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.
Model predicts competition between similar products in sales.
Indirect competition emerged from the complex organization of human societies, and knowledge of the existing network topology may aid in developing effective strategies for success. Here, we propose an agent-based model of competition with systems co-existing in a `small-world' social network. We show that within the r…
Kaggle competitions offer valuable insights for business forecasting.
Algorithm for decentralized competition among adaptive agents.
This work bridges competitive learning with gradient-based learning for faster feature extraction.
New algorithm for competing influence spread in unknown networks.
Paper studies competitive networks where teams aim to minimize their own objectives, adapting to each other's strategies.
A competition increases financial transaction models' robustness against attacks.
This work tackles representation learning by introducing stochastic competition-based activations.
We propose a simple dynamical model of the formation of production networks among monopolistically competitive firms. The model subsumes the standard general equilibrium approach à la Arrow-Debreu but displays a wide set of potential dynamic behaviors. It robustly reproduces key stylized facts of firms' demographics. O…
Combines gradient-based and competitive learning for unsupervised feature extraction.
GNNRank uses neural networks to learn global rankings from competition match data.
AlgoPerf competition evaluates neural network training speed-ups.
Deep network learns Obstacle Tower challenge without human demonstrations.
Presented are two neural network architectures for convex functions, demonstrating competitive performance.
We address the issue of the factors driving startup success in raising funds. Using the popular and public startup database Crunchbase, we explicitly take into account two extrinsic characteristics of startups: the competition that the companies face, using similarity measures derived from the Word2Vec algorithm, as we…
FDN improves probabilistic regressors' adaptability to distribution shifts.
This paper uses NARX neural networks for macroeconomic forecasting and goal setting.
Competition has been introduced in the electricity markets with the goal of reducing prices and improving efficiency. The basic idea which stays behind this choice is that, in competitive markets, a greater quantity of the good is exchanged at a lower and a lower price, leading to higher market efficiency. Electricity …
We propose a new way of constructing invertible neural networks by combining simple building blocks with a novel set of composition rules. This leads to a rich set of invertible architectures, including those similar to ResNets. Inversion is achieved with a locally convergent iterative procedure that is parallelizable …
Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning tasks, while making pr…
We train an enhanced deep convolutional neural network in order to identify eight cardiac abnormalities from the standard 12-lead electrocardiograms (ECGs) using the dataset of 14000 ECGs. Instead of straightforwardly applying an end-to-end deep learning approach, we find that deep convolutional neural networks enhance…
This work makes vision networks more interpretable by identifying key neurons.
Paper proposes combining GAM and DNN for accurate peak demand estimation from lower-resolution data.
Recurrent Neural Networks (RNN) have become competitive forecasting methods, as most notably shown in the winning method of the recent M4 competition. However, established statistical models such as ETS and ARIMA gain their popularity not only from their high accuracy, but they are also suitable for non-expert users as…
Researchers improved Minecraft game performance using imitation learning.
With the advent of Big Data, nowadays in many applications databases containing large quantities of similar time series are available. Forecasting time series in these domains with traditional univariate forecasting procedures leaves great potentials for producing accurate forecasts untapped. Recurrent neural networks …
In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the st…
The aim of this work is to enable inference of deep networks that retain high accuracy for the least possible model complexity, with the latter deduced from the data during inference. To this end, we revisit deep networks that comprise competing linear units, as opposed to nonlinear units that do not entail any form of…
Machine learning for ASD diagnosis using morphological MRI networks.
We propose a novel learning method for multilayered neural networks which uses feedforward supervisory signal and associates classification of a new input with that of pre-trained input. The proposed method effectively uses rich input information in the earlier layer for robust leaning and revising internal representat…
HMCNAS generates competitive neural architectures without human-defined parameters.
Pakistan examines digital mergers using traditional competition tools.
This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes is used to dynamically set the learning rate of the network through the trainin…
User smeznar achieved 8th place in PGDL by predicting generalization of deep learning models.
Gradient-free method improves predictive accuracy for probabilistic models.
The design of neural network architectures for a new data set is a laborious task which requires human deep learning expertise. In order to make deep learning available for a broader audience, automated methods for finding a neural network architecture are vital. Recently proposed methods can already achieve human expe…
Layer fusion reduces deep neural network layers with minimal loss in accuracy.
Study copyright's impact on creative industries using AI-generated fonts.
New model improves deep learning robustness against adversarial attacks.
Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use residual, parallel structures and concatenation block between shallow and deep features …
Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.
Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to degradations, that make the task challenging. In the current work a deep neural network architecture …
Study shows competition feedback can make ML predictors biased towards specific user groups.
In this study, we propose the integration of competitive learning into convolutional neural networks (CNNs) to improve the representation learning and efficiency of fine-tuning. Conventional CNNs use back propagation learning, and it enables powerful representation learning by a discrimination task. However, it require…
Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations. It relies on querying a distribution over functions defined by a relatively cheap surrogate model. An accurate model for this distribution over functions is critical to the effectiveness of the approac…
This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelih…
Deep learning detects bid-rigging cartels with high accuracy.