Optimal policy for dynamic assortment planning under MNL model with O ( T ) O(\sqrt{T}) O ( T ) regret.
problem Maximizing revenue in dynamic assortment planning under MNL model with unknown parameters.
method Trisection-based policy with adaptive confidence bounds.
result Achieves O ( T ) O(\sqrt{T}) O ( T ) regret bound, independent of the number of products. Study proves a tight lower bound for MNL-Bandit assortment selection problems.
problem Dynamic assortment planning under MNL bandit model with capacity constraints.
method Proved a tight lower bound on accumulated regret for all parameters.
result Tight lower bound matches existing upper bounds up to logarithmic factors.
Study dynamic assortment planning under nested logit models for revenue maximization.
problem Maximize revenue by dynamically selecting assortments of products during a selling season.
method Developed a novel UCB policy that learns and makes decisions based on customers' choice behavior.
result Achieved accumulated regret of i l d e O ( M N T ) ilde{O}(\sqrt{MNT}) i l d e O ( M N T ) with a lower bound of Ω ( M T ) Ω(\sqrt{MT}) Ω ( M T ) . Proposes balancing revenue and environmental impact in assortment planning.
problem Maximizing revenue while considering environmental impact in retail assortment planning.
method Multi-objective optimization using Higg Material Sustainability Index.
result Shows it's possible to have lower environmental impact without significant revenue loss.
We consider the problem of learning the preferences of a heterogeneous population by observing choices from an assortment of products, ads, or other offerings. Our observation model takes a form common in assortment planning applications: each arriving customer is offered an assortment consisting of a subset of all pos…
SRL embeds combinatorial optimization into RL for better decision-making.
problem Challenges of standard RL in complex, structured decision-making problems.
method Structured Reinforcement Learning (SRL) with combinatorial optimization layers in actor neural network.
result SRL outperforms unstructured RL and imitation learning by up to 92% on dynamic problems.
This work studies the parameter identification problem for the Markov chain choice model of Blanchet, Gallego, and Goyal used in assortment planning. In this model, the product selected by a customer is determined by a Markov chain over the products, where the products in the offered assortment are absorbing states. Th…
Analyzes fashion demand to optimize style mix in retail.
problem Optimizing fashion assortment planning in retail.
method Derives a style quotient from customer demand data, decoupling style from price.
result Shows the relationship between customer perception and retailer's style mix.
A new model predicts fashion demand 6-12 months ahead, boosting retailer profits.
problem Accurate demand forecasting for fashion retailers with short product life cycles.
method Product age-based forecast model, incorporating unique feature engineering.
result Significant revenue uplift of 41% compared to retailer's plan.
Proposes robust assortment optimization from observational data.
problem Real-world scenarios often violate assumptions of stable customer preferences and correct choice models.
method Develops a robust framework that accounts for potential distributional shifts in customer choice behavior.
result Uncovered the notion of ``robust item-wise coverage'' as the minimal data requirement for sample-efficient robust assortment learning.
New model optimizes assortment and pricing with dynamic customer arrivals.
problem Suboptimal decisions in classical models due to fixed arrival rates.
method Poisson-MNL model with UCB algorithm for dynamic decisions.
result Efficient algorithm achieves near optimal cumulative revenue.
New algorithm tackles dynamic assortment optimization with knapsack constraints.
problem Optimizing retailer's assortment decisions under resource constraints with multi-nomial choice modeling.
method Epoch-based re-solving algorithm that transforms MNL's fractional structure into a linear program with slack variables.
result Regret scales logarithmically with time horizon and resource capacities.
Dynamic assortment problem on two-sided platform with unknown parameters
problem Optimizing assortment display in an online platform with incomplete information and heterogeneous customers
method Data-driven algorithm that learns choice parameters while optimizing revenue
result Worst-case regret grows polylogarithmically over time
Paper presents a privacy-preserving method for dynamic assortment selection.
problem Personalized assortment recommendations with data privacy concerns.
method Perturbed upper confidence bound method integrating calibrated noise.
result Policy satisfies Joint Differential Privacy (JDP) with near-optimal regret bound.
We study the problem of dynamic assortment personalization with large, heterogeneous populations and wide arrays of products, and demonstrate the importance of structural priors for effective, efficient large-scale personalization. Assortment personalization is the problem of choosing, for each individual (type), a bes…
Paper tackles dynamic assortment with dual contexts, improving revenue in e-commerce.
problem Maximizing revenue in e-commerce with personalized recommendations from vast catalogs.
method Low-rank dynamic assortment model and upper confidence bound approach.
result Regret bound of i l d e O ( ( d 1 + d 2 ) r T ) ilde{O}((d_1+d_2)r\sqrt{T}) i l d e O (( d 1 + d 2 ) r T ) for dynamic assortment problem. This paper optimizes product assortment decisions with changing contextual information.
problem Optimizing product assortment decisions in a dynamic context.
method Developed an upper confidence bound (UCB) policy to learn and make decisions under a changing contextual MNL model.
result Established a regret bound of O ~ ( d T ) \widetilde O(d\sqrt{T}) O ( d T ) and a lower bound of Ω ( d T / K ) Ω(d\sqrt{T}/K) Ω ( d T / K ) for dynamic assortment optimization. New policy optimizes product assortment in the presence of unpredictable customers.
problem Optimizing product assortment in the presence of outlier customers.
method Developed a robust online assortment optimization policy using an active elimination strategy.
result Established upper and lower bounds on regret, showing optimality up to logarithmic factor in T T T . Paper generalizes Markov chain model to handle dynamic preferences and choice overload.
problem Modeling dynamic customer substitution behavior in assortment optimization.
method Generalizes Markov chain model to account for choice overload.
result Proposes a Markov chain model that reduces to a generalized MNL model with assortment-dependent no-purchase attractions.
Study dynamic assortment and positioning of products with varying display effects.
problem Dynamic assortment and positioning of products with varying display effects.
method Design round-based learning algorithms for both multiplicative and general position effects models, and develop efficient subroutines for optimization.
result First regret-optimal characterization for both models, with matching upper and lower bounds.
PASTA optimizes assortment selection using pessimism principle.
problem Optimizing assortment selection with limited data coverage.
method Pessimistic Assortment Optimization (PASTA) based on the principle of pessimism.
result PASTA correctly identifies optimal assortment with minimal data coverage.
New model improves community detection in networks with strong assortativity.
problem Classic SBMs fail to recover assortative communities in networks with reduced information.
method Introduced a constrained SBM with strong assortativity constraints and efficient algorithms.
result Significant boost in community recovery capabilities, especially close to information-theoretic threshold.
Study optimal product assortment using historical data, proving item coverage suffices.
problem Offline assortment optimization under MNL model with limited historical data.
method Pessimistic Rank-Breaking (PRB) algorithm combining rank-breaking and pessimistic estimation.
result Optimal item coverage is both sufficient and necessary for efficient offline learning.
New algorithm reduces regret in dynamic assortment selection.
problem Dynamic assortment selection with consumer choice modeling.
method Optimistic algorithm with convex relaxation.
result Regret bound of O ( d T + κ ) O(\sqrt{dT} + κ) O ( d T + κ ) , improving over existing methods. Method infers assortative communities in networks without resolution limit.
problem Finding statistically significant assortative modules in networks.
method Nonparametric Bayesian formulation of the planted partition model.
result Method uncovers an arbitrarily large number of communities with statistical evidence.
Study optimizes dynamic product selection and pricing using censored preference feedback.
problem Maximizing revenue from dynamic assortment and pricing decisions.
method Proposes a censored multinomial logit model and LCB pricing strategy combined with UCB or TS product selection.
result Achieves optimal regret bounds for dynamic pricing and selection.
Improved neural network convergence with causal Bayesian modeling in retail performance.
problem Improving neural network convergence in retail performance models.
method Causal Bayesian neural network implementation, removal of weakest SEM path, Flipout layers, Vadam optimizer.
result Neural network convergence improved with removal of the weakest SEM path.
Study analyzes crude oil futures markets using visibility graphs to understand their structure and dynamics.
problem Understanding the structure and dynamics of crude oil futures markets during global challenges.
method Visibility graph analysis of daily and high-frequency data.
result Crude oil futures markets exhibit small-world properties and assortative mixing, with unique sensitivities to global disruptions.
PlaNet learns latent dynamics from images for better planning in unknown environments.
problem Leveraging planning in unknown environments with accurate dynamics models.
method Deep Planning Network (PlaNet) learns dynamics from images using latent space and multi-step variational inference.
result PlaNet achieves high performance in continuous control tasks with contact dynamics and sparse rewards.
Diffusion approximations optimize sequential experimentation for uncertain parameters.
problem Maximizing reward from unknown parameter Θ with delayed action.
method Bayesian sequential experimentation framework, dynamic programming, diffusion asymptotics.
result Derives diffusion approximation for optimal experimentation strategy.
VASE uses Bayesian neural networks to improve exploration in sparse reward environments.
problem Exploration in environments with continuous control and sparse rewards.
method VASE uses a Bayesian neural network model of the environment dynamics and variational inference to alternately update the model's accuracy and policy.
result VASE outperforms other surprise-based exploration techniques in continuous control sparse reward environments.
DPN combines model-based and model-free reinforcement learning for efficient planning.
problem Efficiently plan actions in reinforcement learning environments.
method Combines model-based and model-free reinforcement learning, dynamically constructing plans using a learned state-transition model.
result Reduces the number of state transitions during planning by up to 96%, improving data efficiency and performance.
New method uses autoregressive models for dynamic planning.
problem Planning in dynamic environments with moving obstacles and goals.
method Conditional autoregressive generative models in a discrete latent space.
result Method nearly matches true environment performance for planning.
New method uses multi-hop assortativity to classify network functionalities.
problem Classifying network functionalities based on structure and metadata.
method Introduces multi-hop assortativity to capture node similarity in paths.
result Multi-hop assortativity features outperform state-of-the-art methods in network classification.
Paper introduces ML for optimal motion planning in urban traffic.
problem Variations in search efficiency due to dynamic obstacles.
method Introduces machine learning-based heuristic for optimal motion planning considering dynamic obstacles.
result Added performance consistency for real-time implementation.
The paper proposes a method to test properties of the optimal assortment in multinomial logit models.
problem Uncertainty quantification for the optimal assortment in multinomial logit models.
method The paper proposes a novel inferential framework to test properties of the optimal assortment in multinomial logit models, reducing the problem to detecting the sign change point of marginal revenue gaps.
result The asymptotic normality of the marginal revenue gap estimator and the construction of a maximum statistic to detect the sign change point.
DMNL bandits optimize assortment choices balancing relevance and diversity.
problem Balancing relevance-driven choice with within-assortment diversity.
method Augments MNL choice probabilities with a submodular diversity function, proposing a white-box UCB-based algorithm.
result Achieves at least a ( 1 − 1 e + 1 ) (1-\frac{1}{e+1}) ( 1 − e + 1 1 ) -approximate regret bound of $ ilde{O}\left(d \sqrt{T/K}
ight)$ . Proposes DLGPD model to learn dynamics from images for planning.
problem Planning in unknown, indirectly observable environments.
method Deep latent Gaussian process dynamics model trained jointly with neural networks.
result Demonstrates improved data efficiency and transfer learning.
New algorithm reduces switching costs in multinomial logit bandit problems.
problem Minimizing switching costs in multinomial logit bandit problems.
method Proposed AT-DUCB and FH-DUCB algorithms with low assortment switching costs.
result AT-DUCB and FH-DUCB algorithms achieve almost optimal minimax regret with low switching costs.
Algorithm maximizes revenue from user choices with contextual information.
problem Maximizing revenue from user choices with contextual preference information.
method Proposes an algorithm that learns from user feedback and achieves a revenue regret of order \( \widetilde{O}(d \sqrt{K T} / L_0 ) \).
result Achieves a revenue regret of order \( \widetilde{O}(d \sqrt{K T} / L_0 ) \) and a lower bound of order \( \Omega(d \sqrt{T}/ L_0) \).
Regularizes model-based planning using energy-based models for efficient learning.
problem Challenges in using learned dynamics models for accurate planning.
method Regularization using energy estimates of state transitions.
result Proposes effective regularization method for planning with pre-trained dynamics models.
Paper presents a method for probabilistic load forecasting using adaptive online learning.
problem Inability to assess intrinsic uncertainties and capture dynamic changes in consumption patterns.
method Adaptive online learning of hidden Markov models for recursive parameter updates and sequential prediction.
result Significant improvement in performance compared to existing techniques across various scenarios.
Unified framework integrates symbolic planning and HRL for robust decision-making.
problem Combining reinforcement learning and symbolic planning for robust decision-making in dynamic environments.
method Integrates symbolic planning with hierarchical reinforcement learning to guide task execution and improve planning.
result Unified framework leads to rapid policy search and robust symbolic plans in complex domains.
This paper studies when particle filtering is efficient for planning in partially observed systems.
problem The efficiency of particle filtering for planning in partially observed linear dynamical systems.
method Coupling of ideal and approximate sequences to bound particle complexity.
result Polynomially many particles suffice for stable systems to approximate optimal planning.
AOP combines model-based planning with model-free learning to handle lifelong learning challenges.
problem Learning control in an online reset-free lifelong learning scenario where mistakes can compound and dynamics change.
method Adaptive Online Planning (AOP) that combines model-based planning with model-free learning, approximating uncertainty to call upon planning only when necessary.
result Achieves strong performance in lifelong learning challenges, gracefully adapting behaviors in the face of unpredictable changes.
Jointly tackles assortment and pricing in retail, using bandit models.
problem Maximizing revenue or profit in retail through optimal assortment and pricing.
method Contextual bandits with a flexible, interpretable model for high-dimensional contexts and actions.
result Proves lower regret compared to state-of-the-art methods in various bandit and pricing models.
Study optimizes product assortment for retailers with repeated exposures and patience costs.
problem Optimizing product assortment for online retailers with repeated exposures and varying consumer patience.
method Developed a cascade multinomial logit model to capture repeated exposures and patience costs.
result Proposed an approximation solution to the assortment optimization problem.
Proposes new methods for Markov chain choice models with panel data.
problem Dependence among transactions for the same customer in historical data.
method Expectation-maximization (EM) algorithms incorporating partial-ordering preference information.
result EM algorithms outperform traditional methods on synthetic and real datasets.