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.
HASSO improves SO algorithms by dynamically tuning hyperparameters.
Much of the focus in machine learning research is placed in creating new architectures and optimization methods, but the overall loss function is seldom questioned. This paper interprets machine learning from a multi-objective optimization perspective, showing the limitations of the default linear combination of loss f…
Develops a new flexible grid trading model using ANN and SSO.
Non-exhaustive learning (NEL) is an emerging machine-learning paradigm designed to confront the challenge of non-stationary environments characterized by anon-exhaustive training sets lacking full information about the available classes.Unlike traditional supervised learning that relies on fixed models, NEL utilizes se…
An adaptive clustering algorithm learns from evolving data without manual tuning.
VAV method optimizes learning rate for faster, stable SGD convergence.
TopInG improves graph interpretability using persistent homology.
COME replaces entropy minimization to prevent model collapse.
Constrained optimization of high-dimensional numerical problems plays an important role in many scientific and industrial applications. Function evaluations in many industrial applications are severely limited and no analytical information about objective function and constraint functions is available. For such expensi…
The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing adversarial robustness. Nevertheless, min-max optimization beyond the purpose of AT has not been rigorously explored in the adversarial contex…
In this paper we first present a class of algorithms for training multi-level neural networks with a quadratic cost function one layer at a time starting from the input layer. The algorithm is based on the fact that for any layer to be trained, the effect of a direct connection to an optimized linear output layer can b…
Optimized testing of discrete distributions using predicted data.