arXiv research

Proposes a regularization method for unsupervised domain adaptation that aligns predictions with target data's top singular vectors.

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of learning temporal relationships and translation invariant representations, is u…

NLE embeds labels for domain adaptation with neural networks.

Graded bundles are a particularly nice class of graded manifolds and represent a natural generalisation of vector bundles. By exploiting the formalism of supermanifolds to describe Lie algebroids we define the notion of a weighted $A$-connection on a graded bundle. In a natural sense weighted $A$-connections are adapte…

ReCAP adapts to dynamic financial markets by segmenting and combining policy vectors.

Model user preferences for conversational LLMs using weak rewards.

SaR-SVM-STV improves hyperspectral image classification with shape-adaptive reconstruction and denoising.

We adapt the notions of stability of holomorphic vector bundles in the sense of Mumford-Takemoto and Hermitian-Einstein metrics in holomorphic vector bundles for canonically polarized framed manifolds, i.e. compact complex manifolds X together with a smooth divisor D such that K_X \otimes [D] is ample. It turns out tha…

This paper presents a generalization of symplectic geometry to a principal bundle over the configuration space of a classical field. This bundle, the vertically adapted linear frame bundle, is obtained by breaking the symmetry of the full linear frame bundle of the field configuration space, and it inherits a generaliz…

Photometric stereo is a method for estimating the normal vectors of an object from images of the object under varying lighting conditions. Motivated by several recent works that extend photometric stereo to more general objects and lighting conditions, we study a new robust approach to photometric stereo that utilizes …

In this study, we propose a new definition of multivariate conditional value-at-risk (MCVaR) as a set of vectors for discrete probability spaces. We explore the properties of the vector-valued MCVaR (VMCVaR) and show the advantages of VMCVaR over the existing definitions given for continuous random variables when adapt…

In this document we are going to derive the equations needed to implement a Variational Bayes i-vector extractor. This can be used to extract longer i-vectors reducing the risk of overfittig or to adapt an i-vector extractor from a database to another with scarce development data. This work is based on Patrick Kenny's …

New proof confirms periodic orbit conjecture for Eulerisable flows.

VOGP efficiently identifies Pareto optimal solutions in black-box vector optimization.

A new policy for contextual bandits adapts to reward vector shifts.

We present a local and constructive differential geometric description of finite-dimensional solvable and transitive Lie algebras of vector fields. We show that it implies a Lie's conjecture for such Lie algebras. Also infinite-dimensional analytical solvable and transitive Lie algebras of vector fields whose derivativ…

Computes derivatives of sections in vector bundles using Lie derivatives.

In this work, we design a machine learning based method, online adaptive primal support vector regression (SVR), to model the implied volatility surface (IVS). The algorithm proposed is the first derivation and implementation of an online primal kernel SVR. It features enhancements that allow efficient online adaptive …

Study on adaptivity constraints in linear contextual bandits with optimal design.

State-of-the-art speaker recognition systems comprise an x-vector (or i-vector) speaker embedding front-end followed by a probabilistic linear discriminant analysis (PLDA) backend. The effectiveness of these components relies on the availability of a large collection of labeled training data. In practice, it is common …

The paper explores linear generalised complex structures over vector bundles.

Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph structured data. However, as previous methods usually focus on learning embeddings for a single network, they can not learn representations transferable on multiple networks. Hence, it i…

We employ Riemannian jets which are adapted to the Riemannian geometry to obtain the existence-uniqueness of viscosity solutions to the $\infty(x)$-Laplace equation in Riemannian vector fields. Due to the differences between Euclidean jets and Riemannian jets, the Euclidean method of proof is not valid in this environm…

In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet few algorithms have been developed for setting the step-size automatically for TD learning. An important limitation of current methods is that…

Although Recurrent Neural Network (RNN) has been a powerful tool for modeling sequential data, its performance is inadequate when processing sequences with multiple patterns. In this paper, we address this challenge by introducing a novel mixture layer and constructing an adaptive RNN. The mixture layer augmented RNN (…

New algorithm resists contamination in high-dimensional regression with optimal performance.

This paper explores adaptive methods in over-parameterized linear regression.

Two algorithms address limited adaptivity in generalized linear contextual bandits.

IntSGD compresses SGD gradients without floats, converging as SGD.

In this paper, we present GASG21 (Grassmannian Adaptive Stochastic Gradient for $L_{2,1}$ norm minimization), an adaptive stochastic gradient algorithm to robustly recover the low-rank subspace from a large matrix. In the presence of column outliers, we reformulate the batch mode matrix $L_{2,1}$ norm minimization with…

CoDA adapts dynamics models to new physical systems by conditioning on context.

New calculus framework for vector bundles with metrics.

EVA adapts LoRA for faster, more efficient fine-tuning.

New approach for adaptive conformal inference using Blackwell's theory.

A new algorithm for personalized recommendations adapts to changing user interests.

MILDA uses unlabelled data to compute LDA projections.

We present Rotated Adaptive Tetra-iterated Quantizer (RATQ), a fixed-length quantizer for gradients in first order stochastic optimization. RATQ is easy to implement and involves only a Hadamard transform computation and adaptive uniform quantization with appropriately chosen dynamic ranges. For noisy gradients with al…

On the slit tangent manifold $TM^0$ of a Finsler space $(M,F)$ there are given some natural foliations as vertical foliation and some other fundamental foliations produced by the vertical and horizontal Liouville vector fields, see [A. Bejancu, H. R. Farran, Finsler Geometry and Natural Foliations on the Tangent Bundle…

Gradient boosting adapted for vector inputs.

State-of-the-art link prediction utilizes combinations of complex features derived from network panel data. We here show that computationally less expensive features can achieve the same performance in the common scenario in which the data is available as a sequence of interactions. Our features are based on social vec…

We give an inductive construction for irreducible Clifford systems on Euclidean vector spaces. We then discuss how this notion can be adapted to Riemannian manifolds, and outline some developments in octonionic geometry.

Given a finite collection of $C^1$ vector fields on a $C^2$ manifold which span the tangent space at every point, we consider the question of when there is locally a coordinate system in which these vector fields have a higher level of smoothness. For example, when is there a coordinate system in which the vector field…

Adaptive classifier optimizes high-dimensional data with spiked covariance structure.

In this paper we study the geometrical structures on the cotangent bundle using the notions of adapted tangent structure and regular vector fields. We prove that the dynamical covariant derivative on $T^{*}M$ fix a nonlinear connection for a given $\mathcal{J}$-regular vector field. Using the Legendre transformation in…

For a non-vanishing gradient-like vector field on a compact manifold $X^{n+1}$ with boundary, a discrete set of trajectories may be tangent to the boundary with reduced multiplicity $n$, which is the maximum possible. (Among them are trajectories that are tangent to $\partial X$ exactly $n$ times.) We prove a lower bou…

Due to the advantage of achieving a better performance under weak regularization, elastic net has attracted wide attention in statistics, machine learning, bioinformatics, and other fields. In particular, a variation of the elastic net, adaptive elastic net (AEN), integrates the adaptive grouping effect. In this paper,…

We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different, standard supervised learning methods perform poorly. Zero-shot domain adaptation attemp…

The present paper proposes generalized Gaussian kernel adaptive filtering, where the kernel parameters are adaptive and data-driven. The Gaussian kernel is parametrized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of the scalar width parameter. These…