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.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “MLA”

Part 1: Training Sets & ASG Transformsq-fin.CP

Develops a method to improve price prediction algorithms using macro-financial indicators.

problem Tackles issues with small data-sets in price predictive algorithms.

method Trains separate classifiers on datasets from various countries, develops a three-level MLA, and creates an ASG transform.

result Shows that a predictive algorithm using macro-financial indicators can outperform one using only price statistics.

price prediction macro-financial indicators data-science undergraduate project MLA

2017-12-15abs ↗pdf ↗

The Mirror Langevin Algorithm Converges with Vanishing Biascs.DS

Mirror Langevin Algorithm converges with zero bias.

problem Achieving convergence with zero bias in discrete-time sampling.

method Discretization of Mirror Langevin Diffusion and mean-square analysis.

result Mirror Langevin Algorithm converges with zero bias.

Mirror Langevin Algorithm Convergence Zero Bias Discrete Time Mean-Square Analysis

2021-09-24abs ↗pdf ↗

Modality for Scenario Analysis and Maximum Likelihood Allocationq-fin.RM

New method for risk allocation under multimodality of loss distribution.

problem Risk assessment under multimodal conditional loss distribution.

method Maximum Likelihood Allocation (MLA) and multimodality adjustment.

result Multimodality adjustment improves soundness of risk allocations.

risk allocation multimodality maximum likelihood modality severe scenarios

2020-05-06abs ↗pdf ↗

Training-Free Looped Transformerscs.LG

Training-free looped transformers improve model performance without additional training.

problem Improving model performance without additional training or fine-tuning.

method A lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional fine-tuning.

result Our method improves model performance across various model families.

transformers looping inference pretrained models performance improvement

2026-05-22abs ↗pdf ↗

Pushing the Limit of Unsupervised Learning for Ultrasound Image Artifact Removalcs.CV

Paper explores unsupervised learning for ultrasound image artifact removal.

problem Improving visual quality of ultrasound images from various artifacts.

method Inspired by optimal transport cycleGAN, unsupervised deep learning for artifact removal.

result Unsupervised learning method provides comparable results to supervised learning.

ultrasound imaging artifact removal unsupervised learning deep learning optimal transport

2020-06-26abs ↗pdf ↗

Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewardsmath.ST

New algorithm uses machine learning to predict rewards for decision-making problems.

problem Sequential decision-making under uncertainty with scarce online data.

method Machine Learning-Assisted Upper Confidence Bound (MLA-UCB) algorithm.

result Proves to improve cumulative regret even with biased surrogate rewards.

multi-armed bandits machine learning sequential decision-making surrogate rewards upper confidence bound

2025-06-20abs ↗pdf ↗