Generative Latent Implicit Conditional Optimization (GLICO) learns from small samples.
problem Learning from small labeled datasets.
method Generative Latent Implicit Conditional Optimization (GLICO) learns a latent space and generator from small labeled data.
result GLICO synthesizes new samples for every class using as few as 10 examples per class.
Paper introduces CageBO for optimizing complex public policy problems.
problem Complex decision-making and implicit constraints in public policy.
method CageBO framework using conditional variational autoencoder.
result CageBO outperforms baselines in optimizing large-scale police redistricting.
In this paper, we describe the "implicit autoencoder" (IAE), a generative autoencoder in which both the generative path and the recognition path are parametrized by implicit distributions. We use two generative adversarial networks to define the reconstruction and the regularization cost functions of the implicit autoe…
Proposes LDIDPs for efficient sequential data generation from latent dynamical models.
problem Challenges in generating high-fidelity sequential samples from latent dynamical models.
method Utilizes implicit diffusion processes to sample from latent dynamical processes.
result Demonstrates accurate learning of dynamics and efficient generation of high-quality sequential data.
Develops efficient algorithms for learning latent-variable models using implicit moment tensor computation.
problem Learning latent-variable models with moment tensors of super-constant degree.
method Implicit moment tensor computation for general models, extending previous work on clustering mixtures of spherical Gaussians.
result First poly(d, k) time learning algorithms for various models including mixtures of linear regressions, spherical Gaussians, and positive linear combinations of non-linear activations.
The paper provides theoretical guarantees for transformation-based models in variational inference.
problem Theoretical justification for transformation-based models in variational inference.
method Theoretical analysis of non-linear latent variable models and Gaussian process priors.
result Theoretical guarantees for implicit variational inference, achieving optimal risk bounds and approximating the true posterior.
Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models. However, the majority of existing methods have limited expressive power due to the Gaussian assumption of latent variables. In t…
DDMI generates high-quality INRs by adapting positional embeddings.
problem Existing INR generative models fail to produce high-quality representations.
method DDMI uses adaptive positional embeddings and a D2C-VAE to enhance expressive power.
result DDMI outperforms existing models across multiple modalities and datasets.
Improves GANs by sampling from an energy-based model induced by discriminator scores.
problem Improving the quality of images generated by GANs.
method DDLS (Discriminator Driven Latent Sampling) using the sum of latent prior log-density and discriminator output score.
result Significantly improves Inception Score on CIFAR-10 dataset.
Flexible copula model using implicit generative neural networks.
problem Limited flexibility of parametric copulas and curse of dimensionality in non-parametric methods.
method Implicit generative neural networks to model high-dimensional copula distributions with unspecified marginals.
result Demonstrated flexibility and performance on various datasets.
We introduce a new category of multivariate conditional generative models and demonstrate its performance and versatility in probabilistic time series forecasting and simulation. Specifically, the output of quantile regression networks is expanded from a set of fixed quantiles to the whole Quantile Function by a univar…
Memory-based models can learn to approximate Bayes-optimal predictors for non-stationary data.
problem Learning from non-stationary data with unobserved switching points.
method Memory-based neural models, including Transformers, LSTMs, and RNNs, trained to minimize log loss.
result Memory-based models can accurately approximate known Bayes-optimal algorithms and perform Bayesian inference over latent switching points.
Bayesian approach optimizes in-context learning for state space models.
problem Optimizing in-context learning for state space models.
method Bayesian optimal sequential prediction over latent sequence tasks.
result Bayesian optimal predictor converges to posterior predictive mean.
The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the latent variable given the data point is regularized by the prior of the latent variable using Kullback Leibler (KL) divergence. Although the stan…
Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Previous works mitigated such problem by heuristic methods such as strengthe…
Proposes efficient, modular method for implicit differentiation.
problem Implicit differentiation of optimization problems.
method Automatic implicit differentiation using autodiff and implicit function theorem.
result Automatic differentiation of optimization problems is made easier and more modular.
AR-CSM models use derivatives of univariate log-conditionals to estimate joint distributions efficiently.
problem Scalability and stability issues in training autoregressive models.
method Parameterize joint distribution using derivatives of univariate log-conditionals and introduce Composite Score Matching (CSM) for efficient training.
result AR-CSM models are more scalable and stable compared to previous score matching algorithms.
Unified framework for learning function representations using INRs and Transformers.
problem Scalability and efficiency limitations in existing generative models.
method Integrates INRs and Transformer-based hypernetworks into latent variable models.
result Improved scalability, expressiveness, and generalization over existing models.
The paper analyzes optimal implicit bias in linear regression for over-parameterized models.
problem Finding the best generalization performance in over-parameterized linear regression.
method Asymptotic analysis of generalization performance for convex functions/potentials.
result Optimal implicit bias that achieves the best generalization error under certain conditions.
Enhances graph modeling with hyperbolic geometry and variational inference.
problem Challenges in modeling relational data with complex dependencies.
method Semi-implicit hierarchical variational Bayes with Poincaré embedding and mutual information regularization.
result Improves graph representation quality and flexibility in edge prediction and node classification.
IRMAE learns compact latent spaces by minimizing rank.
problem Learning compact latent representations in autoencoders.
method Implicitly minimizes the rank of the covariance matrix through gradient descent in multi-layer linear networks.
result Demonstrates validity on image generation and representation learning tasks.
LiLaN uses linear latent networks to solve stiff ODEs efficiently.
problem Solving stiff ordinary differential equations (StODEs) requires expensive methods.
method LiLaN integrates latent dynamics analytically, avoiding explicit/implicit integration.
result LiLaN can approximate stiff nonlinear systems to any accuracy epsilon.
SLOGAN improves GANs' conditional generation by balancing latent attribute distributions.
problem Imbalanced latent attribute distributions in GANs.
method Stein latent optimization with a Gaussian mixture prior and contrastive loss.
result SLOGAN achieves state-of-the-art unsupervised conditional generation performance.
Most successful machine intelligence systems rely on gradient-based learning, which is made possible by backpropagation. Some systems are designed to aid us in interpreting data when explicit goals cannot be provided. These unsupervised systems are commonly trained by backpropagating through a likelihood function. We i…
The recent success of Generative Adversarial Networks (GAN) is a result of their ability to generate high quality images from a latent vector space. An important application is the generation of images from a text description, where the text description is encoded and further used in the conditioning of the generated i…
XLVINs improve data efficiency in implicit planning by leveraging latent space.
problem Improving data efficiency in implicit planning algorithms.
method XLVINs use a high-dimensional latent space to perform planning computations, breaking the algorithmic bottleneck.
result XLVINs significantly improve data efficiency across various settings compared to value iteration-based implicit planners and model-free baselines.
We tackle the challenge of disentangled representation learning in generative adversarial networks (GANs) from the perspective of regularized optimal transport (OT). Specifically, a smoothed OT loss gives rise to an implicit transportation plan between the latent space and the data space. Based on this theoretical obse…
This paper introduces a neural sampler for scalable sampling from complex distributions.
problem Efficiently sampling from high-dimensional un-normalized distributions.
method Neural implicit sampler trained with KL and Fisher divergence methods.
result The neural sampler generates large batches of samples with low computational costs.
Unified theory for semi-implicit variational inference, bridging approximation and optimization.
problem Developing a statistical theory for semi-implicit variational inference.
method Unified theory combining approximation and optimization analyses.
result Unified theory characterizes SIVI's ability to recover target distributions and governs asymptotic behavior.
We propose an adversarial training procedure for learning a causal implicit generative model for a given causal graph. We show that adversarial training can be used to learn a generative model with true observational and interventional distributions if the generator architecture is consistent with the given causal grap…
DVIP improves on IP-based methods by using IPs as priors over latent functions.
problem Limited expressiveness of IP-based models, especially in function space.
method Proposes DVIP, a multi-layer generalization of IPs, and scalable variational inference.
result DVIP outperforms previous IP-based methods and deep GPs in regression and classification tasks.
Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the representation power of VAEs is limited due to two reasons: (1) the Gaussian assumption…
iGCL preserves graph semantics in latent space augmentations.
problem Manual tuning of augmentation ratios and unexpected graph changes.
method iGCL uses a Variational Graph Auto-Encoder to learn augmentations in the latent space, optimizing an upper bound for contrastive loss.
result iGCL achieves state-of-the-art performance on graph-level and node-level tasks.
Data-driven fault diagnostics of safety-critical systems often faces the challenge of a complete lack of labeled data associated with faulty system conditions (i.e., fault types) at training time. Since an unknown number and nature of fault types can arise during deployment, data-driven fault diagnostics in this scenar…
SGD outperforms GD in high dimensions via implicit conditioning, revealed by asymptotic analysis.
problem Understanding why SGD outperforms GD in high-dimensional convex problems.
method Asymptotic analysis of multi-pass SGD on high-dimensional convex quadratics, establishing an equivalence to HSGD.
result SGD's efficiency is explained by implicit conditioning, not regularization.
Implicit probabilistic models are a flexible class of models defined by a simulation process for data. They form the basis for theories which encompass our understanding of the physical world. Despite this fundamental nature, the use of implicit models remains limited due to challenges in specifying complex latent stru…
Paper proposes Adversarial CCA for multi-view alignment and generation.
problem Aligning multiple views in cross-view data analysis problems.
method Bayesian perspective, adversarial training for consistent latent encodings.
result ACCA model achieves superior performance in multi-view alignment and generation.
LLMs encode latent topic distributions, suggesting Bayesian inference.
problem Capturing topic structure from large language models.
method Connecting LLM optimization to implicit Bayesian inference and de Finetti's theorem.
result LLMs recover latent topic distributions, matching LDA-generated topics.
Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy. Recently, high-dimensional parametric models like neural networks have succeeded in building rich representations using either compressive, reconstructive or supervised criteria. However, the seman…
Study shows SGD's generalization is not explained by implicit bias.
problem Explaining the generalization ability of overparameterized learning algorithms.
method Revisited Stochastic Convex Optimization with SGD, demonstrating limitations of implicit bias.
result No distribution-independent or distribution-dependent implicit regularizer can explain SGD's generalization.
Recent progress in variational inference has paid much attention to the flexibility of variational posteriors. One promising direction is to use implicit distributions, i.e., distributions without tractable densities as the variational posterior. However, existing methods on implicit posteriors still face challenges of…
New dual formulation reduces generalization error for ERM-fDR.
problem Generalization error in constrained optimization problems.
method Introduces a dual formulation of ERM-fDR using Legendre-Fenchel transform and implicit function theorem.
result Explicit characterizations of generalization error for algorithms under mild conditions.
Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable neighboring node sharing for better generative modeling of graph dependency structure, together with …
Modality-agnostic compression improves across diverse data types.
problem Efficiently compressing data across multiple modalities.
method Functional view of data, Implicit Neural Representation (INR), modality-agnostic latent representations, variational compression.
result Improved performance compared to existing methods, especially for diverse modalities.
Generative model learns investment strategies without explicit utility specification.
problem Challenges in modeling complex, multi-objective fund optimization.
method Generative adversarial network (GAN) framework that learns latent strategy representations.
result Framework captures diverse investment styles and realizations of optimization parameters.
New findings suggest latent regularization is unnecessary for high-quality image generation.
problem Improving image generation quality without latent regularization.
method Investigated the effect of latent regularization on image generation using learned priors.
result In the case of a sufficiently expressive prior, latent regularization is not necessary and may harm image quality.
Deep generative neural networks have proven effective at both conditional and unconditional modeling of complex data distributions. Conditional generation enables interactive control, but creating new controls often requires expensive retraining. In this paper, we develop a method to condition generation without retrai…
ACE models allow flexible conditioning and prediction of latent variables.
problem Lack of flexibility in conditioning and prediction of latent variables in probabilistic models.
method Introduces Amortized Conditioning Engine (ACE) that explicitly represents latent variables and allows runtime conditioning and prediction.
result ACE models outperform existing methods in diverse tasks like image completion, classification, Bayesian optimization, and simulation-based inference.