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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Flip-noise”

The Privacy Subsidy in Glosten-Milgrom: Bid-Ask Spread and Welfare under Flip-Noise Direction Observationcs.GT

Privacy subsidy found in market trading with noisy direction signals.

problem Analyzing welfare and bid-ask spread in a market with privacy mechanisms.

method Closed-form derivation of bid-ask spread and welfare under flip-noise direction observation.

result Privacy subsidy of

μηΔ

from liquidity pool to traders, robust across models.

Privacy subsidy Glosten-Milgrom model Flip-noise Sequential trading Differential privacy

2026-05-19abs ↗pdf ↗

Benign Overfitting for Two-layer ReLU Convolutional Neural Networkscs.LG

Two-layer ReLU networks can overfit without harm, study finds.

problem Understanding when and how two-layer ReLU networks can overfit without harming generalization.

method Established algorithm-dependent risk bounds for two-layer ReLU convolutional neural networks with label-flipping noise.

result Gradient descent-trained ReLU networks can achieve near-zero training loss and Bayes optimal test risk.

ReLU networks benign overfitting two-layer neural networks gradient descent label-flipping noise

2023-03-07abs ↗pdf ↗

Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Contextcs.LG

Transformers trained on random classification tasks generalize well and can overfit without error.

problem Understanding how transformers generalize and overfit in-context.

method Analysis of implicit regularization during gradient descent training.

result Transformers can overfit without error and still generalize well.

transformers gradient descent classification generalization overfitting

2024-10-02abs ↗pdf ↗

Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classificationstat.ML

Ridge regression shows different behaviors in binary classification with noisy labels.

problem Binary classification with noisy labels and anisotropic cluster distributions.

method Investigation of ridge regression behavior in overparameterized settings with label noise.

result Ridge regression exhibits qualitatively different behavior based on the scale of cluster mean vectors and covariance matrices.

ridge regression binary classification label noise overparameterization anisotropic clusters

2025-03-11abs ↗pdf ↗