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

76152228304 · Jun 202019922001200920172026
48 results for interpolating solution

REPAIR mitigates variance collapse to enable linear interpolation between SGD solutions.

problem Linear interpolation between SGD solutions is difficult due to variance collapse in permuted activations.
method REPAIR rescales preactivations of interpolated networks to mitigate variance collapse.
result 60%-100% relative barrier reduction across various architectures and tasks.

A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We investigate this overparameterized regime in linear regression, where all solut…

2019-03-21abs ↗pdf ↗

New optimization method helps models generalize better after achieving near-perfect training performance.

problem Models can achieve near-perfect training performance but fail to generalize well to unseen examples.
method GROKtimizer combines rapid convergence to interpolation with post-interpolation norm minimization using Critically Damped Momentum.
result GROKtimizer provides a quadratic speedup over classical gradient descent, offering a natural solution for selecting low-norm interpolating solutions.

Adversarial training improves linear regression solutions, revealing sparsity and abrupt interpolation.

problem Adversarial attacks on linear regression models.
method Formulated as a convex problem, adversarial training is used to find robust solutions that are sparse and interpolate data.
result Adversarial training with small disturbances gives the solution with the minimum-norm that interpolates the training data, revealing abrupt transition into interpolation.

This paper constructs PH spline curves with prescribed arc lengths.

problem Interpolating points, tangent directions, and curvatures with prescribed arc-length.
method Local construction of G2G^2 planar PH biarc curves of degree 7.
result Prescribed arc-length can be satisfied for any data and any chosen ratio between boundary tangents.

In this article we study various analytic aspects of interpolating sesqui-harmonic maps between Riemannian manifolds where we mostly focus on the case of a spherical target. The latter are critical points of an energy functional that interpolates between the functionals for harmonic and biharmonic maps. In the case of …

2019-07-09abs ↗pdf ↗

We introduce a new wavelet transform suitable for analyzing functions on point clouds and graphs. Our construction is based on a generalization of the average interpolating refinement scheme of Donoho. The most important ingredient of the original scheme that needs to be altered is the choice of the interpolant. Here, …

2011-10-10abs ↗pdf ↗

In the absence of explicit regularization, Kernel "Ridgeless" Regression with nonlinear kernels has the potential to fit the training data perfectly. It has been observed empirically, however, that such interpolated solutions can still generalize well on test data. We isolate a phenomenon of implicit regularization for…

2018-08-01abs ↗pdf ↗

Strong inductive biases prevent harmless interpolation in overparameterized models.

problem Understanding the conditions under which overparameterized models can interpolate noise without overfitting.
method Theoretical analysis of high-dimensional kernel regression and deep neural networks, focusing on the role of inductive biases.
result The strength of an estimator's inductive bias determines whether interpolation is harmless or requires fitting noise for good generalization.

This paper finds sparsest ReLU networks for interpolating data.

problem Finding the sparsest neural network that fits a dataset.
method Proposes a continuous, differentiable objective function based on p\ell^p quasinorms.
result Global minimizers of the proposed objective correspond to sparsest ReLU networks.

Two-layer ReLU networks often converge to simpler solutions, improving generalization.

problem Understanding generalization in overparametrized neural networks, especially for complex tasks.
method Theoretical analysis of two-layer ReLU networks, focusing on the early alignment phase.
result Two-layer ReLU networks often converge to simpler solutions rather than interpolating the training data, leading to better generalization.

Matrix SMD converges to unique solution minimizing Bregman divergence.

problem High-dimensional multi-output classification and matrix completion problems.
method Stochastic Mirror Descent with matrix parameters and matrix mirror functions.
result Matrix SMD converges exponentially to the unique solution minimizing Bregman divergence.

Deep linear networks can closely approximate interpolants without improving risk.

problem Understanding the risk bounds of deep linear networks compared to minimum 2\ell_2-norm solutions.
method Bounding excess risk of interpolating deep linear networks trained using gradient flow.
result Deep linear networks can closely approximate or match minimum 2\ell_2-norm solutions in terms of risk.

The paper shows how multi-task learning in neural networks is similar to kernel regression and Hilbert spaces.

problem Understanding the solutions to multi-task shallow ReLU neural network learning problems.
method Analyzing the properties of solutions to multi-task shallow ReLU neural network learning problems, proving uniqueness and equivalence to minimum-norm interpolation problems in Hilbert spaces.
result The solutions to multi-task neural network interpolation problems are almost always unique and coincide with the solution to a minimum-norm interpolation problem in a Sobolev (Reproducing Kernel) Hilbert Space.

Randomly sampled interpolators achieve zero generalization error with enough data.

problem Understanding the high generalization ability of machine learning models.
method Algebraic geometry tools to prove zero generalization error for random interpolators.
result Generalization error of randomly sampled interpolators becomes zero once the number of training samples exceeds a geometric threshold.

Study large deviation in stationarized fully lifted blirp interpolation.

problem Understanding atypical solutions in random optimization problems.
method Large deviation theory applied to fully lifted blirp interpolation.
result Elegant relations uncovered for fundamental interpolating parameters.

We classify generalised supersymmetric fluxbranes in type II string theory obtained as Kaluza-Klein reductions of the Minkowski space vacuum of eleven-dimensional supergravity. We obtain two families of smooth solutions which contains all the known solutions, new solutions called nullbranes, and solutions interpolating…

2001-10-18abs ↗pdf ↗

New research shows SVM and related methods can overfit without harm in multiclass classification.

problem Understanding benign overfitting in multiclass classification.
method Analyzing three training algorithms: ERM with cross-entropy, least-squares, and one-vs-all SVM.
result All three algorithms can lead to classifiers that interpolate training data and have equal accuracy under high overparameterization.

The paper studies the minimum ℓ₁-norm interpolator's risk behavior in over-parameterized settings.

problem Understanding the risk behavior of minimum ℓ₁-norm interpolators in high-dimensional settings.
method Exact characterization of the risk behavior through a system of two non-linear equations.
result Observation of a multi-descent phenomenon in the generalization risk of the minimum ℓ₁-norm interpolator.

Study shows gap between uniform convergence and test error in random feature models.

problem Understanding the gap between uniform convergence and test error in random feature models.
method Analytical expressions for uniform convergence over norm balls, interpolators, and minimum norm interpolator risk derived and proved.
result Uniform convergence over interpolators still gives a non-trivial bound of test error even when classical uniform convergence is vacuous.

Regression models can interpolate noisy data and still perform well, contrary to the bias-variance tradeoff.

problem Understanding why overparametrized models can generalize well despite the bias-variance tradeoff.
method Analysis of minimum norm solutions and ridge regression, focusing on the smallest singular value of the regression matrix.
result Testing error exhibits double descent behavior as model order increases, contrary to the classical bias-variance tradeoff.

New insights into optimization and generalization for linear models.

problem Understanding the implicit regularization of optimization methods for linear models.
method Investigating the norms minimized by interpolating solutions and using projections to move between solutions.
result Proving that for over-parameterized linear classification, projections onto the data-span enable the use of under-parameterized techniques.

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.

Study on clustering in high dimensions with anisotropic Gaussian mixtures, showing interpolation can be optimal and robust.

problem Clustering in high-dimensional anisotropic Gaussian mixtures.
method Derive minimax bounds, analyze 2\ell_2-regularized classifiers, and investigate interpolation's robustness.
result Interpolating solutions can be optimal and robust under certain conditions.

Adversarial training improves linear regression solutions, offering robustness against small perturbations.

problem Vulnerability of linear models to adversarial perturbations.
method Formulated as a min-max problem, adversarial training minimizes the best solution under worst-case attacks.
result Adversarial training yields the minimum-norm interpolating solution in overparameterized models, equivalent to parameter shrinking methods in underparameterized models.

Following Kobayashi, we consider Griffiths negative complex Finsler bundles, naturally leading us to introduce Griffiths extremal Finsler metrics. As we point out, this notion is closely related to the theory of interpolation of norms, and is characterized by an equation of complex Monge--Ampère type, whose correspondi…

2019-10-04abs ↗pdf ↗

Neural networks learn incrementally from orthogonal data, interpolating with minimal complexity.

problem Understanding the learning dynamics and implicit bias in ReLU networks with orthogonal data.
method Gradient flow analysis of two-layer ReLU networks from small initialization with orthogonal training data.
result The learned interpolator has a squared 2\ell_2-norm scaling as n\sqrt{n}, close to the minimal interpolator's complexity.

In this paper, we study the CR Yamabe flow with zero CR Yamabe invariant. We use the CR Poincaré inequality and a Gagliardo-Nirenberg type interpolation inequality to show that this flow has long time solution and the solution converges to a contact form with flat pseudo-Hermitian scalar curvature exponentially.

2018-07-24abs ↗pdf ↗

New method AM learns optimal vector fields for entire distribution sequences, matching OT.

problem Optimal Transport (OT) problem in generative modeling.
method Action Matching (AM) method learns optimal vector fields for a sequence of distributions.
result AM method achieves optimal transport by learning vector fields for entire distribution sequences.

New model leads to optimal test loss in sparse linear regression.

problem Sparse linear regression with low test loss despite interpolating training data.
method Developed a new parametrization of the model that combines benefits of ℓ1 and ℓ2 norms.
result Training via gradient descent leads to an interpolator with near-optimal test loss.

FFRK automatically extracts features for spatial interpolation without external variables.

problem Spatial interpolation challenges, especially nonstationarity and lack of explanatory variables.
method Feature-Free Regression Kriging (FFRK) method that extracts geospatial features.
result FFRK outperforms classical methods in predicting heavy metal concentrations.

This work proposes a novel method for interpolating ROMs without solving FEM models.

problem Interpolating ROMs for unseen parameter values without solving FEM models.
method Non-intrusive Space-Time POD interpolation on compact Stiefel manifolds.
result Robust ROMs derived for unseen parameter values with strong correlations to high-fidelity simulations.