Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

3857711,1561,541 · Jun 202019922001200920172026
48 results for operator-theoretic learning

Unified framework explains why overfitting is benign in interpolating learning.

problem Understanding why overfitting is benign in highly overparameterized models.
method Spectral-transport stability framework.
result Sharp benign-overfitting criterion and explicit phase-transition rates.

In this paper, we get a Kastler-Kalau-Walze type theorem associated to nonminimal de Rham-Hodge operators on compact manifolds with boundary. We give two kinds of operator-theoretic explanations of the gravitational action in the case of four dimensional compact manifolds with flat boundary.

2016-07-27abs ↗pdf ↗

New bound for neural networks with full-rank weights, independent of network width.

problem Understanding generalization of neural networks with full-rank weight matrices.
method Using Koopman operators to derive a tighter generalization bound for full-rank weight matrices.
result The bound is tighter than existing norm-based bounds when condition numbers are small.

We investigate in detail the connection between harmonic maps from Riemann surfaces into the unitary group $\U(n)$ and their Grassmannian models: these are families of shift-invariant subspaces of $L^2(S^1,\C^n)$. With the help of operator-theoretic methods we derive a criterion for finiteness of the uniton number whic…

2018-12-21abs ↗pdf ↗

A large number of algorithms in machine learning, from principal component analysis (PCA), and its non-linear (kernel) extensions, to more recent spectral embedding and support estimation methods, rely on estimating a linear subspace from samples. In this paper we introduce a general formulation of this problem and der…

2014-08-21abs ↗pdf ↗

When estimating finite mixture models, it is common to make assumptions on the mixture components, such as parametric assumptions. In this work, we make no distributional assumptions on the mixture components and instead assume that observations from the mixture model are grouped, such that observations in the same gro…

2016-06-30abs ↗pdf ↗

Kernel-based Bayesian filter for nonlinear systems using infinite-dimensional operators.

problem Modeling and predicting nonlinear dynamical systems.
method Functional Bayesian perspective, reproducing kernel Hilbert space, Gaussian kernel.
result Effective approximation and accurate results for nonlinear systems.

In this article, we introduce the notion of cycling operations of arbitrary order in Garside groups, which is a full generalization of the cycling and decycling operations. Theoretically, this notion together with other related concepts provides a context in which various definitions and arguments concerning Garside gr…

2006-05-30abs ↗pdf ↗

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.

Paper tackles conditional expectation estimation using compactification operators.

problem Estimating conditional expectations from product of two random variables.
method Operator theoretic approach using kernel integral operators in reproducing kernel Hilbert space.
result Solutions allow numerical approximation and convergence of data-driven implementations.

New method learns policies from offline data using operator models.

problem Limited understanding of approximation errors in offline reinforcement learning.
method Linking reinforcement learning to Hamilton-Jacobi-Bellman equation, proposing operator-theoretic algorithm.
result Global convergence of the value function and finite-sample guarantees derived.

The paper tackles data-driven optimal control of unknown nonlinear systems using RKHS.

problem Unknown nonlinear dynamics and stage cost functions.
method Embed state densities into RKHS, learn Markov operators, solve Hamilton-Jacobi-Bellman recursions.
result Solves a wide range of nonlinear control problems, including depth regulation.

DOODL learns shared spectral dynamics across related dynamical systems.

problem Learning independent dynamical operators for each system limits discovery of shared structure.
method DOODL learns a dictionary of characteristic spectral dynamics on a manifold of related systems.
result DOODL achieves errors one to two orders of magnitude lower than independent operator estimation methods.

The paper proposes a new method for creating interpretable models using convex optimization.

problem Creating models that are both accurate and interpretable for decision-making.
method Formulates convex learning problems that combine interpretability with accuracy, using operator theory and parametric nonlinear models.
result Shows how to create efficient surrogate models that are both accurate and interpretable.

Unified framework for analyzing graph neural operators converging to graph limits.

problem Analyzing convergence of graph neural operators to graph limits.
method Develops a unified spectral framework for graph neural operators under various graphon assumptions.
result Unified framework enables direct comparison of convergence rates and tradeoffs.

Develops a smooth operator framework for analyzing neural network representations.

problem Analyzing the geometry of feedforward neural network representations.
method Introduces a smooth operator-theoretic approach based on diffusion Markov operators derived from feature clouds.
result Establishes a stable operator-geometric framework for tracking training, width, and perturbation stability.

Geometric formalism views optimization algorithms as discrete connections, revealing their algebraic curvature and flatness properties.

problem Understanding and optimizing the behavior of iterative optimization algorithms.
method Introducing a geometric and operator-theoretic formalism where optimization algorithms are encoded by coupled channels (drift and diffusion) whose algebraic curvature measures the deviation from ideal reversibility.
result Flat connections correspond to methods whose updates commute up to higher order, achieving minimal numerical dissipation and preserving stability.

MGDL refines deep neural networks by training grades sequentially, improving stability.

problem Training deep neural networks is challenging due to nonconvex optimization landscapes.
method MGDL trains deep networks grade by grade, freezing previously learned grades and training new ones to fit residuals.
result MGDL guarantees vanishing error in a fixed-width multigrade ReLU architecture.

New framework for higher-order singular-value derivatives of rectangular matrices.

problem Challenging to derive higher-order Fréchet derivatives of singular values in real rectangular matrices.
method Using Kato's analytic perturbation theory for self-adjoint operators and embedding rectangular matrices into block self-adjoint operators.
result Closed-form expressions for the nn-th order spectral variations of singular values.

Develops a new framework for temporal anchoring in deep embedding spaces.

problem Temporal anchoring in deep embedding spaces, especially drift and convergence issues.
method Operator-theoretic framework with drift maps and event-indexed blocks, proving convergence theorems and equivalence theorems.
result Proves convergence theorems and equivalence theorems for the proposed framework.

Kernel Dynamic Mode Decomposition reconstructs dynamical systems using Laplacian kernel.

problem Reconstructing spatial-temporal dynamics of complex systems.
method Kernel Dynamic Mode Decomposition with Laplacian kernel.
result Laplacian kernel allows for the closability of Koopman operators in RKHS, enabling reconstruction.

New method uses weighted SDEs to improve sampling from complex distributions.

problem Sampling from highly non-log-concave distributions.
method Introduces weighted stochastic differential equations to augment diffusion-based samplers.
result Demonstrates improved exploration of nonconvex or multimodal landscapes.

The paper analyzes variance reduction in stochastic gradient Langevin dynamics.

problem Reducing the variance of stochastic gradient estimators in Langevin dynamics.
method Central limit theorem and Poisson equation analysis for variance characterization.
result Anti-symmetric perturbations can reduce the variance of non-reversible Langevin dynamics.

Paper develops a minimax optimal test for goodness-of-fit using kernel Stein discrepancy.

problem Developing a robust goodness-of-fit test for general domains.
method Kernel Stein Discrepancy (KSD) with spectral regularization and adaptive testing.
result Proposed regularized test achieves minimax optimality up to a logarithmic factor.

Bayesian method with Gaussian process priors achieves optimal convergence rates for regression function and its derivatives.

problem Estimating the regression function and its derivatives in nonparametric regression.
method Bayesian approach with Gaussian process priors, focusing on convergence rates and plug-in property.
result Equivalence of convergence rates of posterior distributions and Bayes estimators for regression function and its derivatives.

Meta-learning improves neural networks by adapting learning algorithms.

problem Conventional AI approaches solve tasks from scratch, but meta-learning aims to improve the learning algorithm.
method Meta-learning adapts a learning algorithm based on multiple learning episodes.
result Meta-learning can tackle deep learning challenges like data and computation bottlenecks.

New method uses bi-level optimization to learn useful representations for imitation learning.

problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.

Study Whittle index learning algorithms for restless bandits with constant stepsizes.

problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.