Search Results for author: Jelena Bradic

Found 34 papers, 3 papers with code

Adaptive Split Balancing for Optimal Random Forest

no code implementations17 Feb 2024 Yuqian Zhang, Weijie Ji, Jelena Bradic

While random forests are commonly used for regression problems, existing methods often lack adaptability in complex situations or lose optimality under simple, smooth scenarios.

feature selection

The Decaying Missing-at-Random Framework: Doubly Robust Causal Inference with Partially Labeled Data

no code implementations22 May 2023 Yuqian Zhang, Abhishek Chakrabortty, Jelena Bradic

Notably, we relax the need for a positivity condition, commonly required in the missing data literature, and allow uniform decay of labeling propensity scores with sample size, accommodating faster growth of unlabeled data.

Causal Inference Partially Labeled Datasets +1

Dynamic treatment effects: high-dimensional inference under model misspecification

no code implementations12 Nov 2021 Yuqian Zhang, Weijie Ji, Jelena Bradic

This paper introduces a new approach by proposing novel, robust estimators for both treatment assignments and outcome models.

High-dimensional Inference for Dynamic Treatment Effects

no code implementations10 Oct 2021 Jelena Bradic, Weijie Ji, Yuqian Zhang

Estimating dynamic treatment effects is a crucial endeavor in causal inference, particularly when confronted with high-dimensional confounders.

Causal Inference Vocal Bursts Intensity Prediction

Double Robust Semi-Supervised Inference for the Mean: Selection Bias under MAR Labeling with Decaying Overlap

1 code implementation14 Apr 2021 Yuqian Zhang, Abhishek Chakrabortty, Jelena Bradic

Apart from a moderate-sized labeled data, L, the SS setting is characterized by an additional, much larger sized, unlabeled data, U.

Causal Inference Selection bias

Comments on Leo Breiman's paper 'Statistical Modeling: The Two Cultures' (Statistical Science, 2001, 16(3), 199-231)

no code implementations21 Mar 2021 Jelena Bradic, Yinchu Zhu

Breiman challenged statisticians to think more broadly, to step into the unknown, model-free learning world, with him paving the way forward.

Dynamic covariate balancing: estimating treatment effects over time with potential local projections

no code implementations1 Mar 2021 Davide Viviano, Jelena Bradic

We propose a method that allows for (i) treatments to be assigned dynamically over time based on high-dimensional covariates, past outcomes and treatments; (ii) outcomes and time-varying covariates to depend on treatment trajectories; (iii) heterogeneity of treatment effects.

regression

Learning to Combat Noisy Labels via Classification Margins

no code implementations1 Feb 2021 Jason Z. Lin, Jelena Bradic

A deep neural network trained on noisy labels is known to quickly lose its power to discriminate clean instances from noisy ones.

Classification General Classification +1

DeepHazard: neural network for time-varying risks

1 code implementation26 Jul 2020 Denise Rava, Jelena Bradic

Our approach is tailored for a wide range of continuous hazards forms, with the only restriction of being additive in time.

Survival Analysis Survival Prediction

Detangling robustness in high dimensions: composite versus model-averaged estimation

no code implementations12 Jun 2020 Jing Zhou, Gerda Claeskens, Jelena Bradic

We find, however, that model-averaged and composite quantile estimators often outperform least-squares methods, even in the case of Gaussian model noise.

Vocal Bursts Intensity Prediction

Fair Policy Targeting

no code implementations25 May 2020 Davide Viviano, Jelena Bradic

One of the major concerns of targeting interventions on individuals in social welfare programs is discrimination: individualized treatments may induce disparities across sensitive attributes such as age, gender, or race.

Fairness

Censored Quantile Regression Forest

no code implementations8 Jan 2020 Alexander Hanbo Li, Jelena Bradic

Random forests are powerful non-parametric regression method but are severely limited in their usage in the presence of randomly censored observations, and naively applied can exhibit poor predictive performance due to the incurred biases.

regression

Minimax Semiparametric Learning With Approximate Sparsity

no code implementations27 Dec 2019 Jelena Bradic, Victor Chernozhukov, Whitney K. Newey, Yinchu Zhu

This paper is about the feasibility and means of root-n consistently estimating linear, mean-square continuous functionals of a high dimensional, approximately sparse regression.

regression

Estimating Treatment Effect under Additive Hazards Models with High-dimensional Covariates

no code implementations29 Jun 2019 Jue Hou, Jelena Bradic, Ronghui Xu

Estimating causal effects for survival outcomes in the high-dimensional setting is an extremely important topic for many biomedical applications as well as areas of social sciences.

Management valid +1

Sparsity Double Robust Inference of Average Treatment Effects

no code implementations2 May 2019 Jelena Bradic, Stefan Wager, Yinchu Zhu

Many popular methods for building confidence intervals on causal effects under high-dimensional confounding require strong "ultra-sparsity" assumptions that may be difficult to validate in practice.

Statistics Theory Econometrics Methodology Statistics Theory

Synthetic learner: model-free inference on treatments over time

no code implementations2 Apr 2019 Davide Viviano, Jelena Bradic

Understanding the effect of a particular treatment or a policy pertains to many areas of interest, ranging from political economics, marketing to healthcare.

counterfactual Marketing +1

Censored Quantile Regression Forests

1 code implementation8 Feb 2019 Alexander Hanbo Li, Jelena Bradic

Random forests are powerful non-parametric regression method but are severely limited in their usage in the presence of randomly censored observations, and naively applied can exhibit poor predictive performance due to the incurred biases.

regression

High-dimensional semi-supervised learning: in search for optimal inference of the mean

no code implementations2 Feb 2019 Yuqian Zhang, Jelena Bradic

We provide a high-dimensional semi-supervised inference framework focused on the mean and variance of the response.

Testability of high-dimensional linear models with non-sparse structures

no code implementations26 Feb 2018 Jelena Bradic, Jianqing Fan, Yinchu Zhu

Uniform non-testability identifies a collection of alternatives such that the power of any test, against any alternative in the group, is asymptotically at most equal to the nominal size.

Feature Correlation regression +1

Fixed effects testing in high-dimensional linear mixed models

no code implementations14 Aug 2017 Jelena Bradic, Gerda Claeskens, Thomas Gueuning

A robust matching moment construction is used for creating a test that adapts to the size of the model sparsity.

Decision Making Marketing +2

Breaking the curse of dimensionality in regression

no code implementations1 Aug 2017 Yinchu Zhu, Jelena Bradic

In this article, we are interested in conducting large-scale inference in models that might have signals of mixed strengths.

regression valid

Fine-Gray competing risks model with high-dimensional covariates: estimation and Inference

no code implementations29 Jul 2017 Jue Hou, Jelena Bradic, Ronghui Xu

The purpose of this paper is to construct confidence intervals for the regression coefficients in the Fine-Gray model for competing risks data with random censoring, where the number of covariates can be larger than the sample size.

Comments on `High-dimensional simultaneous inference with the bootstrap'

no code implementations6 May 2017 Jelena Bradic, Yinchu Zhu

We provide comments on the article "High-dimensional simultaneous inference with the bootstrap" by Ruben Dezeure, Peter Buhlmann and Cun-Hui Zhang.

Vocal Bursts Intensity Prediction

A projection pursuit framework for testing general high-dimensional hypothesis

no code implementations2 May 2017 Yinchu Zhu, Jelena Bradic

We propose a new inference method developed around the hypothesis adaptive projection pursuit framework, which solves the testing problems in the most general case.

Variable Selection Vocal Bursts Intensity Prediction

Uniform Inference for High-dimensional Quantile Regression: Linear Functionals and Regression Rank Scores

no code implementations20 Feb 2017 Jelena Bradic, Mladen Kolar

The main technical result are the development of a Bahadur representation of the debiasing estimator that is uniform over a range of quantiles and uniform convergence of the quantile process to the Brownian bridge process, which are of independent interest.

regression valid

Two-sample testing in non-sparse high-dimensional linear models

no code implementations14 Oct 2016 Yinchu Zhu, Jelena Bradic

In analyzing high-dimensional models, sparsity of the model parameter is a common but often undesirable assumption.

regression Two-sample testing +2

Linear Hypothesis Testing in Dense High-Dimensional Linear Models

no code implementations10 Oct 2016 Yinchu Zhu, Jelena Bradic

The test statistics are constructed in such a way that lack of sparsity in the original model parameter does not present a problem for the theoretical justification of our procedures.

regression Two-sample testing +2

Significance testing in non-sparse high-dimensional linear models

no code implementations7 Oct 2016 Yinchu Zhu, Jelena Bradic

We show that existing inferential methods are sensitive to the sparsity assumption, and may, in turn, result in the severe lack of control of Type-I error.

Vocal Bursts Intensity Prediction

Robust Confidence Intervals in High-Dimensional Left-Censored Regression

no code implementations22 Sep 2016 Jelena Bradic, Jiaqi Guo

In this paper, we develop smoothed estimating equations that augment the de-biasing method, such that the resulting estimator is adaptive to censoring and is more robust to the misspecification of the error distribution.

regression Vocal Bursts Intensity Prediction

Boosting in the presence of outliers: adaptive classification with non-convex loss functions

no code implementations5 Oct 2015 Alexander Hanbo Li, Jelena Bradic

Along with the Arch Boosting framework, the non-convex losses lead to the new class of boosting algorithms, named adaptive, robust, boosting (ARB).

Binary Classification General Classification

Robustness in sparse linear models: relative efficiency based on robust approximate message passing

no code implementations31 Jul 2015 Jelena Bradic

We observe this pattern for all choices of the number of non-zero parameters $s$, both $s \leq n$ and $s \approx n$.

Model Selection

Randomized maximum-contrast selection: subagging for large-scale regression

no code implementations14 Jun 2013 Jelena Bradic

The proposed method is based on careful combination of penalized estimators, each applied to a random projection of the sample space into a low-dimensional space.

regression Variable Selection

Structured Estimation in Nonparameteric Cox Model

no code implementations18 Jul 2012 Jelena Bradic, Rui Song

To better understand the interplay of censoring and sparsity we develop finite sample properties of nonparametric Cox proportional hazard's model.

Variable Selection

Regularization for Cox's proportional hazards model with NP-dimensionality

no code implementations25 Oct 2010 Jelena Bradic, Jianqing Fan, Jiancheng Jiang

High throughput genetic sequencing arrays with thousands of measurements per sample and a great amount of related censored clinical data have increased demanding need for better measurement specific model selection.

Model Selection

Cannot find the paper you are looking for? You can Submit a new open access paper.