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.
Neighbor embeddings balance attraction and repulsion to visualize data.
New method improves sample diversity and efficiency from complex distributions.
ARS visualization improves t-SNE dynamics with tunable attraction and repulsion.
New algorithm detects anomalies by forcing samples to displace mass in low-density regions.
We apply the potential force estimation method to artificial time series of market price produced by a deterministic dealer model. We find that dealers' feedback of linear prediction of market price based on the latest mean price changes plays the central role in the market's potential force. When markets are dominated…
We propose a unifying view of two different Bayesian inference algorithms, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) and Stein Variational Gradient Descent (SVGD), leading to improved and efficient novel sampling schemes. We show that SVGD combined with a noise term can be framed as a multiple chain SG-MCM…
Feature normalization prevents collapse in non-contrastive learning dynamics.
In earlier work, we provided a general description of the forces of attraction and repulsion, encountered by two parallel vertical plates of infinite extent and of possibly differing materials, when partially immersed in an infinite liquid bath and subject to surface tension forces. In the present study, we examine som…
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods. However, we observed th…
Paper improves particle variational inference by optimizing generalization error bound.
In the present work, torsion energy is defined. Its law of conservation is given. It is shown that this type of energy gives rise to a repulsive force which can be used to interpret supernovae type Ia observations, and consequently the accelerating expansion of the Universe. This interpretation is a pure geometric one …
CAMEL embeds data into a manifold using curvature-augmented forces.
The possibility that price dynamics is affected by its distance from a moving average has been recently introduced as new statistical tool. The purpose is to identify the tendency of the price dynamics to be attractive or repulsive with respect to its own moving average. We consider a number of tests for various models…
This work proposes a novel method for estimating the influence that unknown static objects might have over mobile agents. Since the motion of agents can be affected by the presence of fixed objects, it is possible use the information about trajectories deviations to infer the presence of obstacles and estimate the forc…
Study shows global invertibility in nonlinear elasticity with vanishing self-repulsion term.
Repulsive ensembles improve uncertainty estimates in PINNs for differential equations.
Enhances contrastive learning for better representation learning on wild images.
A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly trained models, the algorithm evaluates pointwise fitness of individual nodes in neural network. Labeled training data is randomly sampled an…
Repulsive deep ensembles improve diversity and Bayesian inference.
Computer experiments reveal complex knots that don't simplify.
FoRDE uses input gradients to improve neural network ensembles.
Study identifies stable configurations of intertwined threads with repulsive interactions.
This work shows dimension regularization can replace skip-gram negative sampling for graph embeddings, improving efficiency and performance.
Randomized feature models learn interaction kernels from agent paths.
New solutions found for elliptic systems with mixed couplings.
Shielded LMC samples from non-convex spaces with repulsive drift.
New approach improves multi-head attention by making heads less similar.
Research examines correlations of complex logarithms of lattice points, showing level repulsion and Poissonian behavior.
Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum mean discrepancy (MMD) as the loss function for GAN and makes two contributions. F…
We introduce a binary embedding framework, called Proximity Preserving Code (PPC), which learns similarity and dissimilarity between data points to create a compact and affinity-preserving binary code. This code can be used to apply fast and memory-efficient approximation to nearest-neighbor searches. Our framework is …
RePULSe improves language model alignment by reducing undesired outputs without sacrificing overall performance.
The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we prove that such repulsive sampling schemes lowers the variance of the gradient est…
NucleusDiff models atomic nuclei interactions to prevent separation violations in drug design.
This paper introduces repulsive Monte Carlo methods for computing the sliced Wasserstein distance.
We consider the problem of diversity enhancing clustering, i.e, developing clustering methods which produce clusters that favour diversity with respect to a set of protected attributes such as race, sex, age, etc. In the context of fair clustering, diversity plays a major role when fairness is understood as demographic…
The paper studies Möbius energy gradient of helix pairs and finds limiting behavior as coiling ratio increases.
New Gaussian DPP model reveals directionality in data.
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure…
Domain adaptation is transfer learning which aims to generalize a learning model across training and testing data with different distributions. Most previous research tackle this problem in seeking a shared feature representation between source and target domains while reducing the mismatch of their data distributions.…
A new model improves clustering by reducing redundancy in mixture of local EPCAs.
The t-distributed Stochastic Neighbor Embedding (tSNE) algorithm has become in recent years one of the most used and insightful techniques for the exploratory data analysis of high-dimensional data. tSNE reveals clusters of high-dimensional data points at different scales while it requires only minimal tuning of its pa…
The study examines correlations of logarithms of integers at different scalings.
The paper proves a Lojasiewicz inequality for maps from the 2-sphere to itself.
Paper proposes ARB-Loss to improve classification precision in imbalanced datasets.
Determinantal point processes (DPPs) are random point processes well-suited for modeling repulsion. In machine learning, the focus of DPP-based models has been on diverse subset selection from a discrete and finite base set. This discrete setting admits an efficient sampling algorithm based on the eigendecomposition of…
This paper presents a model of capital accumulation for a large number of heterogenous producer-consumers in an exchange space in which interactions depend on agents' positions. Each agent is described by his production, consumption, stock of capital, as well as the position he occupies in this abstract space. Each age…
Study on capillarity minimizers with nonlocal repulsion and gravity, proving existence and nonexistence.
Spectral portfolio theory links neural networks to wealth dynamics via SGD weight matrices.