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.
Differentially private graph learning via bounded sensitivity PPR.
This work analyzes PPR-based node embeddings and their topological information.
Novel compression method preserves privacy while reducing communication costs.
Estimates mode of discrete distributions with fewer samples.
The paper provides statistical theory and intuition for personalized PageRank (called "PPR"): a popular technique that samples a small community from a massive network. We study a setting where the entire network is expensive to obtain thoroughly or to maintain, but we can start from a seed node of interest and "crawl"…
New algorithm improves fraud detection by analyzing financial account relationships.
Despite the overwhelming success of the existing Social Networking Services (SNS), their centralized ownership and control have led to serious concerns in user privacy, censorship vulnerability and operational robustness of these services. To overcome these limitations, Distributed Social Networks (DSN) have recently b…
The paper analyzes oversmoothing in GNNs and quantifies the effects of mixing and denoising.
We investigate the theoretical limits of pipeline parallel learning of deep learning architectures, a distributed setup in which the computation is distributed per layer instead of per example. For smooth convex and non-convex objective functions, we provide matching lower and upper complexity bounds and show that a na…
The paper finds Koopman invariant subspaces using personalized PageRank.
Deep learning is a form of machine learning for nonlinear high dimensional pattern matching and prediction. By taking a Bayesian probabilistic perspective, we provide a number of insights into more efficient algorithms for optimisation and hyper-parameter tuning. Traditional high-dimensional data reduction techniques, …
FREDE efficiently embeds graphs using linear space and guarantees quality.
Graph embedding learns low-dimensional representations for nodes in a graph and effectively preserves the graph structure. Recently, a significant amount of progress has been made toward this emerging research area. However, there are several fundamental problems that remain open. First, existing methods fail to preser…
Novel graph-based method detects R-peaks in noisy ECG signals without preprocessing.
Combines deep and statistical learning for structured data.