no code implementations • ICML 2020 • Nian Si, Fan Zhang, Zhengyuan Zhou, Jose Blanchet
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.
no code implementations • 4 Apr 2024 • Miao Lu, Han Zhong, Tong Zhang, Jose Blanchet
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.
no code implementations • 21 Mar 2024 • Jose Blanchet, Jiajin Li, Markus Pelger, Greg Zanotti
In this paper, we propose a novel conceptual framework to detect outliers using optimal transport with a concave cost function.
no code implementations • 13 Jan 2024 • Xinru Hua, Rasool Ahmad, Jose Blanchet, Wei Cai
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.
no code implementations • 15 Nov 2023 • Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
This is accomplished through a comprehensive modeling framework centered around distributionally robust Markov decision processes (DRMDPs).
no code implementations • 13 Oct 2023 • Shengbo Wang, Jose Blanchet, Peter Glynn
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 $\Omega(|S||A|t_{\text{mix}} \epsilon^{-2})$.
no code implementations • 10 Aug 2023 • Jose Blanchet, Daniel Kuhn, Jiajin Li, Bahar Taskesen
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.
no code implementations • 28 May 2023 • Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
Further, the variance-reduced distributionally robust Q-learning combines the synchronous Q-learning with variance-reduction techniques to enhance its performance.
no code implementations • 25 May 2023 • Jose Blanchet, Haoxuan Chen, Yiping Lu, Lexing Ying
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.
no code implementations • 11 Apr 2023 • Junrong Lin, Mahmudul Hasan, Pinar Acar, Jose Blanchet, Vahid Tarokh
Our method is effective and robust in finding optimal processing paths.
2 code implementations • 12 Mar 2023 • Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet
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.
no code implementations • 26 Feb 2023 • Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
We consider a reinforcement learning setting in which the deployment environment is different from the training environment.
no code implementations • 15 Feb 2023 • Shengbo Wang, Jose Blanchet, Peter Glynn
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).
no code implementations • 31 Jan 2023 • Xinru Hua, Truyen Nguyen, Tam Le, Jose Blanchet, Viet Anh Nguyen
The scarcity of labeled data is a long-standing challenge for many machine learning tasks.
no code implementations • 27 Jan 2023 • Zhipeng Liang, Xiaoteng Ma, Jose Blanchet, Jiheng Zhang, Zhengyuan Zhou
As a framework for sequential decision-making, Reinforcement Learning (RL) has been regarded as an essential component leading to Artificial General Intelligence (AGI).
no code implementations • 28 Nov 2022 • Yiping Lu, Jiajin Li, Lexing Ying, Jose Blanchet
The optimal design of experiments typically involves solving an NP-hard combinatorial optimization problem.
no code implementations • 4 Oct 2022 • Jiajin Li, Sirui Lin, Jose Blanchet, Viet Anh Nguyen
Distributionally robust optimization has been shown to offer a principled way to regularize learning models.
no code implementations • 28 Sep 2022 • Jikai Jin, Yiping Lu, Jose Blanchet, Lexing Ying
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.
no code implementations • 14 Sep 2022 • Xiaoteng Ma, Zhipeng Liang, Jose Blanchet, Mingwen Liu, Li Xia, Jiheng Zhang, Qianchuan Zhao, Zhengyuan Zhou
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).
no code implementations • 17 May 2022 • Jiajin Li, Jianheng Tang, Lemin Kong, Huikang Liu, Jia Li, Anthony Man-Cho So, Jose Blanchet
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.
no code implementations • 15 May 2022 • Yiping Lu, Jose Blanchet, Lexing Ying
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.
no code implementations • 14 Mar 2022 • Jin Xie, Teng Zhang, Jose Blanchet, Peter Glynn, Matthew Randolph, David Scheinker
In order for an algorithm to see sustained use, it must be compatible with changes to hospital capacity, patient volumes, and scheduling practices.
no code implementations • 23 Feb 2022 • Xuhui Zhang, Jose Blanchet, Soumyadip Ghosh, Mark S. Squillante
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.
no code implementations • 13 Feb 2022 • Yuan Shi, Saied Mahdian, Jose Blanchet, Peter Glynn, Andrew Y. Shin, David Scheinker
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.
no code implementations • NeurIPS 2021 • Carson Kent, Jiajin Li, Jose Blanchet, Peter W. Glynn
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).
no code implementations • 30 Nov 2021 • Xinru Hua, Huanzhong Xu, Jose Blanchet, Viet Nguyen
However, small perturbations which are imperceptible to humans may significantly degrade the performance of well-trained deep neural networks.
no code implementations • ICLR 2022 • Yiping Lu, Haoxuan Chen, Jianfeng Lu, Lexing Ying, Jose Blanchet
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).
no code implementations • NeurIPS 2021 • Tam Le, Truyen Nguyen, Makoto Yamada, Jose Blanchet, Viet Anh Nguyen
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.
no code implementations • 29 Sep 2021 • Truyen Nguyen, Xinru Hua, Tam Le, Jose Blanchet, Viet Anh Nguyen
The scarcity of labeled data is a long-standing challenge for cross-domain machine learning tasks.
no code implementations • NeurIPS Workshop DLDE 2021 • Yiping Lu, Haoxuan Chen, Jianfeng Lu, Lexing Ying, Jose Blanchet
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).
no code implementations • 4 Aug 2021 • Jose Blanchet, Karthyek Murthy, Viet Anh Nguyen
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.
no code implementations • 2 Jun 2021 • Nian Si, Karthyek Murthy, Jose Blanchet, Viet Anh Nguyen
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions.
1 code implementation • 1 Jun 2021 • Bahar Taskesen, Man-Chung Yue, Jose Blanchet, Daniel Kuhn, Viet Anh Nguyen
Given available data, we investigate novel strategies to synthesize a family of least squares estimator experts that are robust with regard to moment conditions.
1 code implementation • 30 Mar 2021 • Viet Anh Nguyen, Fan Zhang, Shanshan Wang, Jose Blanchet, Erick Delage, Yinyu Ye
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 code implementations • 8 Mar 2021 • Ilai Bistritz, Zhengyuan Zhou, Xi Chen, Nicholas Bambos, Jose Blanchet
Using these bounds, we show that FKM and EXP3 have no weighted-regret even for $d_{t}=O\left(t\log t\right)$.
no code implementations • 25 Feb 2021 • Jose Blanchet, Fernando Hernandez, Viet Anh Nguyen, Markus Pelger, Xuhui Zhang
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.
no code implementations • 9 Dec 2020 • Bahar Taskesen, Jose Blanchet, Daniel Kuhn, Viet Anh Nguyen
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.
no code implementations • NeurIPS 2020 • Nian Si, Jose Blanchet, Soumyadip Ghosh, Mark Squillante
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.
no code implementations • NeurIPS 2020 • Viet Anh Nguyen, Fan Zhang, Jose Blanchet, Erick Delage, Yinyu Ye
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.
1 code implementation • NeurIPS 2020 • Viet Anh Nguyen, Xuhui Zhang, Jose Blanchet, Angelos Georghiou
We consider the parameter estimation problem of a probabilistic generative model prescribed using a natural exponential family of distributions.
no code implementations • 13 Sep 2020 • Jose Blanchet, Yang Kang, Jose Luis Montiel Olea, Viet Anh Nguyen, Xuhui Zhang
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.
no code implementations • 18 Jul 2020 • Jose Blanchet, Henry Lam, Yang Liu, Ruodu Wang
We discuss relevant applications in risk management and economics.
no code implementations • 18 Jul 2020 • Bahar Taskesen, Viet Anh Nguyen, Daniel Kuhn, Jose Blanchet
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.
1 code implementation • ICML 2020 • Viet Anh Nguyen, Nian Si, Jose Blanchet
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.
no code implementations • 10 Jun 2020 • Nian Si, Fan Zhang, Zhengyuan Zhou, Jose Blanchet
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.
no code implementations • 14 Apr 2020 • Yanjun Han, Zhengqing Zhou, Zhengyuan Zhou, Jose Blanchet, Peter W. Glynn, Yinyu Ye
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.
no code implementations • 11 Mar 2020 • Jose Blanchet, Renyuan Xu, Zhengyuan Zhou
In this paper, we consider online learning in generalized linear contextual bandits where rewards are not immediately observed.
no code implementations • 6 Feb 2020 • Jose Blanchet, Fan Zhang, Bert Zwart
We consider a generic class of chance-constrained optimization problems with heavy-tailed (i. e., power-law type) risk factors.
Optimization and Control Probability
no code implementations • NeurIPS 2019 • Zhengyuan Zhou, Renyuan Xu, Jose Blanchet
In this paper, we consider online learning in generalized linear contextual bandits where rewards are not immediately observed.
no code implementations • NeurIPS 2019 • Ilai Bistritz, Zhengyuan Zhou, Xi Chen, Nicholas Bambos, Jose Blanchet
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.
no code implementations • 7 Jun 2019 • Saied Mahdian, Jose Blanchet, Peter Glynn
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.
no code implementations • 4 Jun 2019 • Jose Blanchet, Karthyek Murthy, Nian Si
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.
no code implementations • 20 May 2019 • Jose Blanchet, Yang Kang, Fan Zhang, Zhangyi Hu
Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation.
no code implementations • 30 Jan 2019 • Casey Chu, Jose Blanchet, Peter Glynn
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.
no code implementations • NeurIPS 2019 • Virag Shah, Jose Blanchet, Ramesh Johari
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.
1 code implementation • 4 Oct 2018 • Jose Blanchet, Karthyek Murthy, Fan Zhang
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
no code implementations • NeurIPS 2018 • Virag Shah, Jose Blanchet, Ramesh Johari
In other words, arrivals exhibit positive externalities.
no code implementations • 19 May 2017 • Jose Blanchet, Yang Kang, Fan Zhang, Fei He, Zhangyi Hu
Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms.
no code implementations • 19 May 2017 • Jose Blanchet, Yang Kang, Fan Zhang, Karthyek Murthy
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.
no code implementations • 28 Feb 2017 • Jose Blanchet, Yang Kang
We propose a novel method for semi-supervised learning (SSL) based on data-driven distributionally robust optimization (DRO) using optimal transport metrics.