no code implementations • 1 Aug 2024 • Haoran Xu, Peter W. Glynn, Yinyu Ye

When there is only a single type of resource and the decision maker knows the total number of customers, we propose an algorithm with a $O(\log K)$ regret upper bound and provide a $\Omega(\log K)$ regret lower bound.

1 code implementation • 24 Jun 2024 • Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding, Chenwei Wu, Yinyu Ye, Zhi-Quan Luo, Ruoyu Sun

We find that $\geq$ 90% of these learning rates in $v$ could be harmlessly removed if we (1) carefully partition the parameters into blocks following our proposed principle on Hessian structure; (2) assign a single but good learning rate to each parameter block.

no code implementations • 20 Mar 2024 • Zihao Li, Hui Yuan, Kaixuan Huang, Chengzhuo Ni, Yinyu Ye, Minshuo Chen, Mengdi Wang

In this paper, we focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization over complex structured variables.

no code implementations • 26 Feb 2024 • Jiashuo Jiang, Yinyu Ye

To be specific, our algorithm operates in the primal space and we resolve the primal LP for the CMDP problem at each period in an online manner, with \textit{adaptive} remaining resource capacities.

no code implementations • 12 Feb 2024 • Yinyu Ye, Shijing Chen, Dong Ni, Ruobing Huang

Different diseases, such as histological subtypes of breast lesions, have severely varying incidence rates.

no code implementations • 11 Feb 2024 • Wenzhi Gao, Chunlin Sun, Chenyu Xue, Dongdong Ge, Yinyu Ye

Online linear programming plays an important role in both revenue management and resource allocation, and recent research has focused on developing efficient first-order online learning algorithms.

no code implementations • 12 Oct 2023 • Boyu Pang, Ruizhi Liao, Yinyu Ye

This paper presents an integer programming-based optimal sensor allocation model to ensure the detection accuracy of the scheme while using the minimum number of sensing kits or probing vehicles.

no code implementations • 21 Aug 2023 • Jiyuan Tan, Chenyu Xue, Chuwen Zhang, Qi Deng, Dongdong Ge, Yinyu Ye

In this paper, we propose the stochastic homogeneous second-order descent method (SHSODM) for stochastic functions enjoying gradient dominance property based on a recently proposed homogenization approach.

no code implementations • 2 Jun 2023 • Minshuo Chen, Jie Meng, Yu Bai, Yinyu Ye, H. Vincent Poor, Mengdi Wang

We present algorithms and establish near-optimal regret upper and lower bounds, of the form $\tilde{\mathcal{O}}(\sqrt{{\rm poly}(H) SAK})$, for RL in the delayed and missing observation settings.

no code implementations • 21 May 2023 • Yanguang Chen, Wenzhi Gao, Dongdong Ge, Yinyu Ye

We propose a new method to accelerate online Mixed Integer Optimization with Pre-trained machine learning models (PreMIO).

no code implementations • 28 Jan 2023 • Jinsong Liu, Chenghan Xie, Qi Deng, Dongdong Ge, Yinyu Ye

In this paper, we propose several new stochastic second-order algorithms for policy optimization that only require gradient and Hessian-vector product in each iteration, making them computationally efficient and comparable to policy gradient methods.

1 code implementation • 2 Sep 2022 • Zhaonan Qu, Wenzhi Gao, Oliver Hinder, Yinyu Ye, Zhengyuan Zhou

Moreover, our implementation of customized solvers, combined with a random row/column sampling step, can find near-optimal diagonal preconditioners for matrices up to size 200, 000 in reasonable time, demonstrating their practical appeal.

3 code implementations • 30 Jul 2022 • Chuwen Zhang, Dongdong Ge, Chang He, Bo Jiang, Yuntian Jiang, Yinyu Ye

In this paper, we propose a Dimension-Reduced Second-Order Method (DRSOM) for convex and nonconvex (unconstrained) optimization.

no code implementations • 1 Jul 2022 • Chaoyu Chen, Xin Yang, Ruobing Huang, Xindi Hu, Yankai Huang, Xiduo Lu, Xinrui Zhou, Mingyuan Luo, Yinyu Ye, Xue Shuang, Juzheng Miao, Yi Xiong, Dong Ni

In this work, we propose to revisit the classic regression tasks with novel investigations on directly optimizing the fine-grained correlation losses.

no code implementations • 27 Apr 2022 • Devansh Jalota, Yinyu Ye

In this setting, we first study the limitations of static pricing algorithms, which set uniform prices for all users, along two performance metrics: (i) regret, i. e., the optimality gap in the objective of the Eisenberg-Gale program between an online algorithm and an oracle with complete information, and (ii) capacity violations, i. e., the over-consumption of goods relative to their capacities.

no code implementations • 27 Oct 2021 • Guanting Chen, Xiaocheng Li, Yinyu Ye

On a high level, we define the fairness in a way that a fair online algorithm should treat similar agents/customers similarly, and the decision made for similar agents/customers should be consistent over time.

no code implementations • 23 Jul 2021 • Guanting Chen, Johann Demetrio Gaebler, Matt Peng, Chunlin Sun, Yinyu Ye

Value iteration is a well-known method of solving Markov Decision Processes (MDPs) that is simple to implement and boasts strong theoretical convergence guarantees.

no code implementations • 6 Jul 2021 • Zhengyuan Zhou, Panayotis Mertikopoulos, Nicholas Bambos, Peter W. Glynn, Yinyu Ye

One of the most widely used methods for solving large-scale stochastic optimization problems is distributed asynchronous stochastic gradient descent (DASGD), a family of algorithms that result from parallelizing stochastic gradient descent on distributed computing architectures (possibly) asychronously.

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.

1 code implementation • 18 Feb 2021 • Dongdong Ge, Chengwenjian Wang, Zikai Xiong, Yinyu Ye

The crossover method, which aims at deriving an optimal extreme point from a suboptimal solution (the output of a starting method such as interior-point methods or first-order methods), is crucial in this process.

Optimization and Control 90C05

no code implementations • 12 Feb 2021 • Xiaocheng Li, Chunlin Sun, Yinyu Ye

In this paper, we study the bandits with knapsacks (BwK) problem and develop a primal-dual based algorithm that achieves a problem-dependent logarithmic regret bound.

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.

no code implementations • 23 Jun 2020 • Masoud Badiei Khuzani, Yinyu Ye, Sandy Napel, Lei Xing

In particular, we prove that in the scaling limits, the empirical measure of the Langevin particles converges to the law of a reflected It\^{o} diffusion-drift process.

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.

1 code implementation • NeurIPS 2020 • Xiaocheng Li, Chunlin Sun, Yinyu Ye

In this paper, we develop a simple and fast online algorithm for solving a class of binary integer linear programs (LPs) arisen in general resource allocation problem.

Data Structures and Algorithms Optimization and Control

no code implementations • 12 Sep 2019 • Xiaocheng Li, Yinyu Ye

We study an online linear programming (OLP) problem under a random input model in which the columns of the constraint matrix along with the corresponding coefficients in the objective function are generated i. i. d.

no code implementations • 29 Aug 2019 • Aaron Sidford, Mengdi Wang, Lin F. Yang, Yinyu Ye

In this paper, we settle the sampling complexity of solving discounted two-player turn-based zero-sum stochastic games up to polylogarithmic factors.

1 code implementation • 3 Jul 2019 • Mingxi Zhu, Kresimir Mihic, Yinyu Ye

In this paper, we apply this method to solving few selected machine learning problems related to convex quadratic optimization, such as Linear Regression, LASSO, Elastic-Net, and SVM.

no code implementations • NeurIPS 2019 • Dongdong Ge, Haoyue Wang, Zikai Xiong, Yinyu Ye

Computing the Wasserstein barycenter of a set of probability measures under the optimal transport metric can quickly become prohibitive for traditional second-order algorithms, such as interior-point methods, as the support size of the measures increases.

no code implementations • NeurIPS 2018 • Zhengyuan Zhou, Panayotis Mertikopoulos, Susan Athey, Nicholas Bambos, Peter W. Glynn, Yinyu Ye

We consider a game-theoretical multi-agent learning problem where the feedback information can be lost during the learning process and rewards are given by a broad class of games known as variationally stable games.

no code implementations • NeurIPS 2018 • Aaron Sidford, Mengdi Wang, Xian Wu, Lin Yang, Yinyu Ye

In this paper we consider the problem of computing an $\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any state-action pair samples from the transition function in $O(1)$ time.

no code implementations • ICML 2018 • Zhengyuan Zhou, Panayotis Mertikopoulos, Nicholas Bambos, Peter Glynn, Yinyu Ye, Li-Jia Li, Li Fei-Fei

One of the most widely used optimization methods for large-scale machine learning problems is distributed asynchronous stochastic gradient descent (DASGD).

1 code implementation • 5 Jun 2018 • Aaron Sidford, Mengdi Wang, Xian Wu, Lin F. Yang, Yinyu Ye

In this paper we consider the problem of computing an $\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any state-action pair samples from the transition function in $O(1)$ time.

Optimization and Control

1 code implementation • 31 May 2018 • Tianyi Lin, Shiqian Ma, Yinyu Ye, Shuzhong Zhang

Due its connection to Newton's method, IPM is often classified as second-order method -- a genre that is attached with stability and accuracy at the expense of scalability.

Optimization and Control

1 code implementation • 27 Oct 2017 • Aaron Sidford, Mengdi Wang, Xian Wu, Yinyu Ye

Given a discounted Markov Decision Process (DMDP) with $|S|$ states, $|A|$ actions, discount factor $\gamma\in(0, 1)$, and rewards in the range $[-M, M]$, we show how to compute an $\epsilon$-optimal policy, with probability $1 - \delta$ in time \[ \tilde{O}\left( \left(|S|^2 |A| + \frac{|S| |A|}{(1 - \gamma)^3} \right) \log\left( \frac{M}{\epsilon} \right) \log\left( \frac{1}{\delta} \right) \right) ~ .

1 code implementation • 23 Jul 2017 • Gabriel Haeser, Oliver Hinder, Yinyu Ye

Alternatively, in the convex case, if the primal feasibility is reduced too fast and the set of Lagrange multipliers is unbounded, then the Lagrange multiplier sequence generated will be unbounded.

Optimization and Control

no code implementations • 24 Jan 2011 • Zizhuo Wang, Shiming Deng, Yinyu Ye

The relationship between the action and the demand rate is not known in advance.

no code implementations • 16 Nov 2009 • Shipra Agrawal, Zizhuo Wang, Yinyu Ye

A natural optimization model that formulates many online resource allocation and revenue management problems is the online linear program (LP) in which the constraint matrix is revealed column by column along with the corresponding objective coefficient.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.