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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “under-training”

Using Under-trained Deep Ensembles to Learn Under Extreme Label Noisecs.LG

New approach uses under-trained deep ensembles to learn from noisy labels.

problem Improper labelling hinders reliable generalization in supervised learning.

method Under-trained deep ensembles, each trained on a subset of data, combine to form better labels.

result Significant performance improvement in accuracy and kappa for noisy label tasks.

label noise deep ensembles under-training healthcare sleep apnea

2020-09-23abs ↗pdf ↗

Deep Hedging under Rough Volatilityq-fin.CP

Investigates deep hedging under rough volatility models.

problem Performance of deep hedging framework under non-Markovian conditions.

method Analysis of rough volatility models, use of parsimonious network architectures.

result Parsimonious network architectures can capture non-Markovian time-series.

Deep Hedging Rough Volatility Non-Markovian Parsimonious Networks P&L Distributions

2021-02-03abs ↗pdf ↗

Finite size corrections for neural network Gaussian processescs.LG

There has been a recent surge of interest in modeling neural networks (NNs) as Gaussian processes. In the limit of a NN of infinite width the NN becomes equivalent to a Gaussian process. Here we demonstrate that for an ensemble of large, finite, fully connected networks with a single hidden layer the distribution of ou…

2019-08-27abs ↗pdf ↗

NeuPL: Neural Population Learningcs.AI

NeuPL learns diverse policies in strategy games efficiently.

problem Iterative training of policies in strategy games leads to under-trained good-responses and wasteful repetition.

method NeuPL uses a single conditional model to represent a population of policies, offering convergence guarantees and transfer learning.

result NeuPL achieves better performance and efficiency across various domains, enabling access to novel strategies.

Neural Population Learning strategy games policy population transfer learning convergence guarantees

2022-02-15abs ↗pdf ↗

Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learningcs.LG

Paper introduces MVS to detect non-Markovian observations in reinforcement learning.

problem Real-world sensors violate Markov property, leading to suboptimal reinforcement learning performance.

method Uses prediction-based Markov Violation Score (MVS) combining random forest and ridge regression.

result MVS detects non-Markovian structure in observation trajectories, quantifying its impact.

Reinforcement Learning Markov Property Non-Markovian Observations Prediction Error Random Forest

2026-03-28abs ↗pdf ↗

Impact of Data Breadth and Depth on Performance of Siamese Neural Network Model: Experiments with Three Keystroke Dynamic Datasetscs.LG

Study explores how dataset breadth and depth affect Siamese Neural Network performance.

problem Impact of dataset breadth and depth on Siamese Neural Network performance.

method Experiments with three keystroke datasets varying breadth and depth factors.

result Increasing dataset breadth improves model performance, while depth's impact varies by dataset type.

Siamese Neural Networks Behavioral Biometrics Keystroke Dynamics Dataset Breadth Dataset Depth

2025-01-10abs ↗pdf ↗