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.
Paper explores new Kähler metrics from old, aiming to solve YTD conjecture.
Study on consistency of ML methods for moving objects in non-stationary environments.
New approach to extremal hyperbolic surfaces using NEC groups.
XR-Transformer accelerates XMC by recursively fine-tuning on multi-resolution objectives.
The goal in extreme multi-label classification is to learn a classifier which can assign a small subset of relevant labels to an instance from an extremely large set of target labels. Datasets in extreme classification exhibit a long tail of labels which have small number of positive training instances. In this work, w…
WEINCE improves contrastive learning by correcting softmax biases.
Study models extreme skew surges along French Atlantic coast.
Paper introduces adversarial lossy compression for video artifacts reduction.
We discuss the equivalence between the categories of certain ribbon graphs and subgroups of the modular group and use it to construct exponentially large families of not Hurwitz equivalent simple braid monodromy factorizations of the same element. As an application, we also obtain exponentially large families of {\…
New conditions ensure Dantzig-Wolfe relaxation matches rank-constrained optimization problems.
The thesis explores stability conditions and metrics in differential geometry.
ELM combines machine learning and feature engineering for anomalous diffusion detection.
Distillation improves simple models by approximating complex labels.
This paper optimizes object tracking on edge devices with small matrices.
BOtied optimizes multiple objectives using copulas and CDF indicators.
XR improves search advertising relevance predictions.
A simple baseline for extreme multi-label classification using random projections.
We propose an extension of the concept of Expected Improvement criterion commonly used in Kriging based optimization. We extend it for more complex Kriging models, e.g. models using derivatives. The target field of application are CFD problems, where objective function are extremely expensive to evaluate, but the theor…
Extreme multi-label text classification (XMTC) aims at tagging a document with most relevant labels from an extremely large-scale label set. It is a challenging problem especially for the tail labels because there are only few training documents to build classifier. This paper is motivated to better explore the semanti…
Unified tensor model disentangles object appearance factors.
Develops deep learning model for detecting anomalies in transportation data.
Optimizes neural architecture search to generate novel lightweight models.
Grasping is a complex process involving knowledge of the object, the surroundings, and of oneself. While humans are able to integrate and process all of the sensory information required for performing this task, equipping machines with this capability is an extremely challenging endeavor. In this paper, we investigate …
The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative solution to the problem of linear equations. Therefore, ELM offers the satisfying…
Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are …
Paper studies SERA's effectiveness in optimizing imbalanced regression models.
Investigates how extreme temperature events affect global equity portfolios.
A fundamental problem in computer vision is boundary estimation, where the goal is to delineate the boundary of objects in an image. In this paper, we propose a method which jointly incorporates geometric and topological information within an image to simultaneously estimate boundaries for objects within images with mo…
The study examines MCMC methods for arbitrary objectives and finds likelihood sharpness impacts performance and regularization.
In several real-world applications involving decision making under uncertainty, the traditional expected value objective may not be suitable, as it may be necessary to control losses in the case of a rare but extreme event. Conditional Value-at-Risk (CVaR) is a popular risk measure for modeling the aforementioned objec…
In this paper, a novel joint transmit power and resource allocation approach for enabling ultra-reliable low-latency communication (URLLC) in vehicular networks is proposed. The objective is to minimize the network-wide power consumption of vehicular users (VUEs) while ensuring high reliability in terms of probabilisti…
Extending Lévi-Civita's concept to non-quadratic spaces, this study finds extremal compatible linear connections.
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an extreme diversity space, such as \textit{person-behind-person} and \textit{car-behind…
Many Machine Learning algorithms, such as deep neural networks, have long been criticized for being "black-boxes"-a kind of models unable to provide how it arrive at a decision without further efforts to interpret. This problem has raised concerns on model applications' trust, safety, nondiscrimination, and other ethic…
Paper proposes COM-QEL to avoid overoptimistic solutions in offline optimization.
The objective in extreme multi-label learning is to train a classifier that can automatically tag a novel data point with the most relevant subset of labels from an extremely large label set. Embedding based approaches make training and prediction tractable by assuming that the training label matrix is low-rank and hen…
Bayesian optimization (BO) has been broadly applied to computational expensive problems, but it is still challenging to extend BO to high dimensions. Existing works are usually under strict assumption of an additive or a linear embedding structure for objective functions. This paper directly introduces a supervised dim…
The two-category with three-manifolds as objects, h-cobordisms as morphisms, and diffeomorphisms of these as two-morphisms, is extremely rich; from the point of view of classical physics it defines a nontrivial topological model for general relativity. A rather striking amount of work on pseudoisotopy theory [Hatcher, …
Circle graph complexes reveal link properties via Khovanov homology.
Improved Thompson Sampling for Bayesian Optimization.
New method improves object detection models for long-tailed datasets.
FedVision uses federated learning to improve object detection without transmitting data.
The minimization of convex objectives coming from linear supervised learning problems, such as penalized generalized linear models, can be formulated as finite sums of convex functions. For such problems, a large set of stochastic first-order solvers based on the idea of variance reduction are available and combine bot…
Similarity measure for Gaussian process predictive distributions.
We consider generic static spacetimes with Killing horizons and study properties of curvature tensors in the horizon limit. It is determined that the Weyl, Ricci, Riemann and Einstein tensors are algebraically special and mutually aligned on the horizon. It is also pointed out that results obtained in the tetrad adjust…
ExGAN generates realistic extreme samples using GANs and EVT.
The main aim of this paper is to inspect the properties of survey based on households inflation expectations, conducted by Reserve Bank of India. It is theorized that the respondents answers are exaggerated by extreme response bias. Latent class analysis has been hailed as a promising technique for studying measurement…
The study examines how hyperparameters affect prediction discrepancies in machine learning models.