21 citations · 119 across the 23 of their papers we have counts for
24 papers
Surrogate-powered Causal Inference with Censored Outcomes
Yaroslav Mukhin, Tereza Oprea, Arielle Anderer +2
Clinical trials with survival endpoints lose information when participants are censored before death is observed. We develop target-preserving estimators that use posttreatment dis…
Reinforcement Learning in MDPs with Information-Ordered Policies
Zhongjun Zhang, Shipra Agrawal, Ilan Lobel +2
Many operational Markov decision processes provide structured information where a trajectory generated under one policy may also reveal how other policies would have performed. We…
Entry-Specific Matrix Estimation under Arbitrary Sampling Patterns through the Lens of Network Flows
Yudong Chen, Xumei Xi, Christina Lee Yu
Matrix completion tackles the task of predicting missing values in a low-rank matrix based on a sparse set of observed entries. It is often assumed that the observation pattern is…
Entry-Specific Bounds for Low-Rank Matrix Completion under Highly Non-Uniform Sampling
Xumei Xi, Christina Lee Yu, Yudong Chen
Low-rank matrix completion concerns the problem of estimating unobserved entries in a matrix using a sparse set of observed entries. We consider the non-uniform setting where the o…
The SMART approach to instance-optimal online learning
Siddhartha Banerjee, Alankrita Bhatt, Christina Lee Yu
We devise an online learning algorithm -- titled Switching via Monotone Adapted Regret Traces (SMART) -- that adapts to the data and achieves regret that is instance optimal, i.e.,…
Matrix Estimation for Offline Reinforcement Learning with Low-Rank Structure
Xumei Xi, Christina Lee Yu, Yudong Chen
We consider offline Reinforcement Learning (RL), where the agent does not interact with the environment and must rely on offline data collected using a behavior policy. Previous wo…
The Asymptotics of the Expected Betti Numbers of Preferential Attachment Clique Complexes
Chunyin Siu, Gennady Samorodnitsky, Christina Lee Yu +1
The preferential attachment model is a natural and popular random graph model for a growing network that contains very well-connected ``hubs''. We study the higher-order connectivi…
Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits
Siddhartha Banerjee, Sean R. Sinclair, Milind Tambe +2
Most real-world deployments of bandit algorithms exist somewhere in between the offline and online set-up, where some historical data is available upfront and additional data is co…
Exploiting Neighborhood Interference with Low Order Interactions under Unit Randomized Design
Mayleen Cortez-Rodriguez, Matthew Eichhorn, Christina Lee Yu
Network interference, where the outcome of an individual is affected by the treatment assignment of those in their social network, is pervasive in real-world settings. However, it…
Overcoming the Long Horizon Barrier for Sample-Efficient Reinforcement Learning with Latent Low-Rank Structure
Tyler Sam, Yudong Chen, Christina Lee Yu
The practicality of reinforcement learning algorithms has been limited due to poor scaling with respect to the problem size, as the sample complexity of learning an -optimal pol…
Staggered Rollout Designs Enable Causal Inference Under Interference Without Network Knowledge
Mayleen Cortez, Matthew Eichhorn, Christina Lee Yu
Randomized experiments are widely used to estimate causal effects across a variety of domains. However, classical causal inference approaches rely on critical independence assumpti…
Estimating Total Treatment Effect in Randomized Experiments with Unknown Network Structure
Christina Lee Yu, Edoardo M Airoldi, Christian Borgs +1
Randomized experiments are widely used to estimate the causal effects of a proposed treatment in many areas of science, from medicine and healthcare to the physical and biological…
Detection of Small Holes by the Scale-Invariant Robust Density-Aware Distance (RDAD) Filtration
Chunyin Siu, Gennady Samorodnitsky, Christina Lee Yu +1
A novel topological-data-analytical (TDA) method is proposed to distinguish, from noise, small holes surrounded by high-density regions of a probability density function. The propo…
Nonparametric Matrix Estimation with One-Sided Covariates
Christina Lee Yu
Consider the task of matrix estimation in which a dataset is observed with sparsity , and we would like to estimate , where $\mathb…
Adaptive Discretization in Online Reinforcement Learning
Sean R. Sinclair, Siddhartha Banerjee, Christina Lee Yu
Discretization based approaches to solving online reinforcement learning problems have been studied extensively in practice on applications ranging from resource allocation to cach…
Sequential Fair Allocation: Achieving the Optimal Envy-Efficiency Tradeoff Curve
Sean R. Sinclair, Gauri Jain, Siddhartha Banerjee +1
We consider the problem of dividing limited resources to individuals arriving over rounds. Each round has a random number of individuals arrive, and individuals can be characte…
Sequential Fair Allocation of Limited Resources under Stochastic Demands
Sean R. Sinclair, Gauri Jain, Siddhartha Banerjee +1
We consider the problem of dividing limited resources between a set of agents arriving sequentially with unknown (stochastic) utilities. Our goal is to find a fair allocation - one…
Tensor Completion with Nearly Linear Samples Given Weak Side Information
Christina Lee Yu, Xumei Xi
Tensor completion exhibits an interesting computational-statistical gap in terms of the number of samples needed to perform tensor estimation. While there are only degrees…
Adaptive Discretization for Model-Based Reinforcement Learning
Sean R. Sinclair, Tianyu Wang, Gauri Jain +2
We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action sp…
Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces
Sean R. Sinclair, Siddhartha Banerjee, Christina Lee Yu
We present an efficient algorithm for model-free episodic reinforcement learning on large (potentially continuous) state-action spaces. Our algorithm is based on a novel -learni…
Nonparametric Contextual Bandits in an Unknown Metric Space
Nirandika Wanigasekara, Christina Lee Yu
Consider a nonparametric contextual multi-arm bandit problem where each arm is associated to a nonparametric reward function mapping from co…
Robust Max Entrywise Error Bounds for Tensor Estimation from Sparse Observations via Similarity Based Collaborative Filtering
Devavrat Shah, Christina Lee Yu
Consider the task of estimating a 3-order tensor from noisy observations of randomly chosen entries in the sparse regime. We introduce a similarity based coll…
Iterative Collaborative Filtering for Sparse Matrix Estimation
Christian Borgs, Jennifer Chayes, Devavrat Shah +1
We consider sparse matrix estimation where the goal is to estimate an matrix from noisy observations of a small subset of its entries. We analyze the estimation error o…
Nearest Neighbors for Matrix Estimation Interpreted as Blind Regression for Latent Variable Model
Yihua Li, Devavrat Shah, Dogyoon Song +1
We consider the setup of nonparametric {\em blind regression} for estimating the entries of a large matrix, when provided with a small, random fraction of noisy measur…