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

5 results for “transfer-exponent”

Covariate shift in nonparametric regression with Markovian designmath.ST

The paper analyzes covariate shift in nonparametric regression with Markovian data.

problem Covariate shift in regression problems with Markovian data.

method Extension of nonparametric convergence rates to Markovian dependence structures, using Hölder smoothness assumptions and similarity measures.

result Precise convergence rates for Nadaraya-Watson kernel estimators under specific Markovian conditions.

covariate shift nonparametric regression Markovian design Nadaraya-Watson kernel convergence rates

2023-07-17abs ↗pdf ↗

Classification Tree Pruning Under Covariate Shiftstat.ML

New method prunes classification trees for biased data.

problem Pruning classification trees in imbalanced training data.

method Optimal pruning procedure for inhomogeneous data.

result First efficient procedure for optimal pruning under covariate shift.

classification tree covariate shift pruning average discrepancy transfer-exponent

2023-05-07abs ↗pdf ↗

On the Value of Target Data in Transfer Learningcs.LG

Study examines the impact of target data in transfer learning.

problem Understanding the value of target data in transfer learning.

method Established minimax-rates for source and target sample sizes, introduced transfer exponents.

result Performance limits in transfer learning are captured by transfer exponents.

transfer learning target data source data minimax-rates discrepancy

2020-02-12abs ↗pdf ↗

Marginal Singularity, and the Benefits of Labels in Covariate-Shiftstat.ML

We present new minimax results that concisely capture the relative benefits of source and target labeled data, under covariate-shift. Namely, we show that the benefits of target labels are controlled by a transfer-exponent $γ$ that encodes how singular Q is locally w.r.t. P, and interestingly allows situations where tr…

2018-03-05abs ↗pdf ↗

New similarity measure for covariate shift improves nonparametric regression rates.

problem Improving nonparametric regression under covariate shift.

method Introducing a new similarity measure based on probability ratios.

result Shows a sharper rate of convergence compared to transfer exponent.

covariate shift nonparametric regression distribution mismatch Hölder continuous functions

2022-02-06abs ↗pdf ↗