Search

Group-V materials such as niobium and tantalum have become popular choices for extending the performance of circuit quantum electrodynamics (cQED) platforms allowing for quantum processors and memories with reduced error rates and more modes. The complex surface chemistry of niobium however makes identifying the main modes of decoherence difficult at millikelvin temperatures and single-photon powers. We use niobium coaxial quarter-wave cavities to study the impact of etch chemistry, prolonged atmospheric exposure, and the significance of cavity conditions prior to and during cooldown, in particular niobium hydride evolution, on single-photon coherence. We demonstrate cavities with quality factors of $Q_{\rm int}\gtrsim 1.4\times10^{9}$ in the single-photon regime, a $15$ fold improvement over aluminum cavities of the same geometry. We rigorously quantify the sensitivity of our fabrication process to various loss mechanisms and demonstrate a $2-4\times$ reduction in the two-level system (TLS) loss tangent and a $3-5\times$ improvement in the residual resistivity over traditional BCP etching techniques. Finally, we demonstrate transmon integration and coherent cavity control while maintaining a cavity coherence of \SI{11.3}{ms}. The accessibility of our method, which can easily be replicated in academic-lab settings, and the demonstration of its performance mark an advancement in 3D cQED., Comment: 14 pages, 10 figures

Advancements in quantum system lifetimes and control have enabled the creation of increasingly complex quantum states, such as those on multiple bosonic cavity modes. When characterizing these states, traditional tomography scales exponentially in both computational and experimental measurement requirement, which becomes prohibitive as the state size increases. Here, we implement a state reconstruction method whose sampling requirement instead scales polynomially with subspace size, and thus mode number, for states that can be expressed within such a subspace. We demonstrate this improved scaling with Wigner tomography of multimode entangled W states of up to 4 modes on a 3D circuit quantum electrodynamics (cQED) system. This approach performs similarly in efficiency to existing matrix inversion methods for 2 modes, and demonstrates a noticeable improvement for 3 and 4 modes, with even greater theoretical gains at higher mode numbers., Comment: 6 pages of main text with 4 figures. 10 pages of supplementary information with 6 figures

In applications where the study data are collected within cluster units (e.g., patients within transplant centers), it is often of interest to estimate and perform inference on the treatment effects of the cluster units. However, it is well-established that cluster-level confounding variables can bias these assessments, and many of these confounding factors may be unobservable. In healthcare settings, data sharing restrictions often make it impossible to directly fit conventional risk-adjustment models on patient-level data, and existing privacy-preserving approaches cannot adequately adjust for both observed and unobserved cluster-level confounding factors. In this paper, we propose a privacy-preserving model for cluster-level confounding that only depends on publicly-available summary statistics, can be fit using a single optimization routine, and is robust to outlying cluster unit effects. In addition, we develop a Pseudo-Bayesian inference procedure that accounts for the estimated cluster-level confounding effects and corrects for the impact of unobservable factors. Simulations show that our estimates are robust and accurate, and the proposed inference approach has better Frequentist properties than existing methods. Motivated by efforts to improve equity in transplant care, we apply these methods to evaluate transplant centers while adjusting for observed geographic disparities in donor organ availability and unobservable confounders.

The manipulation of quantum states of light has resulted in significant advancements in both dark matter searches and gravitational wave detectors [1-4]. Current dark matter searches operating in the microwave frequency range use nearly quantum-limited amplifiers [3, 5, 6]. Future high frequency searches will use photon counting techniques [1] to evade the standard quantum limit. We present a signal enhancement technique that utilizes a superconducting qubit to prepare a superconducting microwave cavity in a non-classical Fock state and stimulate the emission of a photon from a dark matter wave. By initializing the cavity in an $|n=4\rangle$ Fock state, we demonstrate a quantum enhancement technique that increases the signal photon rate and hence also the dark matter scan rate each by a factor of 2.78. Using this technique, we conduct a dark photon search in a band around $\mathrm{5.965\, GHz \, (24.67\, \mu eV)}$, where the kinetic mixing angle $\epsilon \geq 4.35 \times 10^{-13}$ is excluded at the $90\%$ confidence level., Comment: 17 pages, 17 figures

We present an adaptation of direct collocation -- a trajectory optimization method commonly used in robotics and aerospace applications -- to quantum optimal control (QOC); we refer to this method as Pade Integrator COllocation (PICO). This approach supports general nonlinear constraints on the states and controls, takes advantage of state-of-the-art large-scale nonlinear programming solvers, and has superior convergence properties compared to standard approaches like GRAPE and CRAB. PICO also allows for the formulation of novel free-time and minimum-time control problems -- crucial for realizing high-performance quantum computers when the optimal pulse duration is not known a priori. We demonstrate PICO's performance both in simulation and on hardware with a 3D circuit cavity quantum electrodynamics system.

Polygenic hazard score (PHS) models designed for European ancestry (EUR) individuals provide ample information regarding survival risk discrimination. Incorporating such information can improve the performance of risk discrimination in an internal small-sized non-EUR cohort. However, given that external EUR-based model and internal individual-level data come from different populations, ignoring population heterogeneity can introduce substantial bias. In this paper, we develop a Kullback-Leibler-based Cox model (CoxKL) to integrate internal individual-level time-to-event data with external risk scores derived from published prediction models, accounting for population heterogeneity. Partial-likelihood-based KL information is utilized to measure the discrepancy between the external risk information and the internal data. We establish the asymptotic properties of the CoxKL estimator. Simulation studies show that the integration model by the proposed CoxKL method achieves improved estimation efficiency and prediction accuracy. We applied the proposed method to develop a trans-ancestry PHS model for prostate cancer and found that integrating a previously published EUR-based PHS with an internal genotype data of African ancestry (AFR) males yielded considerable improvement on the prostate cancer risk discrimination.

Polygenic risk scores (PRS) have recently received much attention for genetics risk prediction. While successful for the Caucasian population, the PRS based on the minority population suffer from small sample sizes, high dimensionality and low signal-to-noise ratios, exacerbating already severe health disparities. Due to population heterogeneity, direct trans-ethnic prediction by utilizing the Caucasian model for the minority population also has limited performance. In addition, due to data privacy, the individual genotype data is not accessible for either the Caucasian population or the minority population. To address these challenges, we propose a Bregman divergence-based estimation procedure to measure and optimally balance the information from different populations. The proposed method only requires the use of encrypted summary statistics and improves the PRS performance for ethnic minority groups by incorporating additional information. We provide the asymptotic consistency and weak oracle property for the proposed method. Simulations and real data analyses also show its advantages in prediction and variable selection., Comment: 35 pages, 6 figures

We study learning on social media with an equilibrium model of users interacting with shared news stories. Rational users arrive sequentially, observe an original story (i.e., a private signal) and a sample of predecessors' stories in a news feed, and then decide which stories to share. The observed sample of stories depends on what predecessors share as well as the sampling algorithm generating news feeds. We focus on how often this algorithm selects more viral (i.e., widely shared) stories. Showing users viral stories can increase information aggregation, but it can also generate steady states where most shared stories are wrong. These misleading steady states self-perpetuate, as users who observe wrong stories develop wrong beliefs, and thus rationally continue to share them. Finally, we describe several consequences for platform design and robustness.

The coronavirus disease 2019 (COVID-19) pandemic has exerted a profound impact on patients with end-stage renal disease relying on kidney dialysis to sustain their lives. Motivated by a request by the U.S. Centers for Medicare & Medicaid Services, our analysis of their postdischarge hospital readmissions and deaths in 2020 revealed that the COVID-19 effect has varied significantly with postdischarge time and time since the onset of the pandemic. However, the complex dynamics of the COVID-19 effect trajectories cannot be characterized by existing varying coefficient models. To address this issue, we propose a bivariate varying coefficient model for competing risks within a cause-specific hazard framework, where tensor-product B-splines are used to estimate the surface of the COVID-19 effect. An efficient proximal Newton algorithm is developed to facilitate the fitting of the new model to the massive Medicare data for dialysis patients. Difference-based anisotropic penalization is introduced to mitigate model overfitting and the wiggliness of the estimated trajectories; various cross-validation methods are considered in the determination of optimal tuning parameters. Hypothesis testing procedures are designed to examine whether the COVID-19 effect varies significantly with postdischarge time and the time since pandemic onset, either jointly or separately. Simulation experiments are conducted to evaluate the estimation accuracy, type I error rate, statistical power, and model selection procedures. Applications to Medicare dialysis patients demonstrate the real-world performance of the proposed methods., Comment: 40 pages, 8 figures, 1 table

Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis. Although several improvements have been shown by previous works, training an excellent deep learning model requires a huge amount of data, which may not hold in practice. To address this challenge, we develop a Kullback-Leibler-based (KL) deep learning procedure to integrate external survival prediction models with newly collected time-to-event data. Time-dependent KL discrimination information is utilized to measure the discrepancy between the external and internal data. This is the first work considering using prior information to deal with short data problem in Survival Analysis for deep learning. Simulation and real data results show that the proposed model achieves better performance and higher robustness compared with previous works., Comment: This paper is not complete and the results are not qualified to be public. Therefore we decided to withdraw the paper and plan to submit a newer version in the future

Risk-adjusted quality measures are used to evaluate healthcare providers while controlling for factors beyond their control. Existing healthcare provider profiling approaches typically assume that the risk adjustment is perfect and the between-provider variation in quality measures is entirely due to the quality of care. However, in practice, even with very good models for risk adjustment, some between-provider variation will be due to incomplete risk adjustment, which should be recognized in assessing and monitoring providers. Otherwise, conventional methods disproportionately identify larger providers as outliers, even though their provider effects need not be "extreme.'' Motivated by efforts to evaluate the quality of care provided by transplant centers, we develop a composite evaluation score based on a novel individualized empirical null method, which robustly accounts for overdispersion due to unobserved risk factors, models the marginal variance of standardized scores as a function of the effective center size, and only requires the use of publicly-available center-level statistics. The evaluations of United States kidney transplant centers based on the proposed composite score are substantially different from those based on conventional methods. Simulations show that the proposed empirical null approach more accurately classifies centers in terms of quality of care, compared to existing methods.

Learning models do not in general imply that weakly dominated strategies are irrelevant or justify the related concept of "forward induction," because rational agents may use dominated strategies as experiments to learn how opponents play, and may not have enough data to rule out a strategy that opponents never use. Learning models also do not support the idea that the selected equilibria should only depend on a game's normal form, even though two games with the same normal form present players with the same decision problems given fixed beliefs about how others play. However, playing the extensive form of a game is equivalent to playing the normal form augmented with the appropriate terminal node partitions so that two games are information equivalent, i.e., the players receive the same feedback about others' strategies.

Private signals model noisy information about an unknown state. Although these signals are called "private," they may still carry information about each other. Our paper introduces the concept of private private signals, which contain information about the state but not about other signals. To achieve privacy, signal quality may need to be sacrificed. We study the informativeness of private private signals and characterize those that are optimal in the sense that they cannot be made more informative without violating privacy. We discuss implications for privacy in recommendation systems, information design, causal inference, and mechanism design.

We show that adding noise before publishing data effectively screens $p$-hacked findings: spurious explanations produced by fitting many statistical models (data mining). Noise creates "baits" that affect two types of researchers differently. Uninformed $p$-hackers, who are fully ignorant of the true mechanism and engage in data mining, often fall for baits. Informed researchers, who start with an ex-ante hypothesis, are minimally affected. We show that as the number of observations grows large, dissemination noise asymptotically achieves optimal screening. In a tractable special case where the informed researchers' theory can identify the true causal mechanism with very little data, we characterize the optimal level of dissemination noise and highlight the relevant trade-offs. Dissemination noise is a tool that statistical agencies currently use to protect privacy. We argue this existing practice can be repurposed to screen $p$-hackers and thus improve research credibility.

Prediction of time-to-event data often suffers from rare event rates, small sample sizes, high dimensionality and low signal-to-noise ratios. Incorporating published prediction models from large-scale studies is expected to improve the performance of prognosis prediction on internal individual-level time-to-event data. However, existing integration approaches typically assume that underlying distributions from the external and internal data sources are similar, which is often invalid. To account for challenges including heterogeneity, data sharing, and privacy constraints, we propose a discrete failure time modeling procedure, which utilizes a discrete hazard-based Kullback-Leibler discriminatory information measuring the discrepancy between the published models and the internal dataset. Simulations show the advantage of the proposed method compared with those solely based on the internal data or published models. We apply the proposed method to improve prediction performance on a kidney transplant dataset from a local hospital by integrating this small-scale dataset with published survival models obtained from the national transplant registry.

Toward explaining the persistence of biased inferences, we propose a framework to evaluate competing (mis)specifications in strategic settings. Agents with heterogeneous (mis)specifications coexist and draw Bayesian inferences about their environment through repeated play. The relative stability of (mis)specifications depends on their adherents' equilibrium payoffs. A key mechanism is the learning channel: the endogeneity of perceived best replies due to inference. We characterize when a rational society is only vulnerable to invasion by some misspecification through the learning channel. The learning channel leads to new stability phenomena, and can confer an evolutionary advantage to otherwise detrimental biases in economically relevant applications.

Multimode cavity quantum electrodynamics ---where a two-level system interacts simultaneously with many cavity modes---provides a versatile framework for quantum information processing and quantum optics. Due to the combination of long coherence times and large interaction strengths, one of the leading experimental platforms for cavity QED involves coupling a superconducting circuit to a 3D microwave cavity. In this work, we realize a 3D multimode circuit QED system with single photon lifetimes of $2$ ms and cooperativities of $0.5-1.5\times10^9$ across 9 modes of a novel seamless cavity. We demonstrate a variety of protocols for universal single-mode quantum control applicable across all cavity modes, using only a single drive line. We achieve this by developing a straightforward flute method for creating monolithic superconducting microwave cavities that reduces loss while simultaneously allowing control of the mode spectrum and mode-qubit interaction. We highlight the flexibility and ease of implementation of this technique by using it to fabricate a variety of 3D cavity geometries, providing a template for engineering multimode quantum systems with exceptionally low dissipation. This work is an important step towards realizing hardware efficient random access quantum memories and processors, and for exploring quantum many-body physics with photons., Comment: 5 pages of main text with 4 figures. 9 pages of supplementary information with 7 figures

Interactions are essential for the creation of correlated quantum many-body states. While two-body interactions underlie most natural phenomena, three- and four-body interactions are important for the physics of nuclei [1], exotic few-body states in ultracold quantum gases [2], the fractional quantum Hall effect [3], quantum error correction [4], and holography [5, 6]. Recently, a number of artificial quantum systems have emerged as simulators for many-body physics, featuring the ability to engineer strong interactions. However, the interactions in these systems have largely been limited to the two-body paradigm, and require building up multi-body interactions by combining two-body forces. Here, we demonstrate a pure N-body interaction between microwave photons stored in an arbitrary number of electromagnetic modes of a multimode cavity. The system is dressed such that there is collectively no interaction until a target total photon number is reached across multiple distinct modes, at which point they interact strongly. The microwave cavity features 9 modes with photon lifetimes of $\sim 2$ ms coupled to a superconducting transmon circuit, forming a multimode circuit QED system with single photon cooperativities of $\sim10^9$. We generate multimode interactions by using cavity photon number resolved drives on the transmon circuit to blockade any multiphoton state with a chosen total photon number distributed across the target modes. We harness the interaction for state preparation, preparing Fock states of increasing photon number via quantum optimal control pulses acting only on the cavity modes. We demonstrate multimode interactions by generating entanglement purely with uniform cavity drives and multimode photon blockade, and characterize the resulting two- and three-mode W states using a new protocol for multimode Wigner tomography., Comment: 5 pages of main text with 5 figures. 11 pages of supplementary information with 10 figures

Cox-nnet is a neural-network based prognosis prediction method, originally applied to genomics data. Here we propose the version 2 of Cox-nnet, with significant improvement on efficiency and interpretability, making it suitable to predict prognosis based on large-scale electronic medical records (EMR) datasets. We also add permutation-based feature importance scores and the direction of feature coefficients. Applying on an EMR dataset of OPTN kidney transplantation, Cox-nnet v2.0 reduces the training time of Cox-nnet up to 32 folds (n=10,000) and achieves better prediction accuracy than Cox-PH (p<0.05). Availability and implementation: Cox-nnet v2.0 is freely available to the public at https://github.com/lanagarmire/Cox-nnet-v2.0

This paper introduces an Ordinary Differential Equation (ODE) notion for survival analysis. The ODE notion not only provides a unified modeling framework, but more importantly, also enables the development of a widely applicable, scalable, and easy-to-implement procedure for estimation and inference. Specifically, the ODE modeling framework unifies many existing survival models, such as the proportional hazards model, the linear transformation model, the accelerated failure time model, and the time-varying coefficient model as special cases. The generality of the proposed framework serves as the foundation of a widely applicable estimation procedure. As an illustrative example, we develop a sieve maximum likelihood estimator for a general semi-parametric class of ODE models. In comparison to existing estimation methods, the proposed procedure has advantages in terms of computational scalability and numerical stability. Moreover, to address unique theoretical challenges induced by the ODE notion, we establish a new general sieve M-theorem for bundled parameters and show that the proposed sieve estimator is consistent and asymptotically normal, and achieves the semi-parametric efficiency bound. The finite sample performance of the proposed estimator is examined in simulation studies and a real-world data example.

Detection mechanisms for low mass bosonic dark matter candidates, such the axion or hidden photon, leverage potential interactions with electromagnetic fields, whereby the dark matter (of unknown mass) on rare occasion converts into a single photon. Current dark matter searches operating at microwave frequencies use a resonant cavity to coherently accumulate the field sourced by the dark matter and a near standard quantum limited (SQL) linear amplifier to read out the cavity signal. To further increase sensitivity to the dark matter signal, sub-SQL detection techniques are required. Here we report the development of a novel microwave photon counting technique and a new exclusion limit on hidden photon dark matter. We operate a superconducting qubit to make repeated quantum non-demolition measurements of cavity photons and apply a hidden Markov model analysis to reduce the noise to 15.7 dB below the quantum limit, with overall detector performance limited by a residual background of real photons. With the present device, we perform a hidden photon search and constrain the kinetic mixing angle to $\epsilon \leq 1.68 \times 10^{-15}$ in a band around 6.011 GHz (24.86 $\mu$eV) with an integration time of 8.33 s. This demonstrated noise reduction technique enables future dark matter searches to be sped up by a factor of 1300. By coupling a qubit to an arbitrary quantum sensor, more general sub-SQL metrology is possible with the techniques presented in this work., Comment: 15 pages, 14 figures, 2 table. Dark matter exclusion analysis modified to include experimental systematics. Discussion of background calibration and detector compatibility with tunable cavity added to conclusion. Future optimizations and integration into axion search sections moved to Supplemental Material. References updated

In observational studies of survival time featuring a binary time-dependent treatment, the hazard ratio (an instantaneous measure) is often used to represent the treatment effect. However, investigators are often more interested in the difference in survival functions. We propose semiparametric methods to estimate the causal effect of treatment among the treated with respect to survival probability. The objective is to compare post-treatment survival with the survival function that would have been observed in the absence of treatment. For each patient, we compute a prognostic score (based on the pre-treatment death hazard) and a propensity score (based on the treatment hazard). Each treated patient is then matched with an alive, uncensored and not-yet-treated patient with similar prognostic and/or propensity scores. The experience of each treated and matched patient is weighted using a variant of Inverse Probability of Censoring Weighting to account for the impact of censoring. We propose estimators of the treatment-specific survival functions (and their difference), computed through weighted Nelson-Aalen estimators. Closed-form variance estimators are proposed which take into consideration the potential replication of subjects across matched sets. The proposed methods are evaluated through simulation, then applied to estimate the effect of kidney transplantation on survival among end-stage renal disease patients using data from a national organ failure registry.

The time-varying effects model is a flexible and powerful tool for modeling the dynamic changes of covariate effects. However, in survival analysis, its computational burden increases quickly as the number of sample sizes or predictors grows. Traditional methods that perform well for moderate sample sizes and low-dimensional data do not scale to massive data. Analysis of national kidney transplant data with a massive sample size and large number of predictors defy any existing statistical methods and software. In view of these difficulties, we propose a Minorization-Maximization-based steepest ascent procedure for estimating the time-varying effects. Leveraging the block structure formed by the basis expansions, the proposed procedure iteratively updates the optimal block-wise direction along which the approximate increase in the log-partial likelihood is maximized. The resulting estimates ensure the ascent property and serve as refinements of the previous step. The performance of the proposed method is examined by simulations and applications to the analysis of national kidney transplant data.

When individuals in a social network learn about an unknown state from private signals and neighbors' actions, the network structure often causes information loss. We consider rational agents and Gaussian signals in the canonical sequential social-learning problem and ask how the network changes the efficiency of signal aggregation. Rational actions in our model are log-linear functions of observations and admit a signal-counting interpretation of accuracy. Networks where agents observe multiple neighbors but not their common predecessors confound information, and even a small amount of confounding can lead to much lower accuracy. In a class of networks where agents move in generations and observe the previous generation, we quantify the information loss with an aggregative efficiency index. Aggregative efficiency is a simple function of network parameters: increasing in observations and decreasing in confounding. Later generations contribute little additional information, even with arbitrarily large generations.

We conduct a sequential social-learning experiment where subjects each guess a hidden state based on private signals and the guesses of a subset of their predecessors. A network determines the observable predecessors, and we compare subjects' accuracy on sparse and dense networks. Accuracy gains from social learning are twice as large on sparse networks compared to dense networks. Models of naive inference where agents ignore correlation between observations predict this comparative static in network density, while the finding is difficult to reconcile with rational-learning models., Comment: Incorporates the experimental results from a previous version of arXiv:1703.02105

A Bayesian agent experiences gain-loss utility each period over changes in belief about future consumption ("news utility"), with diminishing sensitivity over the magnitude of news. Diminishing sensitivity induces a preference over news skewness: gradual bad news, one-shot good news is worse than one-shot resolution, which is in turn worse than gradual good news, one-shot bad news. So, the agent's preference between gradual information and one-shot resolution can depend on his consumption ranking of different states. In a dynamic cheap-talk framework where a benevolent sender communicates the state over multiple periods, the babbling equilibrium is essentially unique without loss aversion. More loss-averse agents may enjoy higher news utility in equilibrium, contrary to the commitment case. We characterize the family of gradual good news equilibria that exist with high enough loss aversion, and find the sender conveys progressively larger pieces of good news. We discuss applications to media competition and game shows.

Monitoring outcomes of health care providers, such as patient deaths, hospitalizations and hospital readmissions, helps in assessing the quality of health care. We consider a large database on patients being treated at dialysis facilities in the United States, and the problem of identifying facilities with outcomes that are better than or worse than expected. Analyses of such data have been commonly based on random or fixed facility effects, which have shortcomings that can lead to unfair assessments. A primary issue is that they do not appropriately account for variation between providers that is outside the providers' control due, for example, to unobserved patient characteristics that vary between providers. In this article, we propose a smoothed empirical null approach that accounts for the total variation and adapts to different provider sizes. The linear model provides an illustration that extends easily to other nonlinear models for survival or binary outcomes, for example. The empirical null method is generalized to allow for some variation being due to quality of care. These methods are examined with numerical simulations and applied to the monitoring of survival in the dialysis facility data.

Modern bio-technologies have produced a vast amount of high-throughput data with the number of predictors far greater than the sample size. In order to identify more novel biomarkers and understand biological mechanisms, it is vital to detect signals weakly associated with outcomes among ultrahigh-dimensional predictors. However, existing screening methods, which typically ignore correlation information, are likely to miss these weak signals. By incorporating the inter-feature dependence, we propose a covariance-insured screening methodology to identify predictors that are jointly informative but only marginally weakly associated with outcomes. The validity of the method is examined via extensive simulations and real data studies for selecting potential genetic factors related to the onset of cancer.

I study endogenous learning dynamics for people who misperceive intertemporal correlations in random sequences. Biased agents face an optimal-stopping problem. They are uncertain about the underlying distribution and learn its parameters from predecessors. Agents stop when early draws are "good enough," so predecessors' experiences contain negative streaks but not positive streaks. When agents wrongly expect systematic reversals (the "gambler's fallacy"), they understate the likelihood of consecutive below-average draws, converge to over-pessimistic beliefs about the distribution's mean, and stop too early. Agents uncertain about the distribution's variance overestimate it to an extent that depends on predecessors' stopping thresholds. I also analyze how other misperceptions of intertemporal correlation interact with endogenous data censoring.

High-dimensional variable selection in the proportional hazards (PH) model has many successful applications in different areas. In practice, data may involve confounding variables that do not satisfy the PH assumption, in which case the stratified proportional hazards (SPH) model can be adopted to control the confounding effects by stratification of the confounding variable, without directly modeling the confounding effects. However, there is lack of computationally efficient statistical software for high-dimensional variable selection in the SPH model. In this work, an R package, SurvBoost, is developed to implement the gradient boosting algorithm for fitting the SPH model with high-dimensional covariate variables and other confounders. Extensive simulation studies demonstrate that in many scenarios SurvBoost can achieve a better selection accuracy and reduce computational time substantially compared to the existing R package that implements boosting algorithms without stratification. The proposed R package is also illustrated by an analysis of the gene expression data with survival outcome in The Cancer Genome Atlas (TCGA) study. In addition, a detailed hands-on tutorial for SurvBoost is provided.