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.
i-cNRL learns network differences with interpretability.
MKA incorporates manifold geometry into kernel alignment for more robust representation comparison.
Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot trial based on a target image. We also deviate from traditional metric-le…
The concept of F-algebra and its representation can be extended to an arbitrary bundle. We define operations of fibered F-algebra in fiber. The paper presents the representation theory of of fibered F-algebra as well as a comparison of representation of F-algebra and of representation of fibered F-algebra.
Partial soft-matching distance improves neural representation comparison by allowing some neurons to remain unmatched.
We construct a new representation formula for indefinite improper affine spheres in terms of two para-holomorphic functions and study singularities which appear in this representation formula. As a result, it follows that cuspidal cross caps never appear as the singularities on indefinite improper affine spheres and so…
AUASE embeds dynamic networks with stability guarantees for node comparison.
Enhances time series comparison by simplifying warping paths.
We give a Weierstrass type representation for semi-discrete minimal surfaces in Euclidean 3-space. We then give explicit parametrizations of various smooth, semi-discrete and fully-discrete catenoids, determined from either variational or integrable systems principles. Finally, we state the shared properties that those…
We propose a new technique, Singular Vector Canonical Correlation Analysis (SVCCA), a tool for quickly comparing two representations in a way that is both invariant to affine transform (allowing comparison between different layers and networks) and fast to compute (allowing more comparisons to be calculated than with p…
We prove asymptotic faithfulness for the quantum mapping class group representation. This provides the first example of asymptotic faithfulness lying outside of the family. The methods used are generalized from the proof of asymptotic faithfulness for skein mapping class group represent…
The choice of making an intervention depends on its potential benefit or harm in comparison to alternatives. Estimating the likely outcome of alternatives from observational data is a challenging problem as all outcomes are never observed, and selection bias precludes the direct comparison of differently intervened gro…
We address the classical problem of hierarchical clustering, but in a framework where one does not have access to a representation of the objects or their pairwise similarities. Instead, we assume that only a set of comparisons between objects is available, that is, statements of the form "objects and are more …
New estimator corrects bias in CKA for sparsely sampled neurons.
Spider category comparison proves equivalence to Sikora's quotient category.
New methods compare neural network models using geometric and topological summaries.
Convolutional sparse representations are a form of sparse representation with a dictionary that has a structure that is equivalent to convolution with a set of linear filters. While effective algorithms have recently been developed for the convolutional sparse coding problem, the corresponding dictionary learning probl…
Assume we are given a set of items from a general metric space, but we neither have access to the representation of the data nor to the distances between data points. Instead, suppose that we can actively choose a triplet of items (A,B,C) and ask an oracle whether item A is closer to item B or to item C. In this paper,…
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on these latent representations, but the field still lacks a large-scale standard …
In recent years, large datasets of high-resolution mammalian neural images have become available, which has prompted active research on the analysis of gene expression data. Traditional image processing methods are typically applied for learning functional representations of genes, based on their expressions in these b…
Machine learning accelerates Lie algebra computations.
SEMASIA provides a large dataset of latent representations for model comparison.
We study the functor of points and the local functor of points (here called the Weil--Berezin functor) for smooth and holomorphic supermanifolds, providing characterization theorems and fully discussing the representability issues. In the end we examine applications to differential calculus including the transitivity t…
Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A si…
Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respe…
Discrete time random walks on a finite set naturally translate via a one-to-one correspondence to discrete Laplace operators. Typically, Ollivier curvature has been investigated via random walks. We first extend the definition of Ollivier curvature to general weighted graphs and then give a strikingly simple representa…
Researchers use Gysin sequence to show sl(N) homology of T(2,m) is cohomology of SU(N) representations.
By performing required evaluations, we show that in the Finsleroid-regular space the Landsberg-space condition just degenerates to the Berwald-space condition (at any dimension number ). Simple and clear expository representations are obtained. Due comparisons with the Finsleroid-Finsler space are indicated. Key…
Self-supervised and supervised methods learn similar intermediate visual representations but diverge in final layers.
This paper contains an overview of results for dynamic multivariate risk measures. We provide the main results of four different approaches. We will prove under which assumptions results within these approaches coincide, and how properties like primal and dual representation and time consistency in the different approa…
Enhances AI models with human feedback for noisy data.
We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into…
Deconfounds neural network representation similarity metrics to improve consistency and accuracy.
NGAT predicts long-term stock trends using graph attention networks.
Develops a new self-supervised learning method combining contrastive and non-contrastive approaches.
DIVE learns video representations even with missing data.
Learning distributed representations of documents has pushed the state-of-the-art in several natural language processing tasks and was successfully applied to the field of recommender systems recently. In this paper, we propose a novel content-based recommender system based on learned representations and a generative m…
Bispectral OT improves dataset comparison by preserving intrinsic coherence.
Emotions play an important role in people's life. Understanding and recognising is not only important for interpersonal communication, but also has promising applications in Human-Computer Interaction, automobile safety and medical research. This project focuses on extending the emotion recognition database, and traini…
Observational studies are rising in importance due to the widespread accumulation of data in fields such as healthcare, education, employment and ecology. We consider the task of answering counterfactual questions such as, "Would this patient have lower blood sugar had she received a different medication?". We propose …
We analyze (the harmonic map representation of) static solutions of the Einstein Equations in dimension three from the point of view of comparison geometry. We find simple monotonic quantities capturing sharply the influence of the Lapse function on the focussing of geodesics. This allows, in particular, a sharp estima…
Learning informative representations of data is one of the primary goals of deep learning, but there is still little understanding as to what representations a neural network actually learns. To better understand this, subspace match was recently proposed as a method for assessing the similarity of the representations …
We introduce GeNet, a method for shotgun metagenomic classification from raw DNA sequences that exploits the known hierarchical structure between labels for training. We provide a comparison with state-of-the-art methods Kraken and Centrifuge on datasets obtained from several sequencing technologies, in which dataset s…
Study compares atom representations in graph neural networks for molecular properties.
For a compact 3-manifold M with arbitrary (possibly empty) boundary, we give a parametrization of the set of conjugacy classes of boundary-unipotent representations of the fundamental group of M into SL(n,C). Our parametrization uses Ptolemy coordinates, which are inspired by coordinates on higher Teichmueller spaces d…
We establish what semi-discrete linear Weingarten surfaces with Weierstrass-type representations in -dimensional Riemannian and Lorentzian spaceforms are, confirming their required properties regarding curvatures and parallel surfaces, and then classify them. We then define and analyze their singularities. In partic…
We study the properties of nonlinear Backward Stochastic Differential Equations (BSDEs) driven by a Brownian motion and a martingale measure associated with a default jump with intensity process . We give a priori estimates for these equations and prove comparison and strict comparison theorems. These results ar…
A new semi-supervised ensemble algorithm called XGBOD (Extreme Gradient Boosting Outlier Detection) is proposed, described and demonstrated for the enhanced detection of outliers from normal observations in various practical datasets. The proposed framework combines the strengths of both supervised and unsupervised mac…