoretical expressiveness of normalizing flows. Traditional an…
Variational InferenceCausal View of Time Series Imputation: Some Identification Results on Missing Mechanism
Time series imputation is one of the most challenge problems and has broad applications in various fields like health care and the Internet of Things. Existing methods mainly aim to model the temporally latent dependenci…
ImputationTime SeriesVariational InferenceCombining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review
Bayesian inference has many advantages in decision making of agents (e.g. robotics/simulative agent) over a regular data-driven black-box neural network: Data-efficiency, generalization, interpretability, and safety wher…
Active LearningBayesian InferenceBayesian OptimizationDecision Making+4Channel Fingerprint Construction for Massive MIMO: A Deep Conditional Generative Approach
Accurate channel state information (CSI) acquisition for massive multiple-input multiple-output (MIMO) systems is essential for future mobile communication networks. Channel fingerprint (CF), also referred to as channel …
DenoisingKnowledge DistillationVariational InferenceStochastic Variational Propagation: Local, Scalable and Efficient Alternative to Backpropagation
Backpropagation (BP) is the cornerstone of deep learning, but its reliance on global gradient synchronization limits scalability and imposes significant memory overhead. We propose Stochastic Variational Propagation (SVP…
DiversityRepresentation LearningVariational Inference