Novel geometry-informed irreversible perturbation accelerates Langevin dynamics convergence.
problem Accelerating convergence of Langevin dynamics for Bayesian computation.
method Geometry-informed irreversible perturbation of Riemannian manifold Langevin dynamics.
result Improves estimation performance over irreversible perturbations that ignore geometry.
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.
This work proves Kerr black holes are dynamically stable under certain perturbations.
problem Dynamical stability of Kerr black holes under axially symmetric perturbations.
method Dimensional reduction to 2+1 Einstein-wave map system, construction of positive-definite energy functional, proving boundary terms vanish.
result Strictly conserved positive energy for axially symmetric linear perturbations of Kerr black holes.
Adversarial training adds dynamic perturbations to neural networks for robustness.
problem Accuracy trade-off and lack of diversity in adversarial examples.
method Dynamic adversarial perturbations in the parameter space of neural networks, updating perturbation biases during training.
result Adversarial training with negligible cost and reduced accuracy trade-off.
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.
New methods use transport maps to improve Langevin dynamics for sampling.
problem Sampling high-dimensional, non-Gaussian distributions efficiently.
method Apply transport maps to accelerate Langevin dynamics convergence.
result Discretized processes converge to target distribution with non-asymptotic bounds.
Efficient algorithm controls unknown systems with adversarial perturbations.
problem Controlling unknown linear systems with adversarial perturbations and convex losses.
method Measures regret against an optimal linear policy, provides efficient algorithm with sublinear regret bound.
result First efficient algorithm with sublinear regret bound of T^{2/3}.
Study perturbs mean curvature flow near non-spherical shrinkers.
problem Understanding the dynamics near non-spherical shrinkers under mean curvature flow.
method Invariant manifold theory from hyperbolic dynamics.
result Generic perturbation makes flow leave a neighborhood of non-spherical shrinkers.
Proposes a method to prove closing of periodic orbits in dynamical systems.
problem Proving generic dynamical systems have finite periodic orbits.
method Perturbation method for Cr closing of periodic orbits. result Validates the conjecture for generic dynamical systems.
Study of mean curvature flows with conical singularities using mathematical techniques.
problem Understanding the dynamics of mean curvature flows near conical singularities.
method Feynman-Kac formula and invariant cone method for noncompact settings.
result Generic initial perturbations avoid conical singularities in mean curvature flows.
Paper introduces metrics for evaluating multi-agent policies using best response dynamics.
problem Evaluation and ranking of multi-agent policies in reinforcement learning.
method Adopting strict best response dynamics (SBRD) to model selfish behaviors, proposing perturbed SBRD for dynamic and non-stationary settings.
result Proposed perturbed SBRD can observe policies with maximum metrics and differ from optimal by any given tolerance.
Researchers found a way to measure energy in black hole perturbations.
problem Lack of positive-definite and conserved energy in black hole stability.
method Dimensional reduction and construction of a positive-definite energy functional.
result Conserved Hamiltonian energy for axially symmetric perturbations of Kerr black holes.
The paper tackles adversarial attacks on recurrent neural networks.
problem Adversarial attacks on recurrent neural networks are easy and lack theoretical guarantees.
method Inspired by dynamical systems theory, the paper dynamically computes adversarial perturbations for each timestep of the input sequence.
result The paper provides theoretical guarantees on the existence of adversarial examples and robustness margins.
LoRA fine-tuning causes forgetting, studied via particle system dynamics.
problem Catastrophic forgetting in LoRA fine-tuning.
method Mean-field self-attention model, partial differential equations, dynamical systems.
result Characterization of phase transitions in forgetting behavior.
LoRA fine-tuning explained with gradient dynamics for low-rank perturbations.
problem Understanding why gradient descent converges to useful low-rank perturbations in LoRA fine-tuning.
method Generalized student-teacher setting with i.i.d. samples and online gradient descent.
result Gradient descent converges to the teacher model in dkO(1) iterations under certain conditions. Herding defines a deterministic dynamical system at the edge of chaos. It generates a sequence of model states and parameters by alternating parameter perturbations with state maximizations, where the sequence of states can be interpreted as "samples" from an associated MRF model. Herding differs from maximum likelihoo…
Graph neural networks detect structural perturbations from time series data.
problem Detecting structural causes of disturbances in complex systems.
method Graph neural network approach to infer structural perturbations from functional time series.
result Data-driven approach outperforms typical reconstruction methods and meets Bayesian inference accuracy.
The paper examines how gradient descent stabilizes low-rank matrix factorization in noisy conditions.
problem Stability of low-rank implicit regularization in perturbed deep matrix factorization.
method Derives spectral conditions for gradient descent to exhibit a low-rank phase in noiseless settings and analyzes perturbed dynamics.
result Gradient descent converges to a low-rank solution under perturbation, with explicit dependence on perturbation size.
Gradient descent with chaotic perturbations improves generalization.
problem Improving generalization of gradient descent.
method Introducing chaotic perturbations to gradient descent to achieve improved generalization.
result Gradient descent with chaotic perturbations converges to a heavy-tailed SDE, leading to improved generalization.
We prove a dynamical wave trace formula for asymptotically hyperbolic (n+1) dimensional manifolds with negative (but not necessarily constant) sectional curvatures which equates the renormalized wave trace to the lengths of closed geodesics. A corollary of this dynamical trace formula is a dynamical resonance-wave trac…
Study of marginally trapped surfaces in a perturbed Schwarzschild spacetime.
problem Understanding marginally trapped surfaces in perturbed Schwarzschild spacetime.
method Developed a method to study spacelike surfaces in a double null coordinate system.
result For every incoming null hypersurface nearly spherically symmetric, there exists a unique embedded marginally trapped surface.
This paper tackles robustness of ensemble stumps and trees under general ℓ_p norm perturbations.
problem The vulnerability of ensemble stumps and trees to small input perturbations under the ℓ_∞ norm.
method Developed dynamic programming algorithms for robustness verification and certified defense under general ℓ_p norm perturbations.
result First certified defense method for ensemble stumps and trees under ℓ_p norm perturbations.
Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (\eg articles with citation link tend to be in the same class), graph neural networks could be more sensiti…
The celebrated KAM Theory says that if one makes a small perturbation of a non-degenerate completely integrable system, we still see a huge measure of invariant tori with quasi-periodic dynamics in the perturbed system. These invariant tori are known as KAM tori. What happens outside KAM tori draws a lot of attention. …
As most natural resources, fisheries are affected by random disturbances. The evolution of such resources may be modelled by a succession of deterministic process and random perturbations on biomass and/or growth rate at random times. We analyze the impact of the characteristics of the perturbations on the management o…
Analyzes learning dynamics of RNNs under locality constraints.
problem Understanding learning dynamics in RNNs with locality constraints.
method Dynamical systems theory applied to data-aligned linear RNNs.
result RFLO solutions are restricted to low-rank perturbations of initial parameters.
New method μP2 improves neural network training by scaling perturbations layerwise.
problem Improving neural network performance as models scale up.
method Layerwise perturbation scaling in the infinite-width limit of neural networks.
result Layerwise perturbation scaling ensures all layers are effectively perturbed in the limit.
Introduces RPU to explain randomization preference in dynamic settings.
problem Explains preference for randomization in dynamic investment problems.
method Introduces recursive perturbed utility (RPU) to incorporate randomization preference.
result Proves RPU-optimal portfolio policy is Gaussian and can be expressed in closed form.
New approach reduces unconstrained linear bandits to simpler optimization problems.
problem Unconstrained linear bandits problem.
method Perturbation-based approach combined with comparator-adaptive OLO algorithms.
result First high-probability guarantees for both static and dynamic regret in unconstrained linear bandits.
Two randomized algorithms improve performance in non-stationary linear bandits.
problem Conservatism in optimistic algorithms for non-stationary linear bandits.
method Two perturbation approaches: randomization and random perturbations.
result D-RandLinUCB and D-LinTS achieve optimal dynamic regret and are oracle-efficient.
New gauge fields modify Fokker-Planck dynamics without changing the stationary state.
problem Understanding and modifying nonreversible dynamics in Fokker-Planck models.
method Formulate nonreversible perturbations as gauge fields, mapping to supersymmetric Hamiltonians, and learning finite forces.
result Learned finite forces can recover the optimal Lyapunov-equation solution in nonconvex landscapes.
Proposes a probabilistic digital twin for dynamical systems using sparse Bayesian learning.
problem Creating and updating accurate digital twins for complex dynamical systems.
method Sparse Bayesian machine learning, two approaches: input-output and output-only.
result Identifies correct perturbation terms and associated parameters in dynamical systems.
Paper presents a privacy-preserving method for dynamic assortment selection.
problem Personalized assortment recommendations with data privacy concerns.
method Perturbed upper confidence bound method integrating calibrated noise.
result Policy satisfies Joint Differential Privacy (JDP) with near-optimal regret bound.
TULiP estimates uncertainty for deep learning models safely.
problem Reliable uncertainty estimation for deep learning models in the open world.
method TULiP considers a hypothetical perturbation, bounds its effect, and computes uncertainty from sampled predictions.
result TULiP achieves state-of-the-art performance in OOD detection benchmarks.
New method learns cell trajectories and network interactions from single-cell data.
problem Network inference in systems biology from steady-state data.
method Min-entropy estimation for stochastic dynamics, leveraging both temporal and perturbational data.
result Jointly learns cellular trajectories and network interactions.
WassersteinGrad improves weather forecasting explanations by addressing geometric misalignment issues.
problem Improving explainability of autoregressive neural predictions on dynamic physical fields.
method WassersteinGrad, a geometric consensus method for averaged perturbed attribution maps.
result WassersteinGrad provides more accurate explanations for weather forecasting models.
Noncompact Ricci-flat solutions have infinite unstable dimensions.
problem Understanding unstable dimensions of noncompact Ricci-flat solutions.
method Derived sufficient conditions for infinite-dimensional unstable manifolds.
result Noncompact Ricci-flat solutions have uncountably many unstable perturbations.
A new method for generating SPX and VIX risk scenarios using perturbed optimal transport.
problem Generating accurate risk estimates for SPX and VIX without full recalibration.
method A joint optimal transport calibration with perturbation methodology for sensitivities, combined with Skew Stickiness Ratio dynamics.
result The proposed method produces accurate risk estimates relative to full recalibration and is computationally faster.
Study of deep neural networks using finite-time Lyapunov exponents.
problem Understanding the geometric structures in input space formed by deep neural networks.
method Analogy with dynamical systems, computing finite-time Lyapunov exponents.
result Ridges of large positive exponents divide input space into regions associated with different classes.
Proposes a new training algorithm for zero-sum games to avoid convergence issues.
problem Gradient-based training leads to weak convergence and cyclic dynamics in zero-sum architectures.
method Follow the perturbed leader algorithm with neural mediating agent.
result Guarantees convergence to mixed Nash equilibrium without cyclic behaviors.
We derive a system of equations governing the coupled gravitational and electromagnetic perturbations of Reissner-Nordström spacetime. The equations are derived in the context of global non-linear stability of Reissner-Nordström under axially symmetric polarized perturbations, as a generalization of the recent work on …
Node-perturbation learning is a type of statistical gradient descent algorithm that can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. It estimates the gradient of an objective function by using the change in the object function in response to the per…
New controller reduces regret in non-stochastic control with adversarial perturbations.
problem Non-stochastic control with adversarial perturbations and partially observed states.
method Denoised observations and online gradient descent.
result Sublinear regret bounds, optimal for known and unknown systems.
Machine learning recently has been used to identify the governing equations for dynamics in physical systems. The promising results from applications on systems such as fluid dynamics and chemical kinetics inspire further investigation of these methods on complex engineered systems. Dynamics of these systems play a cru…
We consider the structured-output prediction problem through probabilistic approaches and generalize the "perturb-and-MAP" framework to more challenging weighted Hamming losses, which are crucial in applications. While in principle our approach is a straightforward marginalization, it requires solving many related MAP …
Reconstructing the causal network in a complex dynamical system plays a crucial role in many applications, from sub-cellular biology to economic systems. Here we focus on inferring gene regulation networks (GRNs) from perturbation or gene deletion experiments. Despite their scientific merit, such perturbation experimen…
Study robust control for systems with continuous states using adversarial perturbations.
problem Fragile policies in Markov control models under internal or external perturbations.
method Distributionally robust stochastic control with adaptive adversarial perturbations.
result Optimal robust policies for continuous state systems with uniform learning guarantees.
Spectral portfolio theory links neural networks to wealth dynamics via SGD weight matrices.
problem Understanding wealth dynamics from neural network training.
method Direct identification of weight matrices as portfolio allocation matrices, linking SGD forces to portfolio dynamics.
result Spectral properties of SGD weight matrices transition between additive and multiplicative regimes, influencing wealth dynamics.