arXiv research

Transformers approximate mean-field dynamics of indistinguishable particles.

New index principle shows indistinguishability of certain knot crossings.

The paper examines how to test if two learning algorithms produce similar outcomes.

Characterizes sample complexity for outcome indistinguishability in machine learning.

Framework uses human judgment to distinguish algorithmically indistinguishable cases.

Survey on calibration in machine learning, viewing it as indistinguishability.

We construct a flat (and fake-flat) 2-connection in the configuration space of $n$ indistinguishable particles in the complex plane, which categorifies the $sl(2,C)$-Knizhnik-Zamolodchikov connection obtained from the adjoint representation of $sl(2,C)$. This will be done by considering the adjoint categorical represen…

A new metric evaluates classification algorithms at the point of indistinguishability.

A treatment of the spin-statistics relation in nonrelativistic quantum mechanics due to Berry and Robbins [Proc. R. Soc. Lond. A (1997) 453, 1771-1790] is generalised within a group-theoretical framework. The construction of Berry and Robbins is re-formulated in terms of certain locally flat vector bundles over n-parti…

Machine learning models have been found to be susceptible to adversarial examples that are often indistinguishable from the original inputs. These adversarial examples are created by applying adversarial perturbations to input samples, which would cause them to be misclassified by the target models. Attacks that search…

Efficiently generates models resistant to falsification.

The paper formalizes robot environments using topological concepts.

We investigate the possibility of statistical evaluation of the market completeness for discrete time stock market models. It is known that the market completeness is not a robust property: small random deviations of the coefficients convert a complete market model into a incomplete one. The paper shows that market inc…

New approach shows backdoor attacks are indistinguishable from natural data features.

A computer vision approach improves neutral particle detection in particle flow algorithms.

Jointly estimates flow fields and particle properties from Lagrangian data.

The possibility of statistical evaluation of the market completeness and incompleteness is investigated for continuous time diffusion stock market models. It is known that the market completeness is not a robust property: small random deviations of the coefficients convert a complete market model into a incomplete one.…

Estimates log-likelihood of interacting particle systems using virtual particles.

This paper optimizes functions of probability measures using particle gradient descent for displacement convex functions.

The excluded area between a pair of two-dimensional hard particles with given relative orientation is the region in which one particle cannot be located due to the presence of the other particle. The magnitude of the excluded area as a function of the relative particle orientation plays a major role in the determinatio…

Differentiable resampling improves particle filter performance.

A method for optimal Bayesian filtering using progressive particle flow and optimal transport maps.

Optimal weights improve particle-based approximations of discrete distributions.

Graph convolutional networks (GCNs) are a widely used method for graph representation learning. To elucidate the capabilities and limitations of GCNs, we investigate their power, as a function of their number of layers, to distinguish between different random graph models (corresponding to different class-conditional d…

Particle MCMC involves using a particle filter within an MCMC algorithm. For inference of a model which involves an unobserved stochastic process, the standard implementation uses the particle filter to propose new values for the stochastic process, and MCMC moves to propose new values for the parameters. We show how p…

Unsupervised learning models can be indistinguishable without identifiability, leading to unreliable representations.

Improved particle approximation for mean-field neural networks.

A new particle filter avoids resampling to improve state estimation in high dimensions.

We introduce a new sequential Monte Carlo algorithm we call the particle cascade. The particle cascade is an asynchronous, anytime alternative to traditional particle filtering algorithms. It uses no barrier synchronizations which leads to improved particle throughput and memory efficiency. It is an anytime algorithm i…

Paper uses averaging from many particle filters to approximate posterior predictive distributions.

Cryo-electron microscopy (cryoEM) is an increasingly popular method for protein structure determination. However, identifying a sufficient number of particles for analysis (often >100,000) can take months of manual effort. Current computational approaches are limited by high false positive rates and require significant…

This paper studies when particle filtering is efficient for planning in partially observed systems.

Interacting particle methods are increasingly used to sample from complex and high-dimensional distributions. These stochastic particle integration techniques can be interpreted as an universal acceptance-rejection sequential particle sampler equipped with adaptive and interacting recycling mechanisms. Practically, the…

Cryo-electron microscopy (cryo-EM) is an emerging experimental method to characterize the structure of large biomolecular assemblies. Single particle cryo-EM records 2D images (so-called micrographs) of projections of the three-dimensional particle, which need to be processed to obtain the three-dimensional reconstruct…

New algorithm trains latent diffusion models using interacting particles.

Graphs indistinguishable by GNNs are fully characterized.

Particle-optimization-based sampling (POS) is a recently developed effective sampling technique that interactively updates a set of particles. A representative algorithm is the Stein variational gradient descent (SVGD). We prove, under certain conditions, SVGD experiences a theoretical pitfall, {\it i.e.}, particles te…

Time dilation $\frac{1}{\sqrt{1-v^2}}$ and relative velocity $v$ are observationally indistinguishable in the special theory of relativity, a duality that carries over into the general theory under Fermi coordinates along a curve (in coordinate-independent language, in the tangent Minkowski space along the curve). For …

We show social events can be accurately predicted, but often undesirably.

Framework expands particle filtering to estimate states beyond prior boundaries.

Enhances particle filters with neural augmentation for multi-sub-state tracking.

CMS uses machine learning to improve particle flow reconstruction.

A new particle algorithm improves mean-field variational inference.

A method makes particle filters differentiable without altering their forward pass.

Online convex optimization is a sequential prediction framework with the goal to track and adapt to the environment through evaluating proper convex loss functions. We study efficient particle filtering methods from the perspective of such a framework. We formulate an efficient particle filtering methods for the non-st…

Cryo-electron microscopy (cryo-EM) studies using single particle reconstruction are extensively used to reveal structural information on macromolecular complexes. Aiming at the highest achievable resolution, state of the art electron microscopes automatically acquire thousands of high-quality micrographs. Particles are…

We introduce a novel description of the dynamics of the order book of financial markets as that of an effective colloidal Brownian particle embedded in fluid particles. The analysis of a comprehensive market data enables us to identify all motions of the fluid particles. Correlations between the motions of the Brownian…

Achieved all-orders worldline action for Kerr black hole.