David Simchi-Levi

research

∙ 04/10/2023

Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk

We study the trade-off between expectation and tail risk for regret dist...

0 David Simchi-Levi, et al. ∙

research

∙ 06/07/2022

A Simple and Optimal Policy Design with Safety against Heavy-tailed Risk for Multi-armed Bandits

We design new policies that ensure both worst-case optimality for expect...

0 David Simchi-Levi, et al. ∙

research

∙ 04/16/2022

PAC-Bayesian Based Adaptation for Regularized Learning

In this paper, we propose a PAC-Bayesian a posteriori parameter selectio...

0 Prem Talwai, et al. ∙

research

∙ 11/21/2021

Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation

We consider the offline reinforcement learning problem, where the aim is...

0 Dylan J. Foster, et al. ∙

research

∙ 11/01/2021

Dynamic Pricing and Demand Learning on a Large Network of Products: A PAC-Bayesian Approach

We consider a seller offering a large network of N products over a time ...

0 Bora Keskin, et al. ∙

research

∙ 06/28/2021

Dynamic Planning and Learning under Recovering Rewards

Motivated by emerging applications such as live-streaming e-commerce, pr...

0 David Simchi-Levi, et al. ∙

research

∙ 05/16/2021

Sobolev Norm Learning Rates for Conditional Mean Embeddings

We develop novel learning rates for conditional mean embeddings by apply...

0 Prem Talwai, et al. ∙

research

∙ 10/07/2020

Near-Optimal Regret Bounds for Model-Free RL in Non-Stationary Episodic MDPs

We consider model-free reinforcement learning (RL) in non-stationary Mar...

2 Weichao Mao, et al. ∙

research

∙ 10/07/2020

Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective

In the classical multi-armed bandit problem, instance-dependent algorith...

10 Dylan J. Foster, et al. ∙

research

∙ 09/27/2020

Privacy-Preserving Dynamic Personalized Pricing with Demand Learning

The prevalence of e-commerce has made detailed customers' personal infor...

6 Xi Chen, et al. ∙

research

∙ 08/31/2020

Design and Analysis of Switchback Experiments

In switchback experiments, a firm sequentially exposes an experimental u...

0 Iavor Bojinov, et al. ∙

research

∙ 06/30/2020

Provably More Efficient Q-Learning in the Full-Feedback/One-Sided-Feedback Settings

We propose two new Q-learning algorithms, Full-Q-Learning (FQL) and Elim...

0 Xiao-Yue Gong, et al. ∙

research

∙ 06/24/2020

Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism

We consider un-discounted reinforcement learning (RL) in Markov decision...

0 Wang Chi Cheung, et al. ∙

research

∙ 05/02/2020

Online Learning and Optimization for Revenue Management Problems with Add-on Discounts

We study in this paper a revenue management problem with add-on discount...

0 David Simchi-Levi, et al. ∙

research

∙ 03/28/2020

Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability

We consider the general (stochastic) contextual bandit problem under the...

0 David Simchi-Levi, et al. ∙

research

∙ 11/04/2019

Network Revenue Management with Limited Switches: Known and Unknown Demand Distributions

This work is motivated by a practical concern from our retail partner. W...

0 David Simchi-Levi, et al. ∙

research

∙ 10/19/2019

Online Pricing with Offline Data: Phase Transition and Inverse Square Law

This paper investigates the impact of pre-existing offline data on onlin...

0 Jinzhi Bu, et al. ∙

research

∙ 08/26/2019

Multi-stage and Multi-customer Assortment Optimization with Inventory Constraints

We consider an assortment optimization problem where a customer chooses ...

0 Elaheh Fata, et al. ∙

research

∙ 07/20/2019

A Competitive Analysis of Online Knapsack Problems with Unit Density

We study an online knapsack problem where the items arrive sequentially ...

0 Will Ma, et al. ∙

research

∙ 06/07/2019

Reinforcement Learning under Drift

We propose algorithms with state-of-the-art dynamic regret bounds for un...

0 Wang Chi Cheung, et al. ∙

research

∙ 05/26/2019

Phase Transitions and Cyclic Phenomena in Bandits with Switching Constraints

We consider the classical stochastic multi-armed bandit problem with a c...

0 David Simchi-Levi, et al. ∙

research

∙ 05/12/2019

Algorithms for Online Matching, Assortment, and Pricing with Tight Weight-dependent Competitive Ratios

Motivated by the dynamic assortment offerings and item pricings occurrin...

0 Will Ma, et al. ∙

research

∙ 03/19/2019

Conservative Exploration for Semi-Bandits with Linear Generalization: A Product Selection Problem for Urban Warehouses

The recent rising popularity of ultra-fast delivery services on retail p...

0 Rong Jin, et al. ∙

research

∙ 03/04/2019

Hedging the Drift: Learning to Optimize under Non-Stationarity

We introduce general data-driven decision-making algorithms that achieve...

0 Wang Chi Cheung, et al. ∙

research

∙ 02/28/2019

Meta Dynamic Pricing: Learning Across Experiments

We study the problem of learning across a sequence of price experiments ...

0 Hamsa Bastani, et al. ∙

research

∙ 01/09/2019

The Lingering of Gradients: How to Reuse Gradients over Time

Classically, the time complexity of a first-order method is estimated by...

0 Zeyuan Allen-Zhu, et al. ∙

research

∙ 11/02/2018

Dynamic Pricing under a Static Calendar

This work is motivated by our collaboration with a large Consumer Packag...

0 Will Ma, et al. ∙

research

∙ 10/25/2018

On Policies for Single-leg Revenue Management with Limited Demand Information

In this paper we study the single-leg revenue management problem, with n...

0 Will Ma, et al. ∙

research

∙ 10/11/2018

Inventory Balancing with Online Learning

We study a general problem of allocating limited resources to heterogene...

0 Wang Chi Cheung, et al. ∙

research

∙ 10/06/2018

Learning to Optimize under Non-Stationarity

We introduce algorithms that achieve state-of-the-art dynamic regret bou...

0 Wang Chi Cheung, et al. ∙

research

∙ 09/12/2017

A Practically Competitive and Provably Consistent Algorithm for Uplift Modeling

Randomized experiments have been critical tools of decision making for d...

0 Yan Zhao, et al. ∙

research

∙ 05/23/2017

Uplift Modeling with Multiple Treatments and General Response Types

Randomized experiments have been used to assist decision-making in many ...

0 Yan Zhao, et al. ∙

David Simchi-Levi

Featured Co-authors