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.
EML model tackles evolving features in online metric learning.
New approach for feature evolution in streaming data with limited storage.
Learning with streaming data has attracted much attention during the past few years. Though most studies consider data stream with fixed features, in real practice the features may be evolvable. For example, features of data gathered by limited-lifespan sensors will change when these sensors are substituted by new ones…
Improved detection of burnt areas in satellite images using evolved hyper-features.
TGAT learns node embeddings for evolving graphs, capturing both static and temporal features.
MadEvolve optimizes trading algorithms using LLMs, achieving significant improvements in feature generation and trading strategy optimization.
CDLEEDS detects local changes in evolving data streams for accurate feature attributions.
Neural networks' feature geometry evolves like discrete Ricci flow.
GraphKKE learns fixed-length feature vectors from time-evolving graphs of human microbiome data.
Learning with feature evolution studies the scenario where the features of the data streams can evolve, i.e., old features vanish and new features emerge. Its goal is to keep the model always performing well even when the features happen to evolve. To tackle this problem, canonical methods assume that the old features …
This paper introduces a novel technique to track structures in time evolving graphs. The method is based on a parameter free approach for three-dimensional co-clustering of the source vertices, the target vertices and the time. All these features are simultaneously segmented in order to build time segments and clusters…
Graph neural network using Beltrami flow for feature and topology evolution.
Conventional modeling approaches have found limitations in matching the increasingly detailed neural network structures and dynamics recorded in experiments to the diverse brain functionalities. On another approach, studies have demonstrated to train spiking neural networks for simple functions using supervised learnin…
Reduced order modeling of energetic materials using physics-aware neural networks.
As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep Learning algorithms, various successful feature learning techniques have evolved. I…
We consider the evolution of scale-free networks according to preferential attachment schemes and show the conditions for which the exponent characterizing the degree distribution is bounded by upper and lower values. Our framework is an agent model, presented in the context of economic networks of trades, which shows …
Develops a new GLM framework for claims reserving with adaptive estimation.
A tutorial on dynamic Laplacian for time-evolving data clusters.
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which can…
At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase. However, real-world problem is far more challenging because: i) new classes unseen in the training phase can appear when predicting; ii) discriminative features need to evolve when…
Detecting anomalies and discovering driving signals is an essential component of scientific research and industrial practice. Often the underlying mechanism is highly complex, involving hidden evolving nonlinear dynamics and noise contamination. When representative physical models and large labeled data sets are unavai…
STAD adapts models to evolving time-based data shifts.
Proposes standards for evaluating online machine learning methods in evolving data streams.
Adaptive XGBoost improves accuracy on evolving data streams by updating the ensemble dynamically.
Estimates mean dimension of neural networks to reveal interaction effects.
New algorithm improves fraud detection by analyzing financial account relationships.
Enhances machine learning for dynamic, interconnected entities.
Theory explains why neural nets better learn Calabi-Yau metrics.
SGD efficiently learns the XOR function with near-optimal sample complexity.
A simple model for unbalanced optimal transport captures key features.
Paper tackles continuous transfer learning with evolving target domains.
The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed network capacity that cannot adapt to rapidly changing environments. Deep evolving …
Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising. The recent trend in these areas calls for anomaly detection on time-evolving data with high-dimensional categorical features without labeled samples. Also, there is …
Modeling how individuals evolve over time is a fundamental problem in the natural and social sciences. However, existing datasets are often cross-sectional with each individual observed only once, making it impossible to apply traditional time-series methods. Motivated by the study of human aging, we present an interpr…
Satellite imagery and remote sensing provide explanatory variables at relatively high resolutions for modeling geospatial phenomena, yet regional summaries are often desirable for analysis and actionable insight. In this paper, we propose a novel method of inducing spatial aggregations as a component of the machine lea…
Automates feature extraction for IMU-based activity recognition.
Generalizes information theory to evolving belief.
Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.
In the paper, we consider the problem of link prediction in time-evolving graphs. We assume that certain graph features, such as the node degree, follow a vector autoregressive (VAR) model and we propose to use this information to improve the accuracy of prediction. Our strategy involves a joint optimization procedure …
Adaptive optimal control using value iteration (VI) initiated from a stabilizing policy is theoretically analyzed in various aspects including the continuity of the result, the stability of the system operated using any single/constant resulting control policy, the stability of the system operated using the evolving/ti…
New algorithm updates eigenvectors of evolving graphs efficiently.
This paper demonstrates the use of genetic algorithms for evolving: 1) a grandmaster-level evaluation function, and 2) a search mechanism for a chess program, the parameter values of which are initialized randomly. The evaluation function of the program is evolved by learning from databases of (human) grandmaster games…
While variational dropout approaches have been shown to be effective for network sparsification, they are still suboptimal in the sense that they set the dropout rate for each neuron without consideration of the input data. With such input-independent dropout, each neuron is evolved to be generic across inputs, which m…
Proves upper bounds for heat kernels evolving on manifolds.
CoMGNN models heterogeneous graphs with evolving nodes and edges.
Establishes Calderón-Zygmund inequalities on evolving Riemannian manifolds.
How do individuals accumulate wealth as they interact economically? We outline the consequences of a simple microscopic model in which repeated pairwise exchanges of assets between individuals build the wealth distribution of a population. This distribution is determined for generic exchange rules --- transactions that…
Graphs from features improve classification accuracy in tasks.