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.

168,657 papers · 148 categories

Trend · papers per month

95191286381 · Jun 202019922001200920172026
48 results for Linearized Doubling

This paper explains double descent in linear neural networks, identifying new factors.

problem Understanding double descent in linear neural networks.
method Gradient flow derivation and necessary conditions for double descent.
result Singular values of input-output covariance matrix are important for double descent in two-layer models.

Double descent phenomenon explained in simple terms.

problem Understanding the surprising drop in test error in overparameterized models.
method Informal explanation using linear algebra and probability, visual intuition with polynomial regression, mathematical analysis with ordinary linear regression.
result Three factors create double descent: data undersampling, model size, and parameter count. Ablating any one of these factors prevents double descent.

Study shows double descent curve in high-dimensional linear regression with random projections.

problem Understanding the generalization performance in high-dimensional settings with random projections.
method Fixed prediction problem, ridge regression estimator, minimum norm least-squares fit, random matrix theory, asymptotic equivalents.
result Exhibit a double descent curve for high-dimensional linear regression with random projections.

Double Q-learning has the same mean-squared error as Q-learning under certain conditions.

problem Comparing the mean-squared error of Double Q-learning and Q-learning.
method Theoretical analysis based on Lyapunov equations for both tabular and linear function approximation settings.
result The asymptotic mean-squared error of Double Q-learning is exactly equal to that of Q-learning under specific conditions.

Extends double linear policy with time-varying weights and proves robust positive expectation.

problem Ensuring robustness in policy optimization with time-varying parameters.
method Employed a novel elementary symmetric polynomials characterization approach to prove robust positive expectation (RPE). Derived explicit expressions for expected cumulative gain-loss and variance.
result Proved the robust positive expectation property holds for the extended double linear policy.

Geometric arguments show simplicial arrangements with few double points can't have an irreducible cubic curve dual.

problem Classifying simplicial arrangements with a linear bound on double points.
method Geometric arguments and structure theorem from Green and Tao.
result Simplicial arrangements with few double points can't have an irreducible cubic curve dual.

Optimal regularization can prevent the double descent phenomenon in learning models.

problem The double descent phenomenon in learning models, where test performance is non-monotonic in sample size and model size.
method Theoretical and empirical study of optimal 2\ell_2 regularization for linear regression models and neural networks.
result Optimally-tuned 2\ell_2 regularization achieves monotonic test performance for certain models and mitigates the double descent phenomenon for more general models.

This paper describes an equivalence of the canonical category of N\mathbb N-manifolds of degree 22 with a category of involutive double vector bundles. More precisely, we show how involutive double vector bundles are in duality with double vector bundles endowed with a linear metric. We describe then how special sect…

2017-07-21abs ↗pdf ↗

A linear section of a double vector bundle is a parallel pair of sections which form a vector bundle morphism; examples include the complete lifts of vector fields to tangent bundles and the horizontal lifts arising from a connection in a vector bundle. A grid in a double vector bundle consists of two linear sections, …

2019-09-12abs ↗pdf ↗

The paper studies hyperbolic equations in a spacetime foliation, proving existence and uniqueness.

problem Existence and uniqueness of solutions for first-order linear hyperbolic systems in a double null foliation.
method Proves global existence and uniqueness for first-order linear hyperbolic systems with initial data on a past null hypersurface.
result Derives a novel algebraic constraint for tensorfields satisfying the linearized Bianchi equations.

Analyzes generalization error in generalized linear models, explaining double descent phenomenon.

problem Understanding generalization of machine learning models in high dimensions.
method Develops a framework to characterize asymptotic generalization error for generalized linear models.
result Rigorously explains the double descent phenomenon in generalized linear models.

New method controls linear systems with partial info and disturbances.

problem Controlling linear dynamical systems under partial observation and adversarial disturbances.
method Double Spectral Control (DSC) using two-level spectral approximation strategy.
result Matches best known regret guarantees with exponential runtime improvement.

New method for estimating parameters in inverse problems using double robustness.

problem Estimating parameters defined as linear functionals of solutions to linear inverse problems.
method Source condition double robust inference method that uses iterated Tikhonov regularized adversarial estimators.
result Asymptotic normality of the parameter of interest as long as either the primal or dual inverse problem is sufficiently well-posed.

We use the exterior product of double forms to reformulate celebrated classical results of linear algebra about matrices and bilinear forms namely the Cayley-Hamilton theorem, Laplace expansion of the determinant, Newton identities and Jacobi's formula for the determinant. This new formalism is then used to naturally g…

2011-12-06abs ↗pdf ↗

The paper explores how overfitting can lead to better predictions in high-dimensional data.

problem Understanding the behavior of linear models in high-dimensional settings with more predictors than observations.
method Analysis of ordinary least squares, penalized least squares, and spectral shrinkage estimates.
result The phenomenon of double descent, where model performance can improve with increasing model complexity.

We show that double Lie algebroids, together with a chosen linear splitting, are equivalent to pairs of 2-term representations up to homotopy satisfying compatibility conditions which extend the notion of matched pair of Lie algebroids. We discuss in detail the tangent of a Lie algebroid.

2014-09-04abs ↗pdf ↗

Double descent in transfer learning explained for linear regression problems.

problem Understanding generalization errors in transferring parameters between overparameterized linear regression tasks.
method Analytical characterization of generalization error in terms of transfer learning factors.
result Generalization error follows a two-dimensional double descent trend controlled by transfer learning factors.

A new approach optimizes weights in DLP for better risk-adjusted performance.

problem Optimizing time-varying weights in Double Linear Policy (DLP) for better risk-adjusted performance.
method Stochastic Model Predictive Control (SMPC) framework to maximize risk-adjusted returns while enforcing constraints.
result Empirical results show improved risk-adjusted performance and drawdown control.

In this expository note we describe a surprising phenomenon in overparameterized linear regression, where the dimension exceeds the number of samples: there is a regime where the test risk of the estimator found by gradient descent increases with additional samples. In other words, more data actually hurts the estimato…

2019-12-16abs ↗pdf ↗

Dropout improves regularization in flexible models for rare features.

problem Understanding theoretical properties of dropout in generalized linear models.
method Theoretical analysis and application to adaptive smoothing with B-splines.
result Dropout prefers rare features in mean and dispersion parameters.

New trading policies preserve robust gains in presence of transaction costs.

problem Maintaining robust gains in asset trading with transaction costs.
method Proposed double linear trading policies, analyzed with Monte Carlo simulations and historical data.
result Desired robust positive expected gain can be preserved under certain conditions.

Study shows double and triple descent in unsupervised autoencoders, improving performance in various tasks.

problem Exploring the phenomenon of double descent in unsupervised learning.
method Analytical demonstration and extensive experiments on synthetic and real datasets.
result Over-parameterized unsupervised autoencoders exhibit double and triple descent, enhancing performance in downstream tasks.

Study on ridge regression in convolutional models shows double descent error behavior.

problem Understanding generalization and estimation error in over-parameterized convolutional models.
method Analysis of ridge estimators for convolutional linear models, derivation of exact error formulae.
result Ridge estimators exhibit double descent error behavior in high-dimensional convolutional models.

Double descent risk in L2-regularized models explained and mitigated.

problem Risk of overparameterized models in machine learning.
method Analysis of L2-regularized models, two-layer neural networks, and CNNs.
result Double descent risk in L2-regularized models can be explained and mitigated by adjusting regularization strengths.

The Slope Conjecture proposed by Garoufalidis asserts that the degree of the colored Jones polynomial determines a boundary slope, and its refinement, the Strong Slope Conjecture proposed by Kalfagianni and Tran asserts that the linear term in the degree determines the topology of an essential surface that satisfies th…

2018-11-28abs ↗pdf ↗

Theory and method for reducing prediction variance in noisy feature-subsampled ridge ensembles.

problem Reduction of prediction variance in noisy data with feature bagging.
method Developed analytical learning curves for noisy ridge ensembles, introduced heterogeneous feature ensembling.
result Subsampling shifts the double-descent peak, leading to improved performance over a single linear predictor.

We analyze double descent in finite-width neural networks using influence functions.

problem Understanding double descent in finite-width neural networks.
method Using influence functions to derive population loss bounds and investigate loss function effects.
result Derived bounds exhibit double descent behavior at the interpolation threshold.

Deep learning models can generalize well even when they fit training data perfectly.

problem Generalization in over-parameterized deep learning models.
method Combining empirical risk minimization with capacity control, exploring inductive biases and smooth empirical risk minimizers.
result Double descent phenomenon: test error can decrease after interpolation point.

Every compact symplectic 4-manifold can be realized as a branched cover of the complex projective plane branched along a symplectic curve with cusp and node singularities; the covering map is induced by a triple of sections of a "very ample" line bundle. In this paper, we give an explicit formula describing the behavio…

2006-04-28abs ↗pdf ↗

Study compares random and learned features in deep Bayesian linear models.

problem Understanding how feature learning affects generalization in deep learning.
method Comparing deep random feature models to deep networks with trained layers.
result Random feature models can display double-descent behavior, while deep networks do not.

Given a double vector bundle DMD\to M, we define a bigraded `Weil algebra' W(D)\mathcal{W}(D), which `realizes' the algebra of smooth functions on the supermanifold D[1,1]D[1,1]. We describe in detail the relations between the Weil algebras of DD and those of the double vector bundles D, D"D',\ D" obtained by duality operation…

2019-01-02abs ↗pdf ↗

Paper optimizes prediction in semi-functional linear models using kernel methods.

problem Optimizing prediction in semi-functional linear models with functional and nonparametric components.
method Double-penalized least squares method in reproducing kernel Hilbert spaces, with regularization parameter selection via generalized cross validation.
result Achieves minimax optimal rates of convergence for both functional and nonparametric components.