On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “random-X”

Revisiting Optimism and Model Complexity in the Wake of Overparameterized Machine Learningstat.ML

New complexity measures explain overparameterized models' surprising performance.

problem Understanding why overparameterized models generalize well despite fitting training data.

method Reinterpreting classical degrees of freedom in a random-X setting.

result Random-X prediction error better explains generalization in complex models.

overparameterization degrees of freedom generalization machine learning random-X

2024-10-02abs ↗pdf ↗

Optimal ridge regularization revisitedcs.LG

Optimal ridge regularization computed iteratively from generative parameters.

problem Finding the optimal ridge regularization strength for linear regression.

method Iterative procedure to compute optimal regularization strength numerically.

result The proposed procedure attains near-optimal generalization across various conditions.

ridge regression optimal regularization iterative procedure generalization synthetic data

2026-05-27abs ↗pdf ↗

Backward Deep BSDE Methods and Applications to Nonlinear Problemsq-fin.CP

Paper presents a new backward deep BSDE method for solving nonlinear FBSDE problems.

problem Nonlinear Forward Backward Stochastic Differential Equations (FBSDE) with terminal conditions.

method Backward deep BSDE method applied to FBSDE with nonlinear generators and random initial conditions.

result Derives exact and Taylor-based approximations for time-stepping nonlinear BSDEs.

Backward Deep BSDE Nonlinear FBSDE Taylor Approximation Random Initial Conditions High Dimensions

2020-06-13abs ↗pdf ↗