Vashist Avadhanula
Vashist Avadhanula has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Assaf Zeevi
Columbia University
2 shared publications - Vineet Goyal
Department of Industrial Engineering and Operations Research, Columbia University, New York, New York 10027
2 shared publications - Amine Allouah
MyCustomAI, Santa Clara, USA
1 shared publication - Anil Dania
Meta, Menlo Park, CA, USA
1 shared publication Assaf Zeevi
Decision, Risk, and Operations Division, Columbia Business School, Columbia University, New York, New York 10027
1 shared publication- Caner Gocmen
Meta Platforms Inc
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Mathematics of Operations Research
- Vol. 51 (1) , 568-590
Thompson Sampling for the Multinomial Logit Bandit
We consider a dynamic combinatorial optimization problem where at each time step, the decision maker selects a subset of cardinality K from N possible items and observes a feedback in the form of the index of one of the items in the said subset or none. Each of the N items is ascribed a certain value (reward), which is collected if the item is chosen. This problem is motivated by that of assortment selection in online retail, where items are products. Akin to that literature, it is assumed that the choice of the item given the subset is governed by a multinomial logit (MNL) choice model whose parameters are a priori unknown. The objective of the decision maker is to maximize the expected cumulative rewards over a finite horizon T or alternatively, minimize the regret relative to an oracle that knows the MNL choice model parameters. We formulate this problem as a multiarmed bandit problem that we refer to as the MNL-bandit problem. We present a Thompson sampling-based algorithm for this problem and show that it achieves near-optimal regret as well as attractive empirical performance. Funding: S. Agrawal is supported in part by the Division of Civil, Mechanical and Manufacturing Innovation [NSF Grant 1846792]. V. Goyal is supported in part by the Division of Civil, Mechanical and Manufacturing Innovation [NSF Grants 1351838 and 1636046]. A. Zeevi is supported in part by the Division of Computer and Network Systems [NSF Grant 0964170] and the United States-Israel Binational Science Foundation [Grant 2010466].
- 1 January 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Mathematics of Operations Research
- Vol. 51 (1) , 568-590
Thompson Sampling for the Multinomial Logit Bandit
We consider a dynamic combinatorial optimization problem where at each time step, the decision maker selects a subset of cardinality K from N possible items and observes a feedback in the form of the index of one of the items in the said subset or none. Each of the N items is ascribed a certain value (reward), which is collected if the item is chosen. This problem is motivated by that of assortment selection in online retail, where items are products. Akin to that literature, it is assumed that the choice of the item given the subset is governed by a multinomial logit (MNL) choice model whose parameters are a priori unknown. The objective of the decision maker is to maximize the expected cumulative rewards over a finite horizon T or alternatively, minimize the regret relative to an oracle that knows the MNL choice model parameters. We formulate this problem as a multiarmed bandit problem that we refer to as the MNL-bandit problem. We present a Thompson sampling-based algorithm for this problem and show that it achieves near-optimal regret as well as attractive empirical performance. Funding: S. Agrawal is supported in part by the Division of Civil, Mechanical and Manufacturing Innovation [NSF Grant 1846792]. V. Goyal is supported in part by the Division of Civil, Mechanical and Manufacturing Innovation [NSF Grants 1351838 and 1636046]. A. Zeevi is supported in part by the Division of Computer and Network Systems [NSF Grant 0964170] and the United States-Israel Binational Science Foundation [Grant 2010466].
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 25-35
Fair Allocation Over Time, with Applications to Content Moderation
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 25-35
Open AccessFair Allocation Over Time, with Applications to Content Moderation
- Top Cited Papers
- 1 September 2019
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Operations Research
- Vol. 67 (5) , 1453-1485
MNL-Bandit: A Dynamic Learning Approach to Assortment Selection
We consider a dynamic assortment selection problem where in every round the retailer offers a subset (assortment) of N substitutable products to a consumer, who selects one of these products according to a multinomial logit (MNL) choice model. The retailer observes this choice, and the objective is to dynamically learn the model parameters while optimizing cumulative revenues over a selling horizon of length T. We refer to this exploration–exploitation formulation as the MNL-Bandit problem. Existing methods for this problem follow an explore-then-exploit approach, which estimates parameters to a desired accuracy and then, treating these estimates as if they are the correct parameter values, offers the optimal assortment based on these estimates. These approaches require certain a priori knowledge of “separability,” determined by the true parameters of the underlying MNL model, and this in turn is critical in determining the length of the exploration period. (Separability refers to the distinguishability of the true optimal assortment from the other suboptimal alternatives.) In this paper, we give an efficient algorithm that simultaneously explores and exploits, without a priori knowledge of any problem parameters. Furthermore, the algorithm is adaptive in the sense that its performance is near optimal in the “well-separated” case as well as the general parameter setting where this separation need not hold.
- 1 September 2019
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Operations Research
- Vol. 67 (5) , 1453-1485
Top Cited PapersMNL-Bandit: A Dynamic Learning Approach to Assortment Selection
We consider a dynamic assortment selection problem where in every round the retailer offers a subset (assortment) of N substitutable products to a consumer, who selects one of these products according to a multinomial logit (MNL) choice model. The retailer observes this choice, and the objective is to dynamically learn the model parameters while optimizing cumulative revenues over a selling horizon of length T. We refer to this exploration–exploitation formulation as the MNL-Bandit problem. Existing methods for this problem follow an explore-then-exploit approach, which estimates parameters to a desired accuracy and then, treating these estimates as if they are the correct parameter values, offers the optimal assortment based on these estimates. These approaches require certain a priori knowledge of “separability,” determined by the true parameters of the underlying MNL model, and this in turn is critical in determining the length of the exploration period. (Separability refers to the distinguishability of the true optimal assortment from the other suboptimal alternatives.) In this paper, we give an efficient algorithm that simultaneously explores and exploits, without a priori knowledge of any problem parameters. Furthermore, the algorithm is adaptive in the sense that its performance is near optimal in the “well-separated” case as well as the general parameter setting where this separation need not hold.
- 1 September 2016
- Published by Elsevier in Operations Research Letters
- Vol. 44 (5) , 612-617
On the tightness of an LP relaxation for rational optimization and its applications
- 1 September 2016
- Published by Elsevier in Operations Research Letters
- Vol. 44 (5) , 612-617
On the tightness of an LP relaxation for rational optimization and its applications