Generative model ensures valid discrete data outputs.
problem Challenges in generative modeling of discrete data like arithmetic expressions and molecular structures.
method Grammar Variational Autoencoder (GVAE) that encodes and decodes to/from parse trees, ensuring valid outputs.
result Generates more coherent latent space with valid discrete outputs.
MHG-VAE achieves 100% valid molecules with simpler architecture.
problem Generating valid molecules and evaluating properties efficiently.
method MHG-VAE uses molecular hypergraph grammar to guide a single VAE.
result 100% validity achieved with simpler architecture.
TES-AE uses tree grammars to speed up autoencoding for tree data.
problem Challenges in autoencoding tree data due to its non-vectorial and discrete nature.
method TES-AE combines reservoir computing with tree grammars for faster training.
result TES-AE outperforms D-VAE in speed and accuracy for tree data.
New grammar model learns sentence structure with latent variables.
problem Grammar induction for sentences with complex dependencies.
method Compound probabilistic context-free grammar with latent variables, variational inference.
result Effective unsupervised parsing compared to state-of-the-art methods.
SIVAE integrates sentences and their syntactic trees for improved text generation.
problem Improving the grammar of generated text.
method SIVAE uses two separate latent spaces for sentences and syntactic trees, optimizing a joint distribution with two encoders and two decoders.
result SIVAE generates sentences with better grammar compared to existing models.
Unsupervised RNNGs perform similarly to supervised ones in language modeling and grammar induction.
problem Training RNNGs requires annotated data, which is costly.
method Amortized variational inference with a neural CRF parser.
result Unsupervised RNNGs achieve comparable performance to supervised ones.
GFlowNet-EM learns complex latent variable models with discrete structures.
problem Challenges in modeling posteriors over discrete compositional latents with expectation-maximization.
method Uses GFlowNets to learn stochastic policies for sampling from complex posterior distributions.
result GFlowNet-EM enables training expressive LVMs with discrete compositional latents.
Method extracts knowledge from LSTM for sequence validation.
problem Validating sequences generated by unknown automata.
method Clustering hidden states to build a corresponding automaton.
result Automaton accurately predicts sequence validity.
Probabilistic grammars improve equation discovery from data.
problem Discovering scientific laws from data using equations.
method Proposed probabilistic context-free grammars to encode soft constraints and a Monte-Carlo algorithm.
result Probabilistic grammars lead to more efficient equation discovery.
AG-RL uses action grammars to improve reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Integrates action grammars into reinforcement learning algorithms to enhance performance.
result Significant improvement in performance across multiple Atari games.
Variational autoencoders learn deep latent models.
problem Learning deep latent-variable models.
method Principled framework using variational inference.
result Introduction to variational autoencoders and extensions.
Unified recurrent networks reveal differences in complexity levels of grammars.
problem Understanding the complexity and behavior of recurrent networks.
method Connecting recurrent networks with deterministic finite automata and formal grammars.
result Unified recurrent networks improve performance and match grammars from different complexity levels.
A grammar-driven tree-to-tree model improves program translation accuracy.
problem Improving program translation accuracy between programming languages.
method A grammar-driven tree-to-tree model that exploits known grammar rules of the target language.
result The grammar-based model outperforms state-of-the-art models in program translation accuracy.
Diffusion Variational Autoencoders capture topological properties of datasets.
problem Standard VAEs struggle with topological properties of certain datasets.
method Introduces Diffusion VAEs with transition kernels of Brownian motion on arbitrary manifolds.
result Diffusion VAEs can capture topological properties of synthetic datasets.
AlphaCFG discovers alpha factors using grammar-guided search.
problem Discovering formulaic alpha factors in finance.
method AlphaCFG uses a grammar-based framework to define and discover alpha factors with syntactic and semantic constraints.
result AlphaCFG outperforms state-of-the-art methods in trading profitability and efficiency.
Paper proposes a new autoencoder to handle complex data structures.
problem Challenges in latent variable learning with complex data.
method Variational Composite Autoencoder using hierarchical latent variable model.
result Experimental results show the new model's advantages.
This work prevents variational autoencoders from collapsing by adding an auxiliary decoder.
problem Variational autoencoders can collapse into autodecoders, losing semantic information.
method Adding an auxiliary decoder to regularize the latent space.
result Auxiliary decoders increase semantic information in the latent space and reconstructions.
We propose a new statistical model for computational linguistics. Rather than trying to estimate directly the probability distribution of a random sentence of the language, we define a Markov chain on finite sets of sentences with many finite recurrent communicating classes and define our language model as the invarian…
Codebook for Institutional Grammar 2.0 simplifies policy encoding.
problem Facilitating consistent policy encoding for diverse analytical needs.
method Revised Institutional Grammar with multiple levels of expressiveness.
result Enhanced flexibility and specificity in policy encoding.
Efficient molecular optimization using probabilistic hypergraph grammars and reinforcement learning.
problem Optimizing molecular structures for better performance in various benchmarks.
method Inferred a hypergraph replacement grammar from ChEMBL, used conditional priors for policy model, and applied a modified policy gradient algorithm.
result The approach results in a molecular distribution closer to the training set than using equal or unconditional priors.
Develops inference combinators for probabilistic programs using neural networks.
problem Creating efficient proposals for probabilistic program inference.
method Inference combinators using neural network parameterization of proposals.
result Correct by construction variational methods tailored to specific models.
This tutorial derives the VAE loss function under Gaussian assumptions.
problem Computational intractability of posterior distributions in Bayesian machine learning.
method Derives the variational lower bound loss function of a standard VAE.
result The Kullback-Leibler divergence has a closed form solution under Gaussian assumptions.
This paper improves VAEs with regularization for better image reconstruction.
problem Improving image reconstruction quality in Variational Autoencoders.
method Least square loss function with regularization for better approximation of data.
result Least square loss function leads to better reconstructed images and faster training.
We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesian nonparametric version of the variational autoencoder that has a latent representation with stocha…
This paper quantifies how varying β affects disentanglement in variational autoencoders.
problem The challenge is to quantify the effects of β on disentanglement in variational autoencoders. method The approach involves training multiple variational autoencoders with the same β value and analyzing the disentanglement measures. result There is consistent variance in one disentanglement measure, indicating negative effects on discriminative ability.
Generalized Earley parser predicts future events from sequence data.
problem Predicting future events from unsegmented, unlabeled sequence data.
method Integrates grammar parsing and classification for optimal segmentation and labels.
result Significantly outperforms other approaches in future human activity prediction.
Dr.VAE improves drug response prediction accuracy.
problem Improving accuracy of drug response prediction.
method Two deep generative models based on Variational Autoencoders.
result Dr.VAE outperforms benchmarks by 3-11% AUROC and 2-30% AUPR.
A new speech enhancement method using variational autoencoders.
problem Improving speech quality in noisy environments.
method Using a variational autoencoder as a speech model, trained with unsupervised noise modeling.
result The method outperforms existing techniques in speech enhancement.
Variational autoencoders model water Cherenkov detector data.
problem Modeling generative distribution of water Cherenkov detector data.
method Variational autoencoders and normalizing flows.
result Demonstrated capability of variational autoencoders for generative modelling.
Variational autoencoders often collapse, showing latent variables are non-identifiable.
problem Posterior collapse in variational autoencoders due to non-identifiable latent variables.
method Proves latent variable non-identifiability causes posterior collapse. Proposes latent-identifiable models using Brenier maps and input convex neural networks.
result Latent-identifiable models resolve posterior collapse and provide meaningful representations.
The paper interprets VQ-VAE loss as a form of information bottleneck.
problem Understanding the VQ-VAE loss function.
method Interpreted VQ-VAE loss as variational deterministic information bottleneck (VDIB) and variational information bottleneck (VIB).
result VQ-VAE loss can be derived from VDIB and approximated by VIB.
Proposes a method to train neural networks directly on compressed text data.
problem Training neural networks on compressed text data without decompression.
method Introduces composer modules to encode symbols from grammar compression rules into vector representations.
result Demonstrates that the proposed method can achieve both memory and computational efficiency while maintaining moderate performance.
DAEs can generate images without additional loss terms, inheriting VAE properties.
problem Difficulty in using VAEs for practical generative modelling.
method Empirical exploration of DAEs for image generation without novel methods.
result DAEs can generate images successfully without additional loss terms.
Improved AutoML performance with a pipeline grammar and pre-trained model.
problem Automatic machine learning by pipeline synthesis.
method Model-based reinforcement learning and pipeline grammar.
result Improved performance on AutoML benchmark datasets.
InfoVAE improves variational autoencoders by better training inference distributions.
problem Inaccurate amortized inference and latent variable neglect in variational autoencoders.
method Proposes new training objectives (InfoVAE) to improve inference quality and latent feature use.
result Significantly improves variational posterior quality and effective latent feature use.
Study reveals the regularization effect of variational distributions in VAEs.
problem Understanding the regularization role of variational distributions in VAEs.
method Analyzed the role of variational family in VAEs and studied the regularization effect on local geometry.
result Uncovered the implicit regularizer in the β-VAE objective and proposed a deterministic autoencoding objective. Derives M2VAE objective from marginal joint log-likelihood.
problem Training Multi-Modal Variational Autoencoders (M2VAEs). method Derives trainable evidence lower bound from marginal joint log-likelihood.
result Derives M2VAE objective from marginal joint log-likelihood. Combines variational autoencoders with normalizing flows for faster training.
problem Training normalizing flow models like Glow is slow and requires deep architectures.
method Integrates Glow with a variational autoencoder to speed up training.
result The combined model achieves similar image quality and likelihood to Glow but trains faster.
Variational autoencoders struggle with inference quality due to recognition network limitations.
problem Inference suboptimality in variational autoencoders.
method Examined approximate inference in terms of variational distribution capacity and recognition network quality.
result Inference quality is more influenced by recognition network limitations than variational distribution complexity.
New method uses adversarial networks to improve image quality in autoencoders.
problem Blurriness in autoencoder-generated images due to Gaussian assumptions.
method Integrates adversarial networks to optimize parameters without Gaussian assumptions.
result Improves image quality by allowing better representation of multimodal distributions.
Wasserstein variational inference uses optimal transport for stable likelihood-free training.
problem Approximate Bayesian inference with stability and flexibility for implicit distributions.
method Optimal transport theory, Sinkhorn iterations, and backpropagation.
result Stable likelihood-free training method for autoencoders and probabilistic programs.
Paper proposes efficient multivariate spatial Fay-Herriot models using variational autoencoders.
problem Estimating population characteristics in small areas with limited data.
method Integrates multivariate spatial Fay-Herriot model with variational autoencoders to leverage spatial structure efficiently.
result Significant computational efficiency improvements for high-dimensional datasets.
A neural model samples arbitrary features conditioned on some inputs.
problem Sampling arbitrary features conditioned on some inputs.
method Variational autoencoder with stochastic variational Bayes training.
result Effectiveness and diversity of generated samples on synthetic data and feature problems.
VAE improves MSI data analysis for tissue sub-types.
problem Analyzing MSI data from unprocessed samples.
method Applied Variational Autoencoders for data reduction and pattern detection.
result VAEs outperform standard methods in detecting tissue sub-types.
Net2Vis automates CNN visualization for publications.
problem Lack of consistent visual representations in deep learning papers.
method Proposes a visual grammar and automated system for generating publication-ready CNN visualizations.
result Reduces time and ambiguity in generating network visualizations.
Novel variational autoencoder for generative and classification tasks.
problem Developing a robust generative model for various tasks.
method A novel variational autoencoder with specific latent variables and ordinality enforcement.
result Comparable performance in generative and classification tasks compared to baselines.
Develops VAEs with graphical models for interpretable representations.
problem Creating interpretable representations in complex, high-dimensional data.
method Incorporates structured graphical models into VAE encoders for approximate variational inference.
result Induces interpretable representations with deep generative models under structural constraints.
Reinterprets IWAE as optimizing a tighter variational bound.
problem Improving variational lower bounds in autoencoders.
method Derives and visualizes a tighter lower bound using a more complex distribution.
result IWAE optimizes the standard variational lower bound with a complex distribution.