ContrastiveVI+ models CRISPR screens with noisy guide efficiency.
problem Noisy guide efficiency in CRISPR screens.
method Generative modeling framework that disentangles perturbation-induced from shared variations.
result ContrastiveVI+ better recovers perturbation-induced variations and identifies cells without edits.
Variational inference has become one of the most widely used methods in latent variable modeling. In its basic form, variational inference employs a fully factorized variational distribution and minimizes its KL divergence to the posterior. As the minimization can only be carried out approximately, this approximation i…
The paper learns perturbation sets from data to improve robustness in machine learning.
problem Real-world perturbations are not well characterized in adversarial defenses.
method A conditional generator defines perturbation sets over latent space, with properties for quality measured.
result Learned perturbation sets generate diverse, meaningful perturbations and improve model robustness.
SAMS-VAE models cellular perturbations using sparse additive mechanisms.
problem Modeling effects of diverse interventions on cells.
method Sparse Additive Mechanism Shift Variational Autoencoder (SAMS-VAE).
result SAMS-VAE identifies disentangled, perturbation-specific latent subspaces.
Novel framework predicts cell responses to perturbations using GRNs.
problem Predicting cellular responses to perturbations for drug discovery and personalized therapeutics.
method Graph variational Bayesian causal inference framework with refined GRNs and robust estimator.
result Enhanced model performance and robust estimation of perturbation effects.
This paper analyzes β-Variational Classifiers for robustness and adversarial perturbation detection.
problem Limited robustness of deep neural networks in predictions.
method An analysis of β-Variational Classifiers, focusing on their robustness and adversarial perturbation detection. result Novel insights into the generative component of β-Variational Classifiers. SVAT reduces investment risks by making stock models sensitive to adversarial perturbations.
problem Risk control in stock recommendation models is insufficient, leading to high investment losses.
method SVAT combines adversarial learning and variational perturbation generation to enhance risk awareness.
result SVAT reduces investment risks by more than 30% compared to state-of-the-art baselines.
Eigenvalues of Steklov eigenproblems change predictably with boundary tweaks.
problem Understanding how Steklov eigenvalues respond to boundary changes.
method Analyzing smooth boundary perturbations of Steklov eigenvalues.
result Steklov eigenvalues are generically simple under such perturbations.
Paper proposes a method to improve deep learning models' robustness to real-world variations.
problem Deep learning models fail to generalize to small variations of the input.
method Adversarial mixing with disentangled representations to enforce robustness to real-world transformations.
result Improves generalization and reduces spurious correlations, as shown by experiments.
Investigates fluid flow perturbations using geometric theory.
problem Analyzing linear perturbations in non-equilibrium fluid flows.
method Uses second order variations of the action and Jacobi fields.
result Demonstrates numerical simulations of perturbation dynamics.
Study stability of trading strategy under market perturbations.
problem Dynamic stability of trading strategy under market changes.
method Established reverse conjugacy characterizations, proved continuity and convergence of indirect utility process.
result Continuity and first-order convergence of indirect utility process under market perturbations.
The paper modifies Vafa-Witten equations on 4-manifolds for better solution estimates.
problem Constructing a priori estimates for solutions of Vafa-Witten equations on 4-manifolds.
method Introducing perturbation terms to the Vafa-Witten equations and proving transversality.
result The singularities of solutions can be removed, and moduli spaces constructed.
The paper constructs new bimetric conformal invariants using metric perturbations.
problem Developing new conformal invariants in Riemannian geometry.
method Using linear metric perturbations and conformal invariants.
result New bimetric conformal invariants on 4D manifolds are derived.
New method enhances neural network robustness against adversarial attacks.
problem Enhancing neural network robustness against adversarial attacks.
method Variational framework with per-sample noise level selector.
result Enhanced empirical robustness and certified robustness.
Paper proves existence of solutions for a specific system.
problem Existence of solutions for a conformal Dirac-Einstein system.
method Perturbation methods to prove existence of solutions.
result Existence of solutions for the conformal Dirac-Einstein system.
New model accounts for scale variation and noise in pairwise comparisons.
problem Nonreciprocal pairwise comparisons in decision analysis.
method Additive model with structured matrix and random perturbation.
result Explicit estimators and probability assessments of admissible ranking regions.
DualVDT improves time-series forecasting with a novel dual reparametrized structure.
problem Time-series forecasting with improved performance and analytical rigor.
method Dual reparametrized variational mechanisms on VAE, latent score based generative model, reverse time stochastic differential equation, variational ancestral sampling, KL divergence reduction.
result Advanced performance in time-series forecasting with reduced KL divergence.
Black box variational inference (BBVI) with reparameterization gradients triggered the exploration of divergence measures other than the Kullback-Leibler (KL) divergence, such as alpha divergences. In this paper, we view BBVI with generalized divergences as a form of estimating the marginal likelihood via biased import…
We present another proof of the sharp inequality for Paneitz operator on the standard three sphere, in the spirit of subcritical approximation for the classical Yamabe problem. To solve the perturbed problem, we use a symmetrization process which only works for extremal functions. This gives a new example of symmetriza…
The paper connects neural network ensembles to Bayesian inference using variational methods.
problem Explaining the behavior of ensemble methods in neural networks.
method Deriving conditions for ensemble optimization to reduce divergence to the posterior distribution.
result Ensemble methods can be a valid alternative to approximate Bayesian inference.
Proposes a robust VIB approach using soft labels and mutual info estimation.
problem Improving robustness of VIB to adversarial perturbations.
method Refines categorical class information with soft labels from a reference network, relaxes Gaussian posterior assumption.
result Significantly outperforms benchmarked models on MNIST and CIFAR-10.
The use of Variational Autoencoders in different Machine Learning tasks has drastically increased in the last years. They have been developed as denoising, clustering and generative tools, highlighting a large potential in a wide range of fields. Their embeddings are able to extract relevant information from highly dim…
New framework robustly handles outliers in Wasserstein DRO for better decision-making.
problem Non-geometric perturbations like adversarial outliers distort Wasserstein distance.
method Proposes an outlier-robust WDRO framework using a robust Wasserstein ball.
result Derives minimax optimal excess risk bounds for robust WDRO.
DefenseVGAE defends graph neural networks against adversarial attacks.
problem Vulnerability of GNNs to adversarial structural perturbations.
method Variational Graph Autoencoder (VGAE) to reconstruct graph structure.
result DefenseVGAE reduces adversarial perturbations and boosts GCN performance.
In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize the bias and variance of the resulting Taylor-corrected estimators using the Lagrange error formula. Furthermore, we introduce a family of va…
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,…
Deep neural networks perform well on real world data but are prone to adversarial perturbations: small changes in the input easily lead to misclassification. In this work, we propose an attack methodology not only for cases where the perturbations are measured by ℓp norms, but in fact any adversarial dissimilarit…
Robust statistics traditionally focuses on outliers, or perturbations in total variation distance. However, a dataset could be corrupted in many other ways, such as systematic measurement errors and missing covariates. We generalize the robust statistics approach to consider perturbations under any Wasserstein distance…
The paper calculates variations of Einstein-Hilbert action on CR manifolds.
problem Variation of the Einstein-Hilbert action in pseudohermitian geometry.
method Computed first and second variations on CR manifolds, characterized critical points as pseudo-Einstein structures, and analyzed second variation on standard spheres.
result In three dimensions, the second variation of the Einstein-Hilbert action on CR structures differs from the Riemannian case due to embeddability.
The paper improves SVM and localized SVM stability under triple perturbations.
problem Stability of SVMs and localized SVMs under triple perturbations.
method Generalizes and improves existing results, considering simultaneous variations in probability measure, regularization parameter, and kernel.
result Improved stability of SVMs and localized SVMs under triple perturbations.
A new method for multi-agent planning on graphs outperforms existing approaches.
problem Planning coordination among multiple interacting agents on a graph.
method Variational perturbation theory applied to inference in large networks.
result Our method outperforms state-of-the-art methods in non-local cost function scenarios.
Study magnetic geodesics on Kähler potentials using variational methods.
problem Understanding magnetic geodesics on Kähler potentials.
method Variational method for a generalized Landau-Hall functional.
result Magnetic geodesic equation and its relation to a perturbed complex Monge-Ampère equation.
Study on combustion theory solutions, proving nondegeneracy and stability in limit.
problem One-phase singular perturbation problem in combustion theory.
method Introduce density condition to preserve nondegeneracy, classify stable solutions.
result Global stable solutions have flat level sets in dimensions ≤ 4.
A new method for privacy-preserving Bayesian learning in federated learning.
problem Privacy-preserving learning of models from distributed sensitive data.
method Differentially private partitioned variational inference (DPVI) for federated learning.
result First general framework for federated Bayesian learning with differential privacy.
For hyperbolic 3-manifolds, Ruelle zeta function vanishing order is 4 minus Betti number.
problem Analyzing the Ruelle zeta function at zero for perturbed hyperbolic 3-manifolds.
method Microlocal approach to dynamical zeta functions, first variation, new identity relating pushforwards of resonant and coresonant forms.
result The order of vanishing of the Ruelle zeta function at zero equals 4 minus Betti number for generic perturbations.
Certifiably robust VAEs are trained with bounds on input perturbations.
problem Ensuring VAEs are robust to adversarial attacks.
method Derive bounds on minimal perturbation size, control parameters, and train VAEs to meet criteria.
result Certifiably robust VAEs are more robust to attacks than standard VAEs.
Variational Optimization forms a differentiable upper bound on an objective. We show that approaches such as Natural Evolution Strategies and Gaussian Perturbation, are special cases of Variational Optimization in which the expectations are approximated by Gaussian sampling. These approaches are of particular interest …
We investigate the linear stability of Kähler-Ricci solitons for perturbations induced by varying the complex structure within a fixed Kähler class. We calculate stability for the known examples of Kähler-Ricci solitons.
Develops a new robustness criterion for VAEs and provides theoretical guarantees.
problem Lack of formalization for robustness in VAEs.
method Introduces r-robustness criterion and derives reconstruction margins. result Derives theoretical guarantees for VAE robustness.
In machine learning, the domain adaptation problem arrives when the test (target) and the train (source) data are generated from different distributions. A key applied issue is thus the design of algorithms able to generalize on a new distribution, for which we have no label information. We focus on learning classifica…
New optimal surfaces found in Heisenberg group defy Euclidean sphere optimality.
problem Optimizing mean curvature in Heisenberg group sub-Riemannian setting.
method Developed variational theory, established first and second variation formulas, introduced new critical surfaces.
result Identified and characterized a new family of rotationally invariant critical surfaces, the Pansu-Minkowski spheres.
It is shown in the paper "Variational Properties of the Gauss-Bonnet Curvatures" of M.L. Labbi, that metrics with constant 2k-Gauss-Bonnet curvature on a closed n-dimensional manifold, 1<2k<n, are critical points for a certain Hilbert type functional with respect to volume preserving conformal variations. This motivate…
We study the (massless) Dirac operator on a 3-sphere equipped with Riemannian metric. For the standard metric the spectrum is known. In particular, the eigenvalues closest to zero are the two double eigenvalues +3/2 and -3/2. Our aim is to analyse the behaviour of eigenvalues when the metric is perturbed in an arbitrar…
We present two deep generative models based on Variational Autoencoders to improve the accuracy of drug response prediction. Our models, Perturbation Variational Autoencoder and its semi-supervised extension, Drug Response Variational Autoencoder (Dr.VAE), learn latent representation of the underlying gene states befor…
Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed perturbation to input data. Although several defense methods have been proposed to address specific…
DANCE improves saliency maps by adding subtle input variations.
problem Poor performance of saliency methods in saturated gradients, adversarial perturbations, and inter-feature dependence.
method Two-step procedure: 1) Perturbation mechanism, 2) Aggregation of saliency maps.
result DANCE saliency method outperforms existing methods qualitatively and quantitatively.
The study bounds the stability of Gaussian mixtures under small perturbations.
problem Stability of Gaussian mixtures under small changes in distribution.
method Deriving an explicit bound on parameter stability of spherical Gaussian Mixture Models (sGMM) in a pre-defined model class.
result Upper bound on parameter distance of close sGMMs to the original sGMM, dependent only on the original model.
SIFG uses noisy particles to efficiently sample from complex distributions.
problem Efficient sampling from complex distributions using particle-based methods.
method SIFG introduces a semi-implicit functional gradient flow with Gaussian noise to improve sampling efficiency and accuracy.
result SIFG achieves strong theoretical convergence guarantees and efficient sampling.