Search Results for author:
Found 60 papers, 6 papers with code
Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits
We first present a policy evaluation procedure in the ambiguous environment and also give a heuristic algorithm to solve the distributionally robust policy learning problems efficiently.
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm
Unlike previous work, which relies on a generative model or a pre-collected offline dataset enjoying good coverage of the deployment environment, we tackle robust RL via interactive data collection, where the learner interacts with the training environment only and refines the policy through trial and error.
Automatic Outlier Rectification via Optimal Transport
In this paper, we propose a novel conceptual framework to detect outliers using optimal transport with a concave cost function.
Accelerated Sampling of Rare Events using a Neural Network Bias Potential
In particular, we approximate the variance-free bias potential function with DNNs which is trained to maximize the probability of rare event transition under the importance potential function.
On the Foundation of Distributionally Robust Reinforcement Learning
This is accomplished through a comprehensive modeling framework centered around distributionally robust Markov decision processes (DRMDPs).
Optimal Sample Complexity for Average Reward Markov Decision Processes
In this context, the existing literature provides a sample complexity upper bound of $\widetilde O(|S||A|t_{\text{mix}}^2 \epsilon^{-2})$ and a lower bound of $\Omega(|S||A|t_{\text{mix}} \epsilon^{-2})$.
Unifying Distributionally Robust Optimization via Optimal Transport Theory
In the past few years, there has been considerable interest in two prominent approaches for Distributionally Robust Optimization (DRO): Divergence-based and Wasserstein-based methods.
Sample Complexity of Variance-reduced Distributionally Robust Q-learning
Further, the variance-reduced distributionally robust Q-learning combines the synchronous Q-learning with variance-reduction techniques to enhance its performance.
When can Regression-Adjusted Control Variates Help? Rare Events, Sobolev Embedding and Minimax Optimality
We demonstrate that this kind of quadrature rule can improve the Monte Carlo rate and achieve the minimax optimal rate under a sufficient smoothness assumption.
Neural Network Accelerated Process Design of Polycrystalline Microstructures
Our method is effective and robust in finding optimal processing paths.
A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data
This observation allows us to provide an approximation bound for the distance between the fixed-point set of BAPG and the critical point set of GW.
A Finite Sample Complexity Bound for Distributionally Robust Q-learning
We consider a reinforcement learning setting in which the deployment environment is different from the training environment.
Optimal Sample Complexity of Reinforcement Learning for Mixing Discounted Markov Decision Processes
We consider the optimal sample complexity theory of tabular reinforcement learning (RL) for maximizing the infinite horizon discounted reward in a Markov decision process (MDP).
Dynamic Flows on Curved Space Generated by Labeled Data
The scarcity of labeled data is a long-standing challenge for many machine learning tasks.
Single-Trajectory Distributionally Robust Reinforcement Learning
As a framework for sequential decision-making, Reinforcement Learning (RL) has been regarded as an essential component leading to Artificial General Intelligence (AGI).
Synthetic Principal Component Design: Fast Covariate Balancing with Synthetic Controls
The optimal design of experiments typically involves solving an NP-hard combinatorial optimization problem.
Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints
Distributionally robust optimization has been shown to offer a principled way to regularize learning models.
Minimax Optimal Kernel Operator Learning via Multilevel Training
Learning mappings between infinite-dimensional function spaces has achieved empirical success in many disciplines of machine learning, including generative modeling, functional data analysis, causal inference, and multi-agent reinforcement learning.
Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation
Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the training environment (e. g., a simulator).
Fast and Provably Convergent Algorithms for Gromov-Wasserstein in Graph Data
In this paper, we study the design and analysis of a class of efficient algorithms for computing the Gromov-Wasserstein (GW) distance tailored to large-scale graph learning tasks.
Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent
In this paper, we study the statistical limits in terms of Sobolev norms of gradient descent for solving inverse problem from randomly sampled noisy observations using a general class of objective functions.
The Design and Implementation of a Broadly Applicable Algorithm for Optimizing Intra-Day Surgical Scheduling
In order for an algorithm to see sustained use, it must be compatible with changes to hospital capacity, patient volumes, and scheduling practices.
A Class of Geometric Structures in Transfer Learning: Minimax Bounds and Optimality
In contrast, our study first illustrates the benefits of incorporating a natural geometric structure within a linear regression model, which corresponds to the generalized eigenvalue problem formed by the Gram matrices of both domains.
Surgical Scheduling via Optimization and Machine Learning with Long-Tailed Data
Using data from cardiovascular surgery patients with long and highly variable post-surgical lengths of stay (LOS), we develop a modeling framework to reduce recovery unit congestion.
Modified Frank Wolfe in Probability Space
We propose a novel Frank-Wolfe (FW) procedure for the optimization of infinite-dimensional functionals of probability measures - a task which arises naturally in a wide range of areas including statistical learning (e. g. variational inference) and artificial intelligence (e. g. generative adversarial networks).
Human Imperceptible Attacks and Applications to Improve Fairness
However, small perturbations which are imperceptible to humans may significantly degrade the performance of well-trained deep neural networks.
Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality
In this paper, we study the statistical limits of deep learning techniques for solving elliptic partial differential equations (PDEs) from random samples using the Deep Ritz Method (DRM) and Physics-Informed Neural Networks (PINNs).
Adversarial Regression with Doubly Non-negative Weighting Matrices
In this paper, we propose a novel and coherent scheme for kernel-reweighted regression by reparametrizing the sample weights using a doubly non-negative matrix.
Gradient flows on the feature-Gaussian manifold
The scarcity of labeled data is a long-standing challenge for cross-domain machine learning tasks.
Statistical Numerical PDE : Fast Rate, Neural Scaling Law and When it’s Optimal
In this paper, we study the statistical limits of deep learning techniques for solving elliptic partial differential equations (PDEs) from random samples using the Deep Ritz Method (DRM) and Physics-Informed Neural Networks (PINNs).
Statistical Analysis of Wasserstein Distributionally Robust Estimators
We consider statistical methods which invoke a min-max distributionally robust formulation to extract good out-of-sample performance in data-driven optimization and learning problems.
Testing Group Fairness via Optimal Transport Projections
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions.
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
Given available data, we investigate novel strategies to synthesize a family of least squares estimator experts that are robust with regard to moment conditions.
Robustifying Conditional Portfolio Decisions via Optimal Transport
Despite the non-linearity of the objective function in the probability measure, we show that the distributionally robust portfolio allocation with side information problem can be reformulated as a finite-dimensional optimization problem.
No Weighted-Regret Learning in Adversarial Bandits with Delays
Using these bounds, we show that FKM and EXP3 have no weighted-regret even for $d_{t}=O\left(t\log t\right)$.
Time-Series Imputation with Wasserstein Interpolation for Optimal Look-Ahead-Bias and Variance Tradeoff
Imputation methods in time-series data often are applied to the full panel data with the purpose of training a model for a downstream out-of-sample task.
A Statistical Test for Probabilistic Fairness
Leveraging the geometry of the feature space, the test statistic quantifies the distance of the empirical distribution supported on the test samples to the manifold of distributions that render a pre-trained classifier fair.
Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality
We consider the problem of estimating the Wasserstein distance between the empirical measure and a set of probability measures whose expectations over a class of functions (hypothesis class) are constrained.
Distributionally Robust Local Non-parametric Conditional Estimation
Conditional estimation given specific covariate values (i. e., local conditional estimation or functional estimation) is ubiquitously useful with applications in engineering, social and natural sciences.
Distributionally Robust Parametric Maximum Likelihood Estimation
We consider the parameter estimation problem of a probabilistic generative model prescribed using a natural exponential family of distributions.
Machine Learning's Dropout Training is Distributionally Robust Optimal
This paper shows that dropout training in Generalized Linear Models is the minimax solution of a two-player, zero-sum game where an adversarial nature corrupts a statistician's covariates using a multiplicative nonparametric errors-in-variables model.
Convolution Bounds on Quantile Aggregation
We discuss relevant applications in risk management and economics.
A Distributionally Robust Approach to Fair Classification
We propose a distributionally robust logistic regression model with an unfairness penalty that prevents discrimination with respect to sensitive attributes such as gender or ethnicity.
Robust Bayesian Classification Using an Optimistic Score Ratio
The optimistic score searches for the distribution that is most plausible to explain the observed outcomes in the testing sample among all distributions belonging to the contextual ambiguity set which is prescribed using a limited structural constraint on the mean vector and the covariance matrix of the underlying contextual distribution.
Distributionally Robust Batch Contextual Bandits
Leveraging this evaluation scheme, we further propose a novel learning algorithm that is able to learn a policy that is robust to adversarial perturbations and unknown covariate shifts with a performance guarantee based on the theory of uniform convergence.
Sequential Batch Learning in Finite-Action Linear Contextual Bandits
We study the sequential batch learning problem in linear contextual bandits with finite action sets, where the decision maker is constrained to split incoming individuals into (at most) a fixed number of batches and can only observe outcomes for the individuals within a batch at the batch's end.
Delay-Adaptive Learning in Generalized Linear Contextual Bandits
In this paper, we consider online learning in generalized linear contextual bandits where rewards are not immediately observed.
Efficient Scenario Generation for Heavy-tailed Chance Constrained Optimization
We consider a generic class of chance-constrained optimization problems with heavy-tailed (i. e., power-law type) risk factors.
Optimization and Control Probability
Learning in Generalized Linear Contextual Bandits with Stochastic Delays
In this paper, we consider online learning in generalized linear contextual bandits where rewards are not immediately observed.
Online EXP3 Learning in Adversarial Bandits with Delayed Feedback
An adversary chooses the cost of each arm in a bounded interval, and a sequence of feedback delays \left\{ d_{t}\right\} that are unknown to the player.
Optimal Transport Relaxations with Application to Wasserstein GANs
We propose a family of relaxations of the optimal transport problem which regularize the problem by introducing an additional minimization step over a small region around one of the underlying transporting measures.
Confidence Regions in Wasserstein Distributionally Robust Estimation
Wasserstein distributionally robust optimization estimators are obtained as solutions of min-max problems in which the statistician selects a parameter minimizing the worst-case loss among all probability models within a certain distance (in a Wasserstein sense) from the underlying empirical measure.
A Distributionally Robust Boosting Algorithm
Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation.
Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning
This paper provides a unifying view of a wide range of problems of interest in machine learning by framing them as the minimization of functionals defined on the space of probability measures.
Semi-parametric dynamic contextual pricing
Motivated by the application of real-time pricing in e-commerce platforms, we consider the problem of revenue-maximization in a setting where the seller can leverage contextual information describing the customer's history and the product's type to predict her valuation of the product.
Optimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes
We consider optimal transport based distributionally robust optimization (DRO) problems with locally strongly convex transport cost functions and affine decision rules.
Optimization and Control Primary: 90C15, Secondary: 65K05, 90C47
Bandit Learning with Positive Externalities
In other words, arrivals exhibit positive externalities.
Doubly Robust Data-Driven Distributionally Robust Optimization
Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms.
Data-driven Optimal Cost Selection for Distributionally Robust Optimization
Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be represented exactly as distributionally robust optimization (DRO) problems.
Semi-supervised Learning based on Distributionally Robust Optimization
We propose a novel method for semi-supervised learning (SSL) based on data-driven distributionally robust optimization (DRO) using optimal transport metrics.
