Stochastic encoders outperform deterministic ones in 'perfect perceptual quality'.
problem Understanding when stochastic encoders outperform deterministic ones.
method Provided a toy example to illustrate performance.
result Stochastic encoders can significantly outperform deterministic ones in 'perfect perceptual quality'.
Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representation may improve the generalization ability of the network. Furthermore, limited models have been presented for inverse reconstructions over ti…
The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the posterior and prior. In NLP, VAEs are extremely difficult to train due to the problem of KL collapsing to zero. One has to implement various heu…
Paper introduces a new method for Transformers with linear complexity.
problem No efficient relative positional encoding for linear Transformer models.
method Stochastic Positional Encoding (SPE) that replaces classical RPE.
result SPE behaves like RPE and performs well on benchmarks.
SFM resolves small-scale physics challenges in weather data.
problem Challenges in super-resolving small-scale details in physical sciences like weather.
method Encoding inputs to a latent base distribution, flow matching for stochastic details, adaptive noise scaling.
result SFM framework significantly outperforms existing methods.
Stochastic encoding improves gender classification of brain networks from UK Biobank data.
problem Complexity and bias in interpreting deep learning models of brain connectivity.
method Stochastic encoding in ensemble of CNNs, multivariate balancing algorithm.
result AUROC of 0.8459, with resting-state data more accurate than task data.
Proposes flexible auto-encoders for varying data dimensions.
problem Fixed latent dimensions limit data flexibility.
method Stochastic bottleneck with weighted dropouts.
result Seamless variable dimensionality reduction with high performance.
PE-SVI reduces SVI inference complexity by finding a suitable start point.
problem Complex posterior inference in graphical models leads to suboptimal learning.
method PE-SVI uses a pseudo-encoded start point to reduce gradient steps and step sizes.
result PE-SVI achieves the same ELBo objective as SVI with less than 1% of the required steps.
ST-MAML tackles task ambiguity in meta-learning by encoding tasks with stochastic representations.
problem Handling tasks from multiple distributions is challenging for meta-learning due to task ambiguity.
method ST-MAML uses a stochastic neural network module to encode tasks and propagate task representations to revise input variable encoding.
result ST-MAML matches or outperforms state-of-the-art methods on various tasks.
Improved graph embedding through refined linear transformation and community recovery.
problem Identifying meaningful latent communities in graph data.
method Refined graph encoder embedding via linear transformation, self-training, and latent community recovery.
result Improved vertex embedding and better decision boundaries for vertex classification.
Paper formalizes and analyzes a new bound for variational inference.
problem Lack of theoretical guarantees in variational algorithms.
method Introduces VR-IWAE bound, a generalization of IWAE.
result VR-IWAE bound leads to unbiased gradient estimators.
VCAE improves autoencoder quality on MNIST and CelebA.
problem Overfitting and poor generative/reconstruction quality in autoencoders.
method Proposes variance-constrained autoencoder (VCAE) to enforce variance constraint on latent distribution.
result VCAE outperforms Wasserstein Autoencoder and Variational Autoencoder in quality.
Method learns model for unknown stochastic system from data.
problem Modeling unknown stochastic dynamical systems.
method Autoencoder approach using deep neural networks (DNNs).
result Decoder serves as a predictive model for unknown stochastic systems.
Deterministic training improves generative autoencoder performance.
problem Stochastic training limits generative autoencoder performance.
method Invertible layers for deterministic training.
result AEFs outperform VAEs in log-likelihood and sample quality.
A new model encodes distances and topology in latent variables.
problem Modeling dissimilarity data with latent variables and invariances.
method Isometric Gaussian Process Latent Variable Model using Riemannian geometry and variational inference.
result The model can encode invariances in learned manifolds.
PriorCVAE uses deep generative models to infer hyperparameters in MCMC.
problem Losing hyperparameter information in GP prior inference.
method Conditioning VAE on hyperparameters to encode and estimate them during inference.
result PriorCVAE enables efficient and distinct inference of hyperparameters.
A novel VAE called πVAE models complex data with stochastic processes.
problem Efficient inference of stochastic processes for Bayesian deep learning with big data.
method πVAE is a finitely exchangeable, Kolmogorov consistent, continuous stochastic process VAE.
result πVAE achieves state-of-the-art performance in tasks like spatial interpolation.
Enhances deep kernel learning with stochastic latent variables for better model regularization.
problem Weak model regularization in deep kernel learning, especially on small datasets.
method Introduces DLVKL model with stochastic latent variables, NSDE for expressive posterior, and hybrid prior.
result DLVKL-NSDE outperforms existing deep GPs on large datasets.
The paper proposes using Autoencoders to learn summary statistics for Bayesian inference.
problem Approximating posterior distributions for models with intractable likelihood functions.
method Using Autoencoders to extract summary statistics that retain parameter information and cancel noise.
result The approach effectively learns summary statistics that improve posterior approximation.
Bayesian attention improves model performance and robustness.
problem Limited exploration of stochastic attention in neural networks.
method Introduces Bayesian attention belief networks using gamma and Weibull distributions.
result Outperforms deterministic and stochastic attention methods in accuracy and robustness.
This paper considers the problem of implementing large-scale gradient descent algorithms in a distributed computing setting in the presence of {\em straggling} processors. To mitigate the effect of the stragglers, it has been previously proposed to encode the data with an erasure-correcting code and decode at the maste…
Develops a flexible deep autoencoding topic model with scalable hybrid Bayesian inference.
problem Flexible and interpretable document analysis models.
method DATM with hybrid Bayesian inference, including topic-layer-adaptive stochastic gradient Riemannian MCMC and Weibull variational encoder.
result Demonstrates scalability and efficacy on big corpora in unsupervised and supervised learning tasks.
MIM learns joint distributions with mutual information and low divergence.
problem Learning joint distributions over observations and latent variables.
method Probabilistic auto-encoder with three design principles: low divergence, high mutual information, and low marginal entropy.
result MIM learns representations with high mutual information, consistent encoding and decoding distributions, effective latent clustering, and comparable data log likelihood to VAE.
LSI enables joint learning of latent variables and generative models.
problem Joint optimization of latent variables and generative models.
method Developed a principled ELBO objective in continuous time for joint learning.
result LSI learns effective latent representations and generative transformations.
We present a theory of homogeneous volatility bridge estimators for log-price stochastic processes. The main tool of our theory is the parsimonious encoding of the information contained in the open, high and low prices of incomplete bridge, corresponding to given log-price stochastic process, and in its close value, fo…
Proposes a new model for directed graphs combining deep learning and latent variable models.
problem Graph representation learning for directed graphs.
method Deep Latent Space Model (DLSM) integrating GCN encoder and stochastic decoder with hierarchical variational auto-encoder architecture.
result Achieves state-of-the-art performance on link prediction and community detection tasks.
A novel capsule network model improves surrogate modeling and uncertainty quantification from sparse data.
problem Surrogate modeling and uncertainty quantification of systems from sparse data.
method Adapted Capsule Network (CapsNet) architecture into image-to-image regression encoder-decoder network.
result The proposed approach accurately, efficiently, and robustly predicts responses for arbitrary diffusion fields.
New bounds enable training of probabilistic models for deep networks.
problem Training scalable latent variable models for deep networks.
method Introducing new variational bounds for specific output layers of neural networks.
result Analytical bounds for certain output layers allow training without re-parameterization or Monte Carlo approximations.
We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent approximate posterior distributions, and that acts as…
In this note we present a generative model of natural images consisting of a deep hierarchy of layers of latent random variables, each of which follows a new type of distribution that we call rectified Gaussian. These rectified Gaussian units allow spike-and-slab type sparsity, while retaining the differentiability nec…
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols. Despite its simplicity, such approach yields the number of parameters that grows linearly with the vocabulary s…
Stochastic approach improves neural network training for kinetic simulations.
problem Training neural networks under physical constraints in kinetic fusion simulations.
method Stochastic augmented Lagrangian approach using pyTorch.
result Higher model prediction accuracy achieved compared to fixed penalty method.
New model improves traffic flow predictions with physics and machine learning.
problem Inaccurate predictions in traffic flow modeling with small or noisy datasets.
method Developed a physics regularized Gaussian process (PRGP) model to encode physical models into ML architecture and regularize the training process.
result The PRGP model outperforms previous methods in estimation precision and input robustness.
Quantum methods model uncertain volatility in financial markets.
problem Modeling financial asset prices with uncertain volatility.
method Quantum stochastic calculus with unitary and non-unitary time evolution.
result Different volatility levels encoded in quantum states, leading to varied market price evolutions.
Geometric arbitrage theory reformulates a generic asset model possibly allowing for arbitrage by packaging all asset and their forward dynamics into a stochastic principal fibre bundle, with a connection whose parallel transport encodes discounting and portfolio rebalancing, and whose curvature measures, in this geomet…
We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well. This is accomplished by generalizing the gradient computation in stochastic backpropagation via a reparametriza…
Embedding methods such as word embedding have become pillars for many applications containing discrete structures. Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying linear transformation based on "one-hot" encoding of the discrete symbols. …
Researchers interpret SGD using diffusion metrics for clearer geometric understanding.
problem Elusiveness of geometrical significance in stochastic gradient descent.
method Study a deterministic model with geodesics of diffusion metrics.
result Establishes parallel with General Relativity models.
Bayesian approach for policy search in stochastic domains.
problem Policy search in stochastic domains.
method Nested probabilistic programs, Lightweight Metropolis-Hastings (LMH) adaptation.
result Similar quality policies learned with simpler algorithm.
Acoustic Neighbor Embeddings map speech and text to fixed dimensions for phonetic confusability.
problem Mapping speech and text to fixed dimensions for phonetic confusability.
method Adapting SNE to sequential inputs, training two encoder neural networks.
result More accurate results with low-dimensional embeddings in word recognition tasks.
Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing approaches to modeling this stochasticity typically combine a random noise vector with information about the previous poses. This combination, however, is done in a deterministic manner,…
QSD enhances deep network performance through biologically plausible dropout.
problem Overfitting in deep networks.
method Quantal Synaptic Dilution (QSD) model based on neuronal synapses.
result QSD outperforms standard dropout in various deep network architectures.
Mutual information bounds generalization error in variational classifiers.
problem Controlling overfitting in variational classifiers.
method Derive bounds on generalization error using mutual information.
result Mutual information bounds the generalization error in variational classifiers.
New method selects features for sequential decision making.
problem Dynamic feature selection for instance-wise decisions.
method Latent variable model trained in a supervised manner; reasoning across stochastic latent space.
result Outperforms existing methods on various datasets.
Quantum Portfolios of quantum algorithms encoded on qbits have recently been reported. In this paper a discussion of the continuous variables version of quantum portfolios is presented. A risk neutral valuation model for options dependent on the measured values of the observables, analogous to the traditional Black-Sch…
Integrates inductive biases into VAEs using intermediary latent variables.
problem Ineffective mechanisms for incorporating inductive biases into VAEs.
method InteL-VAEs use an intermediary latent space to control encoding, with a parametric function to enforce desired properties.
result InteL-VAEs lead to better generative models and representations.
The contractive auto-encoder learns a representation of the input data that captures the local manifold structure around each data point, through the leading singular vectors of the Jacobian of the transformation from input to representation. The corresponding singular values specify how much local variation is plausib…
To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable augmentation, REINFORCE, and reparameterization, the ARM estimator achieves adaptive variance reducti…