This paper connects GANs to variational inference, providing new algorithms.
problem Understanding and applying variational inference with implicit distributions.
method Unified review of existing algorithms, introducing prior-contrastive and joint-contrastive methods.
result Unified understanding and practical inference algorithms for variational autoencoders and adversarially learned inference.
Improved neural spike inference from calcium imaging data.
problem Neural spike inference from calcium imaging data.
method Importance weighted adversarial variational autoencoders (IWAE) with adversarial training.
result Adversarial IWAE methods outperform VAEs in inferring neural spikes.
AVO optimizes simulators without likelihoods, combining GANs and variational methods.
problem Inference in non-differentiable simulators is difficult.
method Adversarial Variational Optimization (AVO) using GANs and variational techniques.
result AVO minimizes JS divergence between synthetic and empirical data distributions.
VERA uses variational inference to jailbreak LLMs without manual optimization.
problem Lack of principled objective for gradient-based optimization in jailbreaking LLMs.
method VERA casts black-box jailbreak prompting as a variational inference problem, training a small attacker LLM to approximate the target LLM's posterior over adversarial prompts.
result VERA achieves strong performance across various target LLMs, demonstrating the value of probabilistic inference for adversarial prompt generation.
PuVAE purifies adversarial examples by projecting them onto class manifolds.
problem Vulnerability of deep neural networks to adversarial attacks.
method PuVAE purifies adversarial examples by projecting them onto the manifold of each class.
result PuVAE purifies adversarial examples effectively without prior knowledge of the attack.
This paper uses MH algorithm to improve variational inference and GANs.
problem Improving sampling efficiency in Bayesian inference and GANs.
method Proposes learning an independent sampler to maximize MH acceptance rate, related to variational inference. Deduces GANs from MH perspective.
result Improves variational inference and GANs performance on real-world datasets.
This paper shows equivalence between SVGD and BBVI using kernel gradient flows.
problem Bayesian inference methods and their equivalence.
method Formalizes equivalence between SVGD and BBVI using kernel gradient flows.
result BBVI corresponds precisely to SVGD when using the neural tangent kernel.
Framework improves GCNs for graphless and adversarial settings.
problem Improving GCNs without graph data and making them robust to adversarial attacks.
method Joint probabilistic model with variational inference and Concrete distributions.
result Framework outperforms state-of-the-art algorithms on semi-supervised classification.
This paper integrates auto-encoders and GANs using variational inference.
problem Preventing mode collapse in generative models.
method Develops a principle to combine variational auto-encoders and GANs, using synthetic likelihoods and implicit posterior distributions.
result Unified objective for optimizing the fusion of variational auto-encoders and GANs.
AdVIL improves inference and learning for MRFs with minimal assumptions.
problem Improving inference and learning for Markov random fields (MRFs) with minimal assumptions.
method AdVIL uses adversarial variational inference and learning to approximate latent variables and estimate partition functions.
result AdVIL provides a tighter estimate of the log partition function and better empirical results.
Bayesian Tweedie mixed models are improved with adversarial variational inference.
problem Intractable likelihood function and hierarchical structure of mixed effects.
method Adversarial variational inference with reparameterization and flexible hyper prior.
result Proposed method reduces estimation bias and achieves state-of-the-art predictive performance.
Infer-AVAE infers missing user attributes from incomplete data using a novel adversarial approach.
problem Incomplete user attributes in social networks.
method Infer-AVAE combines MLP and GNNs with adversarial training to infer missing attributes.
result Infer-AVAE outperforms baselines by 7.0% in accuracy on real-world datasets.
CYCLEGAN models are shown to be a special case of approximate Bayesian inference.
problem Learning correspondences between domains without paired data.
method Formalized as Bayesian inference in an LVM, developed a VI algorithm based on KL divergence minimization.
result CYCLEGAN models can be derived within the proposed VI framework.
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.
A new approach to learning in brain-like networks using adversarial algorithms.
problem Complex inter-dependencies in brain-like networks not compatible with conditional independence assumptions.
method Adversarial algorithm for learning models of perceptual processing.
result The approach can mimic known neural phenomena and yields testable hypotheses.
DDVI uses diffusion models for variational inference, improving latent variable model performance.
problem Improving variational inference in latent variable models.
method Introduces diffusion-based variational posteriors trained with a regularized ELBO.
result Outperforms alternative variational posteriors on various benchmarks and a biology task.
Generative Bayesian Inference uses GANs for approximate posterior sampling.
problem Bayesian inference without explicit likelihoods.
method Develops Bayesian GAN (B-GAN) for posterior simulation.
result B-GAN achieves highly competitive performance in posterior sampling.
AVDA transfers knowledge from source to target domains using embeddings.
problem Transferring knowledge from a source domain to a target domain with limited labeled data.
method Adversarial Variational Domain Adaptation (AVDA) with deep embeddings and Gaussian Mixture Model.
result AVDA outperforms previous methods in semi-supervised few-shot domain adaptation.
Paper presents IPVI for unbiased DGP inference with efficiency.
problem Intractable exact inference in deep Gaussian processes.
method Implicit posterior variational inference framework.
result IPVI achieves unbiased posterior belief with efficiency.
Develops robust ML systems for predictive uncertainties and adversarial examples.
problem Uncertainties and vulnerabilities in ML predictions and adversarial examples.
method Bayesian structural time series models, SG-MCMC, SVGD, Markov chain samplers, reinforcement learning.
result Improved robustness and efficiency in Bayesian inference and adversarial machine learning.
Improved IFA with Generative Adversarial Networks for high-dimensional latent variables.
problem Limited expressiveness of traditional VAEs in high-dimensional latent variable modeling.
method Introducing Adversarial Variational Bayes (AVB) and Importance-weighted Adversarial Variational Bayes (IWAVB) algorithms.
result IWAVB demonstrated superior expressiveness and higher likelihood compared to IWAE.
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.
Bayesian hypernetworks learn to transform noise to parameter distributions for neural networks.
problem Approximate Bayesian inference in neural networks with complex parameter correlations.
method Train a Bayesian hypernetwork to transform a simple noise distribution to a complex posterior distribution over neural network parameters using variational inference.
result Bayesian hypernetworks can represent multimodal approximate posteriors with correlations between parameters and enable efficient sampling.
The paper proves that certain variational inference methods preserve generalization guarantees in online learning.
problem Generalization guarantees of Bayesian inference with model mismatch and adversaries.
method Derive generalization bounds for several online, tempered variational inference algorithms.
result Variational inference methods can preserve generalization properties of Bayesian inference.
New deep learning model robust to adversarial attacks using stochastic LWTA units.
problem Adversarial robustness in deep learning networks.
method Introduces deep networks with stochastic LWTA activations, combining them with Bayesian non-parametric tools.
result Achieves high robustness to adversarial perturbations, outperforming state-of-the-art methods.
Paper defends sensitive attributes in GNNs from inference attacks.
problem Protecting sensitive attributes in GNNs from inference attacks.
method Proposes adversarial training with TV and Wasserstein distance to locally filter sensitive attributes.
result Framework creates strong defense against inference attacks with minimal performance loss.
Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.
problem Adversarial robustness of neural networks.
method Replaced ReLU with stochastic LWTA activations, trained with Variational Bayesian and PGD.
result Stochastic LWTA networks achieve state-of-the-art robustness against adversarial attacks.
GATSBI uses GANs for SBI, improving posterior estimation in high dimensions.
problem Statistical inference on stochastic models without likelihoods.
method Adversarial approach to variational objective, amortized inference, implicit priors.
result GATSBI returns well-calibrated posterior estimates in high dimensions.
Bayesian CNN with Variational Inference improves uncertainty handling in neural networks.
problem Uncertainty in neural networks, especially in regions with little data.
method Bayesian Convolutional Neural Network (BayesCNN) using Variational Inference.
result BayesCNN achieves equivalent performance to frequentist inference and incorporates uncertainty measurements.
Half-AVAE enhances VAE for underdetermined ICA with adversarial training.
problem Challenges in ICA under underdetermined conditions.
method Encoder-free VAE with adversarial networks and EE terms.
result Half-AVAE outperforms baseline models in underdetermined ICA.
Bayesian deep learning uses function-space priors to improve model uncertainty and robustness.
problem Bayesian deep learning struggles with model-specific weight-space priors that are hard to interpret and specify.
method Apply a Dirichlet prior in predictive space and perform approximate function-space variational inference.
result The approach improves uncertainty quantification, scalability, and adversarial robustness in large-scale image classification.
Unified view of GANs, VI, RL through PFD.
problem Unified understanding of GANs, VI, RL.
method Probability Functional Descent (PFD) algorithm.
result PFD unifies GANs, VI, RL.
Adversarial GANs improve Bayesian inference on complex models.
problem Hard inference in implicit models and complex posterior distributions.
method Local learning rules based on message passing, minimizing global divergence criterion.
result Unified inference and learning framework for adversarial learning.
Develops scalable inference for complex implicit models.
problem Challenges in specifying complex latent structure and performing inferences in implicit models with large data sets.
method Introduces hierarchical implicit models and develops likelihood-free variational inference (LFVI). LFVI uses an implicit variational family.
result Demonstrates diverse applications of LFVI, including predator-prey simulations, generative adversarial networks, and text generation.
Improved dropout inference for Bayesian neural networks using alpha-divergences.
problem Uncertainty underestimation in dropout variational inference.
method Proposed a re-parametrisation of alpha-divergence objectives for dropout networks.
result Improved uncertainty estimates and accuracy compared to VI in dropout networks.
VERA-V uses variational inference to discover vulnerabilities in multimodal vision-language models.
problem Existing methods for jailbreaking vision-language models are brittle, limited, and focus on single attacks.
method VERA-V recasts jailbreak discovery as learning a joint posterior distribution over text-image prompts, using variational inference and three complementary strategies.
result VERA-V consistently outperforms state-of-the-art baselines, achieving up to 53.75% higher attack success rate.
Paper proposes LSVGD to stabilize GAN training via Langevin Stein Variational Gradient Descent.
problem Mode collapse and performance deterioration in GAN training.
method Langevin Stein Variational Gradient Descent (LSVGD) incorporating noise to stabilize training.
result LSVGD improves performance and stability of various GAN models.
VI approximates complex densities faster than classical methods.
problem Approximating complex probability densities.
method Optimization of a family of probability density functions using KL divergence.
result VI converges faster than Markov Chain Monte Carlo.
MAVENs combine GAN and VAE for better image generation and classification.
problem Improve image generation and classification using unsupervised learning.
method Introduce MAVENs, an ensemble of discriminators in a VAE-GAN network.
result Demonstrated competitive performance in image generation and classification tasks.
A method for training neural networks to sample from target distributions.
problem Training stochastic neural networks to draw samples from complex target distributions.
method Iteratively adjusting neural network parameters using a Stein variational gradient to minimize KL divergence.
result Our method trains neural samplers to approximate likelihood functions effectively, producing realistic images.
Unified framework analyzes privacy risks from gradients in distributed learning.
problem Analyzing inference privacy risks from gradients in machine learning.
method Unified game-based framework for various attacks, including attribute, property, distributional, and user disclosures.
result Demonstrates inefficacy of data aggregation for privacy against inference attacks.
Paper proposes a method to detect out-of-distribution examples using variational inference.
problem Uncertainty in deep neural networks for unseen examples.
method Variational Dirichlet framework to approximate higher-order distribution and use entropy as uncertainty measure.
result Demonstrated to consistently outperform competing algorithms on various datasets.
Edward is a flexible probabilistic programming language that integrates with TensorFlow.
problem Probabilistic programming challenges in flexibility and efficiency.
method Compositional representations of random variables and inference, flexible inference methods, integration with TensorFlow.
result Edward achieves significant speedups in probabilistic modeling and inference.
Proposes adversarial learning for counterfactual fairness in machine learning.
problem Ensuring fairness at the individual level by simulating counterfactual samples.
method Adversarial neural learning approach to infer counterfactual samples.
result Significant improvements in counterfactual fairness for both discrete and continuous settings.
Analyzes how restricted f-GANs differ from classical inference methods.
problem Understanding the inductive bias of generative adversarial networks.
method Theoretical characterization of restricted f-GANs, focusing on linear KL-GANs.
result The optimal generator distribution is a combination of maximum likelihood and method of moments solutions.
A method for estimating signal distributions from inverse problems using normalizing flows.
problem Estimating the distribution of the underlying signal from observations in inverse problems.
method A framework for approximate inference on a pre-trained unconditional flow model, using a composition of two flow models for stable variational inference.
result Our method produces high-quality samples with uncertainty quantification and can be amortized for zero-shot inference.
The study sets lower bounds on MMSE for inferring sensitive features from noisy data.
problem Estimating sensitive features from noisy observations of correlated features.
method Adversarial evaluation framework based on MMSE estimation with theoretical lower bounds.
result Derives closed-form bounds for linear models, showing optimality in noise variance.
A model disentangles features to detect adversarial inputs.
problem Detecting and defending against adversarial attacks on neural networks.
method Proposes a minimax game formulation using variational autoencoders to separate robust and vulnerable features.
result Adversarial inputs cannot bypass the detector without semantic change, indicating successful detection.