Author name cluster

Liyuan Xu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Density Ratio-Free Doubly Robust Proxy Causal Learning

Bariscan Bozkurt
Houssam Zenati
Dimitri Meunier
Liyuan Xu
Arthur Gretton

We study the problem of causal function estimation in the Proxy Causal Learning (PCL) framework, where confounders are not observed but proxies for the confounders are available. Two main approaches have been proposed: outcome bridge-based and treatment bridge-based methods. In this work, we propose two kernel-based doubly robust estimators that combine the strengths of both approaches, and naturally handle continuous and high-dimensional variables. Our identification strategy builds on a recent density ratio-free method for treatment bridge-based PCL; furthermore, in contrast to previous approaches, it does not require indicator functions or kernel smoothing over the treatment variable. These properties make it especially well-suited for continuous or high-dimensional treatments. By using kernel mean embeddings, we propose the first density-ratio free doubly robust estimators for proxy causal learning, which have closed form solutions and strong uniform consistency guarantees. Our estimators outperform existing methods on PCL benchmarks, including a prior doubly robust method that requires both kernel smoothing and density ratio estimation.

PDF Details

ICLR Conference 2023 Conference Paper

A Neural Mean Embedding Approach for Back-door and Front-door Adjustment

Liyuan Xu
Arthur Gretton

We consider the estimation of average and counterfactual treatment effects, under two settings: back-door adjustment and front-door adjustment. The goal in both cases is to recover the treatment effect without having an access to a hidden confounder. This objective is attained by first estimating the conditional mean of the desired outcome variable given relevant covariates (the ``first stage" regression), and then taking the (conditional) expectation of this function as a ``second stage" procedure. We propose to compute these conditional expectations directly using a regression function to the learned input features of the first stage, thus avoiding the need for sampling or density estimation. All functions and features (and in particular, the output features in the second stage) are neural networks learned adaptively from data, with the sole requirement that the final layer of the first stage should be linear. The proposed method is shown to converge to the true causal parameter, and outperforms the recent state-of-the-art methods on challenging causal benchmarks, including settings involving high-dimensional image data.

Details

ICML Conference 2022 Conference Paper

Importance Weighted Kernel Bayes' Rule

Liyuan Xu
Yutian Chen
Arnaud Doucet
Arthur Gretton

We study a nonparametric approach to Bayesian computation via feature means, where the expectation of prior features is updated to yield expected posterior features, based on regression from kernel or neural net features of the observations. All quantities involved in the Bayesian update are learned from observed data, making the method entirely model-free. The resulting algorithm is a novel instance of a kernel Bayes’ rule (KBR). Our approach is based on importance weighting, which results in superior numerical stability to the existing approach to KBR, which requires operator inversion. We show the convergence of the estimator using a novel consistency analysis on the importance weighting estimator in the infinity norm. We evaluate our KBR on challenging synthetic benchmarks, including a filtering problem with a state-space model involving high dimensional image observations. The proposed method yields uniformly better empirical performance than the existing KBR, and competitive performance with other competing methods. We evaluate our KBR on challenging synthetic benchmarks, including a filtering problem with a state-space model involving high dimensional image observations. The proposed method yields uniformly better empirical performance than the existing KBR, and competitive performance with other competing methods.

Details

JMLR Journal 2022 Journal Article

On Instrumental Variable Regression for Deep Offline Policy Evaluation

Yutian Chen
Liyuan Xu
Caglar Gulcehre
Tom Le Paine
Arthur Gretton
Nando de Freitas
Arnaud Doucet

We show that the popular reinforcement learning (RL) strategy of estimating the state-action value (Q-function) by minimizing the mean squared Bellman error leads to a regression problem with confounding, the inputs and output noise being correlated. Hence, direct minimization of the Bellman error can result in significantly biased Q-function estimates. We explain why fixing the target Q-network in Deep Q-Networks and Fitted Q Evaluation provides a way of overcoming this confounding, thus shedding new light on this popular but not well understood trick in the deep RL literature. An alternative approach to address confounding is to leverage techniques developed in the causality literature, notably instrumental variables (IV). We bring together here the literature on IV and RL by investigating whether IV approaches can lead to improved Q-function estimates. This paper analyzes and compares a wide range of recent IV methods in the context of offline policy evaluation (OPE), where the goal is to estimate the value of a policy using logged data only. By applying different IV techniques to OPE, we are not only able to recover previously proposed OPE methods such as model-based techniques but also to obtain competitive new techniques. We find empirically that state-of-the-art OPE methods are closely matched in performance by some IV methods such as AGMM, which were not developed for OPE. We open-source all our code and datasets at https://github.com/liyuan9988/IVOPEwithACME. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2022. ( edit, beta )

PDF Details

YNICL Journal 2022 Journal Article

Predicting diagnosis 4 years prior to Alzheimer’s disease incident

Anqi Qiu
Liyuan Xu
Chaoqiang Liu

This study employed a deep learning longitudinal model, graph convolutional and recurrent neural network (graph-CNN-RNN), on a series of brain structural MRI scans for AD prognosis. It characterized whole-brain morphology via incorporating longitudinal cortical and subcortical morphology and defined a probabilistic risk for the prediction of AD as a function of age prior to clinical diagnosis. The graph-CNN-RNN model was trained on half of the Alzheimer's Disease Neuroimaging Initiative dataset (ADNI, n = 1559) and validated on the other half of the ADNI dataset and the Open Access Series of Imaging Studies-3 (OASIS-3, n = 930). Our findings demonstrated that the graph-CNN-RNN can reliably and robustly diagnose AD at the accuracy rate of 85% and above across all the time points for both datasets. The graph-CNN-RNN predicted the AD conversion from 0 to 4 years before the AD onset at ∼80% of accuracy. The AD probabilistic risk was associated with clinical traits, cognition, and amyloid burden assessed using [18F]-Florbetapir (AV45) positron emission tomography (PET) across all the time points. The graph-CNN-RNN provided the quantitative trajectory of brain morphology from prognosis to overt stages of AD. Such a deep learning tool and the AD probabilistic risk have great potential in clinical applications for AD prognosis.

Details DOI

YNIMG Journal 2021 Journal Article

Common functional brain networks between attention deficit and disruptive behaviors in youth

Ting Yat Wong
Han Zhang
Tonya White
Liyuan Xu
Anqi Qiu

Attention deficits (AD) and disruptive behavior (DB) are highly comorbid youth externalizing behaviors. This study aimed to study reliable functional brain networks shared by AD and DB in youth aged from 8 to 21 years from the Philadelphia Neurodevelopmental Cohort (PNC). The PNC study assessed AD and DB behaviors via Kiddie-Schedule for Affective Disorders and Schizophrenia (K-SADS). This study employed sparse canonical correlation analysis (SCCA) to examine the correlation of AD and DB behaviors with resting-state functional connectivity maps of the brain regions identified via activation likelihood estimation (ALE) meta-analyses on attention deficit/hyperactivity disorder (ADHD) and DB disorder (DBD). Our meta-analyses identified that the middle cingulate cortex, pre-supplementary motor area (pre-SMA), and striatum had a great consensus in existing ADHD studies and the amygdala and inferior parietal lobule were consistently found in existing DBD studies. Our SCCA analysis revealed that the AD and DB behavioral items relevant to inattention and delinquency were correlated with the functional connectivity of the pre-SMA with the ventral attentional and frontoparietal networks (FPN), and the striatum with the default mode (DMN) and dorsal attentional networks. The AD and DB behavioral items relevant to inattention and irritability were associated with the functional connectivity between the amygdala and the DMN and FPN. Our findings suggest that the functional organization of the ADHD- and DBD-related brain regions provides insights on the shared neural basis in AD and DB.

Details DOI

NeurIPS Conference 2021 Conference Paper

Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation

Liyuan Xu
Heishiro Kanagawa
Arthur Gretton

Proxy causal learning (PCL) is a method for estimating the causal effect of treatments on outcomes in the presence of unobserved confounding, using proxies (structured side information) for the confounder. This is achieved via two-stage regression: in the first stage, we model relations among the treatment and proxies; in the second stage, we use this model to learn the effect of treatment on the outcome, given the context provided by the proxies. PCL guarantees recovery of the true causal effect, subject to identifiability conditions. We propose a novel method for PCL, the deep feature proxy variable method (DFPV), to address the case where the proxies, treatments, and outcomes are high-dimensional and have nonlinear complex relationships, as represented by deep neural network features. We show that DFPV outperforms recent state-of-the-art PCL methods on challenging synthetic benchmarks, including settings involving high dimensional image data. Furthermore, we show that PCL can be applied to off-policy evaluation for the confounded bandit problem, in which DFPV also exhibits competitive performance.

PDF Details

ICLR Conference 2021 Conference Paper

Learning Deep Features in Instrumental Variable Regression

Liyuan Xu
Yutian Chen 0001
Siddarth Srinivasan
Nando de Freitas
Arnaud Doucet
Arthur Gretton

Instrumental variable (IV) regression is a standard strategy for learning causal relationships between confounded treatment and outcome variables from observational data by using an instrumental variable, which affects the outcome only through the treatment. In classical IV regression, learning proceeds in two stages: stage 1 performs linear regression from the instrument to the treatment; and stage 2 performs linear regression from the treatment to the outcome, conditioned on the instrument. We propose a novel method, deep feature instrumental variable regression (DFIV), to address the case where relations between instruments, treatments, and outcomes may be nonlinear. In this case, deep neural nets are trained to define informative nonlinear features on the instruments and treatments. We propose an alternating training regime for these features to ensure good end-to-end performance when composing stages 1 and 2, thus obtaining highly flexible feature maps in a computationally efficient manner. DFIV outperforms recent state-of-the-art methods on challenging IV benchmarks, including settings involving high dimensional image data. DFIV also exhibits competitive performance in off-policy policy evaluation for reinforcement learning, which can be understood as an IV regression task.

Details

AAAI Conference 2019 Conference Paper

Dueling Bandits with Qualitative Feedback

Liyuan Xu
Junya Honda
Masashi Sugiyama

We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulling each arm. We employ the same regret as the dueling bandit (DB) problem where the duel is carried out by comparing the qualitative feedback. Although we can naively use classic DB algorithms for solving the QDB problem, this reduction significantly worsens the performance—actually, in the QDB problem, the probability that one arm wins the duel over another arm can be directly estimated without carrying out actual duels. In this paper1, we propose such direct algorithms for the QDB problem. Our theoretical analysis shows that the proposed algorithms significantly outperform DB algorithms by incorporating the qualitative feedback, and experimental results also demonstrate vast improvement over the existing DB algorithms.

PDF Details

NeurIPS Conference 2019 Conference Paper

Uncoupled Regression from Pairwise Comparison Data

Liyuan Xu
Junya Honda
Gang Niu
Masashi Sugiyama

Uncoupled regression is the problem to learn a model from unlabeled data and the set of target values while the correspondence between them is unknown. Such a situation arises in predicting anonymized targets that involve sensitive information, e. g. , one's annual income. Since existing methods for uncoupled regression often require strong assumptions on the true target function, and thus, their range of applications is limited, we introduce a novel framework that does not require such assumptions in this paper. Our key idea is to utilize \emph{pairwise comparison data, which consists of pairs of unlabeled data that we know which one has a larger target value. Such pairwise comparison data is easy to collect, as typically discussed in the learning-to-rank scenario, and does not break the anonymity of data. We propose two practical methods for uncoupled regression from pairwise comparison data and show that the learned regression model converges to the optimal model with the optimal parametric convergence rate when the target variable distributes uniformly. Moreover, we empirically show that for linear models the proposed methods are comparable to ordinary supervised regression with labeled data.

PDF Details