Study enhances robustness of In-CVaR based regression models under perturbation and contamination.
problem Enhancing robustness of nonlinear regression models under perturbation and contamination.
method Introduces interval conditional value-at-risk (In-CVaR) and rigorously analyzes its robustness properties under both perturbation and contamination.
result The In-CVaR based estimator is qualitatively robust in terms of the Prokhorov metric if and only if the largest portion of losses is trimmed.
We regard pre-trained residual networks (ResNets) as nonlinear systems and use linearization, a common method used in the qualitative analysis of nonlinear systems, to understand the behavior of the networks under small perturbations of the input images. We work with ResNet-56 and ResNet-110 trained on the CIFAR-10 dat…
The perturbative approach to nonlinear Sigma models and the associated renormalization group flow are discussed within the framework of Euclidean algebraic quantum field theory and of the principle of general local covariance. In particular we show in an Euclidean setting how to define Wick ordered powers of the underl…
Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this paper, in an effort to scale these approaches to substantially larger models, w…
This paper constructs GCM hypersurfaces in Kerr spacetimes.
problem Extending the Kerr family stability proof to full stability.
method Concatenating a 1-parameter family of GCM spheres by solving an ODE system.
result Removes symmetry restrictions in GCM procedure.
Abstract: Nonlinear random walk with distributionally robust transition probabilities.
problem Modeling nonlinear random walks with robust transition probabilities.
method Scaling limit and nonlinear semigroup approach.
result Explicit computation of the generator and corresponding PDE.
In this work, we prove the existence of a family of solutions of the Allen-Cahn equation with nonlinear Neumann boundary condition under some constraints, whose nodal sets concentrate asymptotically to a given volume nondegenerate capillary hypersurface in a compact Riemannian manifold. Our construction is inspired by …
New geometric interpretation explains over-parameterized models and adversarial perturbations.
problem Geometric understanding of over-parameterized regression and adversarial perturbations.
method Alternative geometric interpretation of regression in feature space.
result Adversarial perturbations are a natural feature of biased models due to underlying geometry.
Continuous-time mean-variance portfolio selection model with nonlinear wealth equations and bankruptcy prohibition is investigated by the dual method. A necessary and sufficient condition which the optimal terminal wealth satisfies is obtained through a terminal perturbation technique. It is also shown that the optimal…
We deal with the interest rate model proposed by Schaefer and Schwartz, which models the long rate and the spread, defined as the difference between the short and the long rates. The approximate analytical formula for the bond prices suggested by the authors requires a computation of a certain constant, defined via a n…
Study on signal-plus-noise decomposition in nonlinear spiked random matrices.
problem Nonlinear spiked random matrix models with rank-one signal and noise.
method Signal-plus-noise decomposition and phase transition analysis.
result Identified precise phase transitions in signal components at critical thresholds.
The paper introduces a method to make neural networks more robust to adversarial attacks.
problem Vulnerability of deep neural networks to small, adversarially designed perturbations.
method A bottom-up strategy using a nonlinear front end that polarizes and quantizes data.
result The approach can completely eliminate adversarial perturbations on MNIST and Fashion MNIST datasets.
CG-EnKF and NS-EnKF outperform deep learning-based SF in data assimilation.
problem Data assimilation with non-linear perturbations.
method Two non-linear extensions of EnKF: CG-EnKF and NS-EnKF.
result CG-EnKF and NS-EnKF outperform SF in high-dimensional multiscale data assimilation.
This the first in a series of papers whose ultimate goal is to establish the full nonlinear stability of the Kerr family for ∣a∣≪m. The paper builds on the strategy laid out in \cite{KS} in the context of the nonlinear stability of Schwarzschild for axially symmetric polarized perturbations. In fact the central id…
Paper develops a new geometric framework for Kerr stability.
problem Uniform decay properties of Kerr solutions.
method Geometric framework for Teukolsky equation in nonlinear Kerr spacetime.
result First nonlinear version of Chandrasekhar transformation.
Improves generalization in learning problems with small parameter method.
problem Improving generalization in learning problems with high-dimensional nonlinear functions.
method Perturbation theory applied to a weakly-controlled gradient system.
result Approximate optimal solutions for improving generalization with small noise.
Study on future stability of FLRW spacetime solutions with decelerated expansion.
problem Stability of solutions to Einstein equations coupled with a nonlinear scalar field.
method Decomposition of metric and scalar field perturbations into spatial averages and oscillatory remainders.
result Future-stability of FLRW spacetime solutions for 1/3<p<1. New measure EC assesses node contributions in nonlinear, time-varying systems.
problem Existing node contribution measures assume linear, time-invariant dynamics, failing for complex, real-world systems.
method Defined 'emergent contribution (EC)' as a dynamical leverage measure from Jacobians of differentiable models.
result EC diverges from average controllability under persistent regime switching and sign reversal, identifying limits of local linearization.
The SPS method constructs confidence regions for true parameters with optimal sample complexity.
problem Constructing exact, non-asymptotic confidence regions for true system parameters.
method Sign-Perturbed Sums (SPS) method, generalized to various types of problems.
result High probability upper bounds for SPS confidence regions show optimal shrinkage rate.
The paper is devoted to the study of BRST charge in perturbed two dimensional conformal field theory. The main goal is to write the operator equation expressing the conservation law of BRST charge in perturbed theory in terms of purely algebraic operations on the corresponding operator algebra, which are defined via th…
New method proves instability of naked singularity and censors it.
problem Proving instability and censoring naked singularity.
method Einstein-scalar field system, hyperbolic short-pulse method, non-perturbative elliptic arguments.
result Tiny anisotropic perturbation leads to anisotropic apparent horizon censoring the naked singularity.
Framework predicts nonlinear system responses using GFDT and generative models.
problem Predicting higher-order moments of nonlinear stochastic systems to small perturbations.
method Combining GFDT with generative modeling to estimate score function directly from data.
result Accurately captures nonlinear and non-Gaussian features of system responses.
The paper proves smoothness of event horizons in Kerr spacetime perturbations.
problem Smoothness of event horizons in Kerr spacetime perturbations.
method Proof of smoothness using stability of slowly rotating Kerr spacetimes.
result Smooth null hypersurfaces of event horizons are proven for Kerr spacetime perturbations.
The paper examines the stability of Minkowski inequality for nearly spherical domains.
problem Stability of Minkowski inequality for nearly spherical domains.
method Analyzes stability inequalities for C1 perturbations of a ball and axially symmetric perturbations. result Established stability inequalities for curvature integrals of nearly spherical domains.
This work explains RL policies using causal models, revealing important patterns and failures.
problem Understanding why RL policies succeed or fail in complex, high-dimensional systems.
method Developed a nonlinear Causal Model Reduction framework to learn simplified causal models from RL policy actions and rewards.
result The approach can uncover important behavioral patterns and failure modes in trained RL policies.
New bounds for nearly-linear networks without training.
problem Generalization of neural networks close to linearity.
method Perturbation of linear networks to derive bounds.
result First non-vacuous bounds for neural nets.
We describe how to use the perturbation theory of Caffarelli to prove Evans-Krylov type C2,α estimates for solutions of nonlinear elliptic equations in complex geometry, assuming a bound on the Laplacian of the solution. Our results can be used to replace the various Evans-Krylov type arguments in the complex geom…
Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence. Ear…
New framework for gravitational perturbations of Kerr spacetimes, focusing on stability.
problem Stability of Kerr spacetimes to gravitational perturbations.
method New geometric framework with tailored null frames and gauge, reformulating Einstein equations.
result Derivation of linearised vacuum Einstein equations in the new framework.
This paper improves flow models to better handle perturbations in real-world data.
problem Flow models amplify initial errors in perturbed data, leading to poor generalization.
method Utilizes Bernstein-type polynomials to construct Normalizing Flows (NF) for higher robustness.
result Proposed NF framework provides theoretical upper bounds and practical advantages.
New method estimates convergence bounds for nonlinear Markov chains.
problem Difficulty in describing properties of nonlinear Markov chains.
method Coupling Markov chains to reconstitute distribution relationships and estimate convergence bounds.
result Estimation of convergence bounds is more precise than existing results.
We show that the maximal future development of asymptotically flat spherically symmetric black hole initial data for a self-gravitating nonlinear scalar field, also called a Higgs field, contains a connected, achronal marginally trapped tube which is asymptotic to the event horizon of the black hole, provided the initi…
Study of Dirac equation with non-local nonlinearity on spheres.
problem Conformally invariant Dirac equation with non-local nonlinearity.
method Investigation of compactness, bubbling, and energy quantization of energy functional; characterization of ground state solutions; proof of Aubin-type inequality and Brezis-Nirenberg type result.
result Existence of solutions to the conformal Einstein-Dirac problem in dimension 4.
We study the small perturbations of the 1+3-dimensional Milne model for the Einstein-Klein-Gordon (EKG) system. We prove the nonlinear future stability, and show that the perturbed spacetimes are future causally geodesically complete. For the proof, we work within the constant mean curvature (CMC) gauge and focus on …
This article is the second in a series of two whose aim is to extend a recent result of Guillarmou-Lefeuvre [arXiv:1806.04218] on the local rigidity of the marked length spectrum from the case of compact negatively-curved Riemannian manifolds to the case of manifolds with hyperbolic cusps. We deal with the nonlinear ve…
Study on robustness of unsupervised representation learning in slightly misspecified settings.
problem Identify nonlinear representation learning in slightly misspecified settings.
method Formalize and investigate Independent Component Analysis (ICA) with observations generated by a mixing function close to a local isometry.
result Approximate identifiability of nonlinear ICA with almost isometric mixing functions.
Study optimal investment and consumption strategies with various transaction costs.
problem Investment and consumption decisions under varying transaction costs.
method Dynamic programming and singular perturbation expansion for small cost-to-wealth ratio.
result Derive leading-order asymptotic formulas for no-trade regions and trading boundaries.
Modified perturbation method removes non-smoothness in solving Black-Scholes equations.
problem Non-smoothness in solving Black-Scholes equations.
method Variable transformations and homotopy perturbation method.
result Excellent agreement with exact solutions for Black-Scholes and multi-asset options.
We revisit the subject of perturbatively quantizing the nonlinear sigma model in two dimensions from a rigorous, mathematical point of view. Our main contribution is to make precise the cohomological problem of eliminating potential anomalies that may arise when trying to preserve symmetries under quantization. The sym…
Bayesian inference with deep, weakly nonlinear networks is solved rigorously.
problem Bayesian inference with neural networks of specific structure.
method Perturbative analysis of fully connected neural networks with a shaped nonlinearity.
result Neural network Bayesian inference can be equivalent to kernel methods under certain conditions.
This is a follow-up of our paper \cite{KS-Kerr1} on the construction of general covariant modulated (GCM) spheres in perturbations of Kerr, which we expect to play a central role in establishing their nonlinear stability. We reformulate the main results of that paper using a canonical definition of ℓ=1 modes on a …
Introduces TPV to analyze model robustness without labels.
problem Analyzing post-training robustness of machine learning models.
method Parameter perturbations and test prediction variance (TPV) as a unifying framework.
result TPV connects various perturbations under a single lens, providing insights into model stability.
New framework allows selective removal of stale data in option calibration.
problem Inability to remove old data from calibrated option pricing models without full retraining.
method Introduces operator-theoretic Gauss-Newton framework for selective forgetting.
result Provides stability guarantees and perturbation bounds for selective data removal.
Unified framework for ensemble sampling in nonlinear contextual bandits with provable regret bounds.
problem Efficient exploration in nonlinear contextual bandits with unknown feature dimensions.
method Developed GLM-ES and Neural-ES for generalized linear and neural contextual bandits, respectively, using maximum likelihood estimation on randomly perturbed data.
result Unified high-probability frequentist regret bounds for GLM-ES and Neural-ES, matching state-of-the-art results.
Stability of Schwarzschild singularity in near-Schwarzschild black holes under perturbations.
problem Stability of the Schwarzschild singularity in near-Schwarzschild black holes.
method Energy methods and new approach to Einstein vacuum equations in axial symmetry.
result The solution displays asymptocially-velocity-term-dominated dynamics and approaches a different Kasner solution at each point of the singularity.
Solves a complex mathematical problem on curved surfaces.
problem Boundary Yamabe problem with constant scalar and mean curvature.
method Iterative schemes and perturbation methods to solve nonlinear elliptic PDEs.
result Existence of a real, positive, smooth solution in compact manifolds.
S. Donaldson introduced a metric on the space of volume forms, with fixed total volume on any compact Riemmanian manifold. With this metric, the space of volume forms formally has non-positive curvature. The geodesic equation is a fully nonlinear degenerate elliptic equation. We solve the geodesic equation and its pert…
Deep neural networks (DNNs) are vulnerable to subtle adversarial perturbations applied to the input. These adversarial perturbations, though imperceptible, can easily mislead the DNN. In this work, we take a control theoretic approach to the problem of robustness in DNNs. We treat each individual layer of the DNN as a …