All Publications

2024

Learning Mixed Multinomial Logits with Provable Guarantees and its Applications in Multi-product Pricing

Management Science
2024

Utility Fairness in Contextual Dynamic Pricing with Demand Learning

Management Science
2024

On Greedy-like Policies in Online Matching with Reusable Network Resources and Decaying Rewards

Management Science
2024

Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition

NeurIPS
2024

Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff

NeurIPS
- Simchi-Levi D
- Wang C
2024

Multi-armed Bandit Experimental Design: Online Decision-making and Adaptive Inference

Management Science
2024

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

Management Science
- Simchi-Levi D
- Wang C
2024

Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk

Management Science
2023

Assortment Planning for Recommendations at Checkout under Inventory Constraints

Mathematics of Operations Research
2023

Non-Stationary Reinforcement Learning: The Blessing of (More) Optimism

Management Science
2023

Online Matching with Bayesian Rewards

Operations Research
2023

Offline Planning and Online Learning under Recovering Rewards

Management Science
2023

Non-stationary Experimental Design under Linear Trends

NeurIPS
2023

Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk

NeurIPS 2023 Spotlight (top 3%)
2023

Model-Free Non-Stationary Reinforcement Learning: Near-Optimal Regret and Applications in Multi-Agent Reinforcement Learning and Inventory Control

Management Science
2022

Trading Safety Stock for Service Response Time in Inventory Positioning

Production and Operations Management

(
Special Issue in celebration of POMs 30 years
)
2022

Calibrating Sales Forecast in a Pandemic Using Competitive Online Non-Parametric Regression

Management Science
2022

Sobolev Norm Learning Rates for Conditional Mean Embeddings

AISTAT 2022
- Gong X
- Simchi-Levi D
2022

Bandits atop Reinforcement Learning: Tackling Online Inventory Models with Cyclic Demands

Management Science
- Simchi-Levi D
- Xu Y
2022

Phase Transitions in Bandits with Switching Constraints

Management Science
2022

Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation

COLT 2022
2022

Estimating and Exploiting the Impact of Photo Layout: A Structural Approach

Management Science
2022

Design and Analysis of Switchback Experiments

Management Science
2022

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

NeurIPS 2022
2022

Learning Mixed Multinomial Logits with Provable Guarantees

NeurIPS 2022
2022

Context-Based Dynamic Pricing with Partially Linear Demand Model

NeurIPS 2022
- Ma W
- Simchi-Levi D
2022

Constructing Demand Curves from a Single Observation of Bundle Sales

WINE 2022
2022

A New Approach for Vehicle Routing with Stochastic Demand: Combining Route Assignment with Process Flexibility
2022

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

Management Science

68

(
12
)
2021

Data-Driven Approximation Schemes for Joint Pricing and Inventory Control Models

Management Science
- Simchi-Levi D
- Xu Y
2021

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

Mathematics of Operations Research
2021

Is Model-Free Learning Nearly Optimal for Non-Stationary RL?

ICML 2021
2021

Dynamic Planning and Learning under Recovering Rewards

ICML 2021
2021

Offline Pricing and Demand Learning with Censored Data

Management Science
2021

Dynamic Pricing and Inventory Control with Fixed Ordering Cost and Incomplete Demand Information

Management Science

Filter by Subject

Learning Mixed Multinomial Logits with Provable Guarantees and its Applications in Multi-product Pricing

Utility Fairness in Contextual Dynamic Pricing with Demand Learning

On Greedy-like Policies in Online Matching with Reusable Network Resources and Decaying Rewards

Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition

Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff

Multi-armed Bandit Experimental Design: Online Decision-making and Adaptive Inference

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

Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk

Assortment Planning for Recommendations at Checkout under Inventory Constraints

Non-Stationary Reinforcement Learning: The Blessing of (More) Optimism

Online Matching with Bayesian Rewards

Offline Planning and Online Learning under Recovering Rewards

Non-stationary Experimental Design under Linear Trends

Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk

Model-Free Non-Stationary Reinforcement Learning: Near-Optimal Regret and Applications in Multi-Agent Reinforcement Learning and Inventory Control

Trading Safety Stock for Service Response Time in Inventory Positioning

Calibrating Sales Forecast in a Pandemic Using Competitive Online Non-Parametric Regression

Sobolev Norm Learning Rates for Conditional Mean Embeddings

Bandits atop Reinforcement Learning: Tackling Online Inventory Models with Cyclic Demands

Phase Transitions in Bandits with Switching Constraints

Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation

Estimating and Exploiting the Impact of Photo Layout: A Structural Approach

Design and Analysis of Switchback Experiments

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

Learning Mixed Multinomial Logits with Provable Guarantees

Context-Based Dynamic Pricing with Partially Linear Demand Model

Constructing Demand Curves from a Single Observation of Bundle Sales

A New Approach for Vehicle Routing with Stochastic Demand: Combining Route Assignment with Process Flexibility

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

Data-Driven Approximation Schemes for Joint Pricing and Inventory Control Models

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

Is Model-Free Learning Nearly Optimal for Non-Stationary RL?

Dynamic Planning and Learning under Recovering Rewards

Offline Pricing and Demand Learning with Censored Data

Dynamic Pricing and Inventory Control with Fixed Ordering Cost and Incomplete Demand Information

Filter by Year