Recently, path norm was proposed as a new capacity measure for neural networks with Rectified Linear Unit (ReLU) activation function, which takes the rescaling-invariant property of ReLU into account. It has been shown that the generalization error bound in terms of the path norm explains the empirical generalization b…
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “basis paths”
Proposes a new method to learn entire solution paths without discretization.
problem Optimizing a family of problems indexed by hyperparameters.
method Parameterizes the solution path with basis functions and solves a single stochastic optimization problem.
result Uniform error of learned path converges linearly to a constant related to basis expressiveness.
This paper introduces PSI-flatness to better understand ReLU neural networks' flatness and generalization.
problem Existing flatness definitions fail to account for ReLU neural networks' Positively Scale-Invariant (PSI) property.
method Formalizes PSI-flatness on basis path values, proving its relation to generalization.
result Minimums with balanced basis path values are flatter and generalize better.
Introduces a neural network-based method for efficient state and parameter estimation in complex systems.
problem Efficiently estimating state paths and parameters from noisy measurements in high-dimensional nonlinear systems.
method Bayesian Information Field Theory with neural network parameterization and optimization algorithms.
result Proposes a method to simplify and enrich state path parameterizations using neural networks, improving inference accuracy.
New basis and Schur-Weyl duality for loop Hecke algebra defined.
problem Define a new basis for the loop Hecke algebra.
method Use higher linear rewriting theory and combinatorics of Dyck paths.
result Yields a conjecture of Damiani-Martin-Rowell and provides a representation theoretic interpretation.
PSLR classifies functional data with scalar covariates using path signatures.
problem Classical functional logistic regression models have limitations in capturing nonlinear and cross-channel dependencies.
method PSLR uses truncated path signatures to create a basis-free representation of functional data.
result PSLR outperforms traditional functional classifiers in accuracy and robustness, especially under non-uniform sampling.
Study transitions between tableau and spider bases for Specht modules.
problem Transitioning between tableau and spider bases for Specht modules.
method Combinatorial path model to study transitioning matrix from tableau basis to spider basis.
result Positive entries in the transitioning matrix for upper-triangular portion.
Geometrically represents path integral reduction Jacobian for interacting systems.
problem Quantizing a model mechanical system with dependent coordinates.
method Geometric representation using scalar curvature and Christoffel symbols in a nonholonomic basis.
result Found a geometric representation for the path integral reduction Jacobian.
This paper simplifies hedge ratios in financial models using pathwise algorithmic differentiation.
problem Expensive and unstable computation of hedge ratios from pathwise sensitivities.
method Develops reduced stochastic hedge ratios of the form φ_j^r = Σ_j^r ξ_j^q X_q, retaining sensitivity tensor through empirical averages.
result Two coefficient criteria are introduced to minimize pathwise residuals and satisfy moment equations.
This research calculates node similarity on graphs using path-based kernels.
problem Computing similarity between nodes on graphs.
method Derives closed-form expressions for co-presence and co-occurrence of nodes on paths.
result Introduced kernels provide competitive results in semi-supervised classification.
It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient descent optimize the neural networks in the vector space of weights, which is, however, not positively scale-invariant. This mismatch may lead to…
We compare two important bases of an irreducible representation of the symmetric group: the web basis and the Specht basis. The web basis has its roots in the Temperley-Lieb algebra and knot-theoretic considerations. The Specht basis is a classic algebraic and combinatorial construction of symmetric group representatio…
Path-independent equilibrium models improve network performance on harder problems.
problem Improving network performance on harder problem instances.
method Investigated path-independent equilibrium models and their impact on network performance.
result Path independence correlates with better performance on harder problem instances.
Two signature-based methods solve optimal stopping in non-Markovian frameworks.
problem Optimal stopping in non-Markovian frameworks, particularly pricing American options.
method Primal and dual formulations using linear functionals of rough path signatures.
result Both primal and dual methods converge and provide numerical examples.
Twistor space constructions and actions are given for full Yang-Mills and conformal gravity using almost complex structures that are not, in general, integrable. These are used as the basis of a derivation of the twistor-string generating functionals for tree level perturbative scattering amplitudes of Yang-Mills and c…
In this paper we review the recently proposed path-integral counterpart of the Koopman-von Neumann operatorial approach to classical Hamiltonian mechanics. We identify in particular the geometrical variables entering this formulation and show that they are essentially a basis of the cotangent bundle to the tangent bund…
New algorithmic view of ℓ2 regularization using ODEs and path-following methods.
problem Optimizing convex loss functions with ℓ2 regularization.
method Established an equivalence between ℓ2-regularized solution paths and ODEs, proposing path-following algorithms based on homotopy methods and numerical ODE solvers.
result The solution path can be viewed as a hybrid of gradient descent and Newton method, providing novel schemes to choose grid points and reducing computational cost.
Signature-Based Optimal Execution for Statistical Arbitrage with Path-Dependent Trading Signalsq-fin.TR
Develops a new trading strategy for statistical arbitrage with path-dependent signals.
problem Optimal execution in statistical arbitrage strategies with dynamic predictive signals.
method Signature-based framework modeling alpha and trading speed as linear functionals of truncated signature of market path.
result Fitted policy achieves higher return on turnover compared to a z-score benchmark.
The paper compares machine learning methods with traditional techniques for pricing and sensitivities of financial products with path-dependent structures.
problem Evaluating financial products with early-termination clauses, especially those with path-dependent structures.
method The paper compares regression methods including randomized recurrent and feed-forward neural networks, and a novel approach using signatures of the underlying price process, with traditional polynomial basis functions for pricing and sensitivities.
result Machine learning algorithms often match the accuracy and efficiency of traditional methods for Asian and look-back options, while randomized neural networks are best for callable certificates.
Deep Importance Samplingq-fin.CP
A new method reduces Monte Carlo variance for financial payoffs.
problem Reducing variance in Monte Carlo estimators for financial payoffs.
method Path-dependent importance sampling using neural networks.
result Significant variance reduction (2-9 times) for various financial payoffs.
Rough path theory is focused on capturing and making precise the interactions between highly oscillatory and non-linear systems. It draws on the analysis of LC Young and the geometric algebra of KT Chen. The concepts and the uniform estimates, have widespread application and have simplified proofs of basic questions fr…
Deep learning improves probabilistic PPDE solution accuracy.
problem Approximating solutions to path-dependent PDEs with limited basis selection.
method Deep learning for conditional expectation estimation with error bounds.
result Deep learning yields more accurate PPDE solutions, especially in high dimensions.
If a knot is represented by an m-strand braid, then HOMFLY polynomial in representation R is a sum over characters in all representations Q\in R^{\otimes m}. Coefficients in this sum are traces of products of quantum R-matrices along the braid, but these matrices act in the space of intertwiners, and their size is equa…
We consider a new family of operators for reinforcement learning with the goal of alleviating the negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include showing on a sample path basis that our family of operators preserve optimality an…
The statistical analysis of data lying on a differentiable, locally Euclidean, manifold introduces a variety of challenges because the analogous measures to standard Euclidean statistics are local, that is only defined within a neighbourhood of each datapoint. This is because the curvature of the space means that the c…
Dynamic Visualization and Fast Computation for Convex Clustering via Algorithmic Regularizationstat.ML
CARP speeds up convex clustering by 100x and offers better visualization.
problem Computational intensity and lack of compelling visualizations in convex clustering.
method Algorithmic Regularization for iterative approximation of regularization paths.
result CARP delivers over 100-fold speed-up and finer approximation grid.
The paper develops fair machine learning models using causal path-specific effects.
problem Fairness in machine learning models under causal constraints.
method Lagrange multiplier approach for infinite-dimensional functional estimation, closed-form solutions for constrained optimization.
result Theoretical and flexible semiparametric estimation strategies for fair predictions.
We propose a method to compute optimal control paths for autonomous vehicles deployed for the purpose of inferring a velocity field. In addition to being advected by the flow, the vehicles are able to effect a fixed relative speed with arbitrary control over direction. It is this direction that is used as the basis for…
Efficiently computes sparse signature coefficients using kernels.
problem Lack of efficient methods for sparse signature coefficients.
method Signature kernels and PDE-based methods.
result Sparse groups of signature coefficients can be isolated effectively.
We propose a new algorithm for estimating NARMAX models with regularization for models represented as a linear combination of basis functions. Due to the -norm penalty the Lasso estimation tends to produce some coefficients that are exactly zero and hence gives interpretable models. The novelty of the contri…
A variance swap is a derivative with a path-dependent payoff which allows investors to take positions on the future variability of an asset. In the idealised setting of a continuously monitored variance swap written on an asset with continuous paths it is well known that the variance swap payoff can be replicated exact…
A path integral on a link complement of a three-sphere fixes a vector (the "link state") in Chern-Simons theory. The link state can be written in a certain basis with the colored link invariants as its coefficients. We use symmetric webs to systematically compute the colored link invariants, by which we can write down …
The study lists low-dimensional stratified groups and their properties.
problem Understanding the algebraic structure of stratified groups.
method Explicitly provided a list of low-dimensional stratified groups and their properties.
result All stratified groups in dimensions up to 7 and some free-nilpotent groups in dimensions up to 14 were studied.
LEAP predicts graph edges and weights from path aggregations.
problem Predicting edges and weights in graphs.
method Trainable framework based on path aggregations.
result LEAP outperforms state-of-the-art methods in link and rating prediction.
Develops geometric integration for rough differential forms.
problem Integrating rough differential forms with low regularity.
method Uses rough path theory to construct geometric integration.
result Constructs geometric integration for rough differential forms.
Diffusion-weighted magnetic resonance imaging (DWI) and fiber tractography are the only methods to measure the structure of the white matter in the living human brain. The diffusion signal has been modelled as the combined contribution from many individual fascicles of nerve fibers passing through each location in the …
A combinatorial description of the centralizer algebras connected to the Links-Gould Invariantmath.QA
In this paper we study the tensor powers of the standard representation of the quantum super-algebra , focusing on the rings of its algebra endomorphisms, called centraliser algebras and denoted by . Their dimensions were conjectured by I. Marin and E. Wagner \cite{MW}. We prove this conjecture, desc…
We give an equivalent description of taut submanifolds of complete Riemannian manifolds as exactly those submanifolds whose normal exponential map has the property that every preimage of a point is a union of submanifolds. It turns out that every taut submanifold is also -taut. We explicitely construct gen…
New method infers and samples point processes from latent diffusion.
problem Modeling point processes with latent diffusion.
method Itô's excursion theory for inference and sampling.
result Proposes a new method to infer and sample point processes.
The paper introduces vortex nerve complexes and new Betti numbers in CW spaces.
problem Understanding the structure and properties of CW complexes and their nerves.
method Introducing vortex nerve complexes and defining new Betti numbers for CW complexes.
result New Betti numbers (vortex , vortex nerve , shape ) are introduced and studied.
The study uses response theory to understand RNNs processing input signals.
problem Understanding how RNNs process sequential data.
method Deriving a Volterra series representation for SRNNs output using response theory from nonequilibrium statistical mechanics.
result SRNNs can be viewed as kernel machines operating on a reproducing kernel Hilbert space associated with the response feature.
ControlBurn selects few features from tree ensembles for better model interpretability.
problem Improving model interpretability in machine learning models.
method Sparse tree ensembles with lasso optimization.
result ControlBurn selects feature-sparse subsets for better model interpretability.
In this paper, we are interested in constructing general graph-based regularizers for multiple kernel learning (MKL) given a structure which is used to describe the way of combining basis kernels. Such structures are represented by sum-product networks (SPNs) in our method. Accordingly we propose a new convex regulariz…
Paper presents a new insurance model equation for diverse structures.
problem Handling diverse insurance models with a single equation.
method Developed a canonical model construction and stochastic backward equations.
result Comparison theorems for different models follow from the new equation.
Uncertainty-Aware Deep Hedgingq-fin.CP
Improved deep hedging with ensemble uncertainty quantification.
problem Uncertainty in deep hedging models hinders their deployment.
method Trained an ensemble of LSTM networks to quantify uncertainty in deep hedging under Heston volatility and proportional transaction costs.
result The ensemble's disagreement provides a strong predictive confidence measure for hedge performance.
Examining Lead-Lag Relationships In-Depth, With Focus On FX Market As Covid-19 Crises Unfoldsq-fin.ST
New technique identifies lead-lag relationships in FX market during pandemic.
problem Identifying lead-lag relationships in financial markets, especially during crises.
method Dynamic Programming technique for finding optimal lead-lag path, using a loose metric.
result The proposed technique gives the best results in identifying statistically significant paths and closest forecasts.
New algorithm selects relevant variables in high-dimensional graphical models.
problem Automatic selection of relevant variables in high-dimensional graphical models.
method Extends Chow and Liu's algorithm using mutual information and entropy coefficient of determination.
result Outperforms existing methods in selecting variables with explanatory power.
This study connects Gaussian processes and RKHS, bridging two machine learning communities.
problem Understanding the relationship between Gaussian processes and RKHS.
method Examining connections and equivalences in regression, interpolation, and other topics.
result Established the equivalence between Gaussian Hilbert space and RKHS.