arXiv research

Paper introduces methods to adjust for missing data in causal inference.

Improved estimator reduces bias in statistical learning models.

New method corrects selection bias in post-selective inference for Group LASSO.

We quantify causal bias in continuous treatment settings.

Adjustment reduces bias in widely applicable Bayesian information criterion.

Mitigates confirmation bias in SSL by adjusting pseudo labels dynamically.

Two-stage TMLE reduces bias and improves efficiency in CRTs.

Peer effects, in which the behavior of an individual is affected by the behavior of their peers, are posited by multiple theories in the social sciences. Other processes can also produce behaviors that are correlated in networks and groups, thereby generating debate about the credibility of observational (i.e. nonexper…

New measure corrects news bias in NLP stock return forecasting.

SSMs have a built-in bias towards low-frequency components, which can be adjusted.

New method improves sampling from score-based models by correcting bias.

New method corrects seasonal Arctic sea ice predictions with probabilistic models.

NICE learns a representation to avoid bad controls in causal inference.

New method controls bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin.

Improves decision-making by correcting feature selection bias.

Bayesian method tackles M-Bias in causal inference.

Debiasing techniques can worsen gender bias in text classification, but a tweak improves both.

Unified framework suppresses model bias in semi-supervised learning with decoupled sampling control.

Recent work in fairness in machine learning has proposed adjusting for fairness by equalizing accuracy metrics across groups and has also studied how datasets affected by historical prejudices may lead to unfair decision policies. We connect these lines of work and study the residual unfairness that arises when a fairn…

With the development of high-throughput technologies, principal component analysis (PCA) in the high-dimensional regime is of great interest. Most of the existing theoretical and methodological results for high-dimensional PCA are based on the spiked population model in which all the population eigenvalues are equal ex…

Bias correction needed after deep learning regression training.

New method reduces model bias and variance by adjusting training sample weights based on label uncertainty.

Improves early stopping in deep networks by adjusting stepsizes.

When the in-sample Sharpe ratio is obtained by optimizing over a k-dimensional parameter space, it is a biased estimator for what can be expected on unseen data (out-of-sample). We derive (1) an unbiased estimator adjusting for both sources of bias: noise fit and estimation error. We then show (2) how to use the adjust…

Continuous Sweep improves binary quantifier performance.

Proposes a three-stage debiasing framework to improve out-of-distribution accuracy.

Proposes SD-KDE for density estimation using debiased kernel density with score-based adjustments.

Improves model fairness under changing bias between labels and sensitive groups.

This paper studies schemes to de-bias the Lasso in a linear model $y=Xβ+ε$ where the goal is to construct confidence intervals for $a_0^Tβ$ in a direction $a_0$, where $X$ has iid $N(0,Σ)$ rows. We show that previously analyzed propositions to de-bias the Lasso require a modification in order to enjoy efficiency in a f…

New tools for assessing and correcting bias in AI algorithms.

Medical deconfounder uses EHRs to estimate treatment effects without confounders.

Introduces recency bias to improve time-series forecasting.

A new algorithm CAP learns optimal policies from observational data with confounding bias and missing observations.

Balance corrects biased survey data for more accurate insights.

CARD detects treatment responders with machine learning and adjustment.

SEDA improves RLDA for high-dimensional data.

The paper addresses causal estimation for text data with apparent overlap violations.

We discovered secular trend bias in a drug effectiveness study for a recently approved drug. We compared treatment outcomes between patients who received the newly approved drug and patients exposed to the standard treatment. All patients diagnosed after the new drug's approval date were considered. We built a machine …

Semi-supervised learning improves QSAR model predictions for novel compounds.

Proposes stabilized weights for causal inference using isotonic calibration.

We prove the main rules of causal calculus (also called do-calculus) for i/o structural causal models (ioSCMs), a generalization of a recently proposed general class of non-/linear structural causal models that allow for cycles, latent confounders and arbitrary probability distributions. We also generalize adjustment c…

A RL framework selects features to balance bias and accuracy dynamically.

We consider large-scale studies in which it is of interest to test a very large number of hypotheses, and then to estimate the effect sizes corresponding to the rejected hypotheses. For instance, this setting arises in the analysis of gene expression or DNA sequencing data. However, naive estimates of the effect sizes …

Estimates causal effects with selection bias and confounding using regression.

New method learns from biased data, outperforming existing approaches.

DOVI improves reinforcement learning with offline data, reducing trial-and-error in critical scenarios.

Corrects bias in Cox models using AI-extracted covariates.

New models reduce regional inequality by adjusting exchange range and asset distribution bias.