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.
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.
Complex computer simulators are increasingly used across fields of science as generative models tying parameters of an underlying theory to experimental observations. Inference in this setup is often difficult, as simulators rarely admit a tractable density or likelihood function. We introduce Adversarial Variational O…
Generative adversarial networks (GANs) have given us a great tool to fit implicit generative models to data. Implicit distributions are ones we can sample from easily, and take derivatives of samples with respect to model parameters. These models are highly expressive and we argue they can prove just as useful for vari…
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.
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.
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.
We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities from one domain as entities from the other domain. First, we introduce implicit latent variable models,…
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.
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.
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.
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.
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.
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…
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.
Bayesian inference on structured models typically relies on the ability to infer posterior distributions of underlying hidden variables. However, inference in implicit models or complex posterior distributions is hard. A popular tool for learning implicit models are generative adversarial networks (GANs) which learn pa…
Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the ava…
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.
Researchers disrupt Gaussian model inference to test adversarial attacks.
problem Disrupting conditional inference in multivariate Gaussian models under adversarial conditions.
method Considered white- and grey-box settings with complete and incomplete knowledge of the Gaussian distribution, respectively. Reduced to quadratic and stochastic quadratic programs. Derived structural properties for solution methods.
result Demonstrated the impact and efficacy of attacks in various applications, including real estate evaluation, interest rate estimation, and signals processing.
We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as t…
Study shows prior Lipschitz continuity can improve adversarial robustness of Bayesian Neural Networks.
problem Improving adversarial robustness of Bayesian Neural Networks.
method Analysis of i.i.d., zero-mean Gaussian priors and posteriors approximated via mean-field variational inference.
result Adversarial robustness is sensitive to the prior variance.
Unified framework for training generator, energy model, and inference model.
problem Training of generator, energy model, and inference model in a unified probabilistic formulation.
method Divergence Triangle framework integrating variational learning, adversarial learning, wake-sleep algorithm, and contrastive divergence.
result Unified training of generator, energy model, and inference model without costly Markov chain Monte Carlo methods.
This work investigates training infinite mixtures with maximum likelihood for improved uncertainty quantification.
problem Improving uncertainty quantification in neural networks.
method Investigates training infinite mixtures with maximum likelihood instead of variational inference.
result The proposed method leads to stochastic networks with increased predictive variance, improved robustness, and higher entropy on out-of-distribution data.