arXiv research

Diffusion models adapt to low-dimensional data regardless of coefficient choices.

Paper tests if beta coefficients in AMF model are consistent over time.

AER dynamically adjusts entropy regularization for better LLM reinforcement learning.

Adaptive transfer learning model for varying mechanisms across domains.

Framework uses deep learning and statistical models to solve PDEs with discontinuous coefficients.

This paper presents a novel adaptive-filter approach for predicting assets on the stock markets. Concepts are introduced here, which allow understanding this method and computing of the corresponding forecast. This approach is applied, as an example, through the prediction over the actual valuation of the PETR3 shares …

Recent breakthrough results in compressed sensing (CS) have established that many high dimensional objects can be accurately recovered from a relatively small number of non- adaptive linear projection observations, provided that the objects possess a sparse representation in some basis. Subsequent efforts have shown th…

Proposes a new ridge estimator for smooth covariates with adaptive centering.

A new method reduces bias in adaptive Lasso estimates.

Paper proposes ABDR for convex subspace clustering with adaptive block diagonal representation.

Paper develops a hybrid DNN approach for RUL prediction with adaptive drift.

Study shows polystability of tangent and canonical sheaves on Kähler-Einstein log Fano pairs.

We propose two sparsity-aware normalized subband adaptive filter (NSAF) algorithms by using the gradient descent method to minimize a combination of the original NSAF cost function and the l1-norm penalty function on the filter coefficients. This l1-norm penalty exploits the sparsity of a system in the coefficients upd…

New framework discovers PDEs from sparse, noisy data.

Develops a chain-level model for Chas-Sullivan products using Morse theory with differential graded coefficients.

This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data. This is achieved using a mixture model where the mixing coefficients are modeled by a Dirichlet process, allowing us to integrate over the coefficients when performing inference. Critically, this then allows us t…

We adapt Thistlethwaite's alternating tangle decomposition of a knot diagram to identify the potential extreme terms in its bracket polynomial, and give a simple combinatorial calculation for their coefficients, based on the intersection graph of certain chord diagrams.

Basis adaptation in Homogeneous Chaos spaces rely on a suitable rotation of the underlying Gaussian germ. Several rotations have been proposed in the literature resulting in adaptations with different convergence properties. In this paper we present a new adaptation mechanism that builds on compressive sensing algorith…

This paper improves neural network generalization by dynamically learning kernel parameters.

This paper establishes non-asymptotic oracle inequalities for the prediction error and estimation accuracy of the LASSO in stationary vector autoregressive models. These inequalities are used to establish consistency of the LASSO even when the number of parameters is of a much larger order of magnitude than the sample …

Enhances CEV model pricing with high-order scheme and adaptive time stepping.

Proves surgery exact triangle for monopole Floer homology over integers.

New adaptive models improve prediction accuracy with missing data.

New robust estimator improves variable selection and coefficient estimation in linear regression with heavy-tailed errors and outliers.

Protocol for constructing tailored evaluation datasets for semantic models.

We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution $ρ$ in $\mathbb{R}^D$, that is nearly supported on a $d$-dimensional set $\mathcal{M}$ - for example supported on a $d$-dimensional Riemannian manifold. Geometric Multi-Resolution Analysis (GM…

ARO overfits by making constraints dependent on uncertainty, leading to brittleness.

New robust estimator for high-dimensional data with outliers and leverage points.

In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the $\ell^1$ norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…

We consider the generic regularized optimization problem $\hat{\mathsfβ}(λ)=\arg \min_βL({\sf{y}},X{\sfβ})+λJ({\sfβ})$. Efron, Hastie, Johnstone and Tibshirani [Ann. Statist. 32 (2004) 407--499] have shown that for the LASSO--that is, if $L$ is squared error loss and $J(β)=\|β\|_1$ is the $\ell_1$ norm of $β$--the opti…

New complexity measure for interactive learning reduces regret to near-optimal levels.

The Newman-Penrose-Perjes formalism is applied to smooth contact structures on riemannian 3-manifolds. In particular it is shown that a contact 3-manifold admits an adapted riemannian metric if and only if it admits a metric with a divergence-free, constantly twisting, geodesic congruence. The shear of this congruence …

Neural GARCH models financial time series with time-varying coefficients.

Graph neural networks can be adapted to new graphs with a limit object called graphon NNs.

We consider the optimal control problem for a linear conditional McKean-Vlasov equation with quadratic cost functional. The coefficients of the system and the weigh-ting matrices in the cost functional are allowed to be adapted processes with respect to the common noise filtration. Semi closed-loop strategies are intro…

Latent FxLMS accelerates ANC by adapting along low-dimensional filter weights.

Paper adapts DDPM to low-dimensional structures in image distributions.

Locally adaptive interpretable regression improves linear regression's predictability.

MLShrink integrates machine learning with wavelet shrinkage for denoising.

The paper proves conditions for the existence of small Urysohn width hypersurfaces in manifolds with positive scalar curvature.

Global information is essential for dense prediction problems, whose goal is to compute a discrete or continuous label for each pixel in the images. Traditional convolutional layers in neural networks, initially designed for image classification, are restrictive in these problems since the filter size limits their rece…

Bayesian posterior contraction rates improve with decreasing tails

Given a compact smooth manifold $M$ with non-empty boundary and a Morse function, a pseudo-gradient Morse-Smale vector field adapted to the boundary allows one to build a Morse complex whose homology is isomorphic to the (absolute or relative to the boundary) homology of $M$ with integer coefficients. Our approach simp…

Study heat content in sub-Riemannian structures, proving asymptotic series existence and coefficients.

We present a theoretical and empirical study of the gradient dynamics of overparameterized shallow ReLU networks with one-dimensional input, solving least-squares interpolation. We show that the gradient dynamics of such networks are determined by the gradient flow in a non-redundant parameterization of the network fun…

New algorithm improves stability and efficiency of neural network training.

Various factorization-based methods have been proposed to leverage second-order, or higher-order cross features for boosting the performance of predictive models. They generally enumerate all the cross features under a predefined maximum order, and then identify useful feature interactions through model training, which…

We adapt to an infinite dimensional ambient space E.R. Reifenberg's epiperimetric inequality and a quantitative version of D. Preiss' second moments computations to establish that the set of regular points of an almost mass minimizing rectifiable $G$ chain in $\ell_2$ is dense in its support, whenever the group $G$ of …