Clear Filters

67 Hits in 0.2 sec

KATRec: Knowledge Aware aTtentive Sequential Recommendations [article]

Mehrnaz Amjadi, Seyed Danial Mohseni Taheri, Theja Tulabandhula
2021 arXiv   pre-print
Sequential recommendation systems model dynamic preferences of users based on their historical interactions with platforms. Despite recent progress, modeling short-term and long-term behavior of users in such systems is nontrivial and challenging. To address this, we present a solution enhanced by a knowledge graph called KATRec (Knowledge Aware aTtentive sequential Recommendations). KATRec learns the short and long-term interests of users by modeling their sequence of interacted items and
more » ... cted items and leveraging pre-existing side information through a knowledge graph attention network. Our novel knowledge graph-enhanced sequential recommender contains item multi-relations at the entity-level and users' dynamic sequences at the item-level. KATRec improves item representation learning by considering higher-order connections and incorporating them in user preference representation while recommending the next item. Experiments on three public datasets show that KATRec outperforms state-of-the-art recommendation models and demonstrates the importance of modeling both temporal and side information to achieve high-quality recommendations.
arXiv:2012.03323v2 fatcat:iuggpzvosnhgrlqewbrkv2xfsi

ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators [article]

Shamma Nasrin, Ahish Shylendra, Yuti Kadakia, Nick Iliev, Wilfred Gomes, Theja Tulabandhula, Amit Ranjan Trivedi
2021 arXiv   pre-print
This work proposes a novel Energy-Aware Network Operator Search (ENOS) approach to address the energy-accuracy trade-offs of a deep neural network (DNN) accelerator. In recent years, novel inference operators have been proposed to improve the computational efficiency of a DNN. Augmenting the operators, their corresponding novel computing modes have also been explored. However, simplification of DNN operators invariably comes at the cost of lower accuracy, especially on complex processing tasks.
more » ... x processing tasks. Our proposed ENOS framework allows an optimal layer-wise integration of inference operators and computing modes to achieve the desired balance of energy and accuracy. The search in ENOS is formulated as a continuous optimization problem, solvable using typical gradient descent methods, thereby scalable to larger DNNs with minimal increase in training cost. We characterize ENOS under two settings. In the first setting, for digital accelerators, we discuss ENOS on multiply-accumulate (MAC) cores that can be reconfigured to different operators. ENOS training methods with single and bi-level optimization objectives are discussed and compared. We also discuss a sequential operator assignment strategy in ENOS that only learns the assignment for one layer in one training step, enabling greater flexibility in converging towards the optimal operator allocations. Furthermore, following Bayesian principles, a sampling-based variational mode of ENOS is also presented. ENOS is characterized on popular DNNs ShuffleNet and SqueezeNet on CIFAR10 and CIFAR100.
arXiv:2104.05217v1 fatcat:aw66hzjb6je3peanwot7babewy

A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning [article]

Lesia Semenova, Cynthia Rudin, Ronald Parr
2021 arXiv   pre-print
Acknowledgments We thank Theja Tulabandhula, Aaron Fisher, Zhi Chen, and Fulton Wang for comments on the manuscript.  ...  ., 2018; Tulabandhula and Rudin, 2014b; Meinshausen and Bühlmann, 2010; Letham et al., 2016; Nevo and Ritov, 2017) .  ...  hypothesis space F that have training performance close to the best model in the class, according to a loss function (Breiman et al., 2001; Srebro et al., 2010; Fisher et al., 2019; Coker et al., 2018; Tulabandhula  ... 
arXiv:1908.01755v3 fatcat:zwzifjshubamrfcf4s5hzcumjm

Incentivizing Exploration in Linear Bandits under Information Gap [article]

Huazheng Wang, Haifeng Xu, Chuanhao Li, Zhiyuan Liu, Hongning Wang
2021 arXiv   pre-print
Agrawal & Tulabandhula (2020) considered heterogeneous contexts in a contextual bandit setting.  ... 
arXiv:2104.03860v1 fatcat:wkjfjzww2rcj7ouhgjgt6njwwi

A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit [article]

Priyank Agrawal, Vashist Avadhanula, Theja Tulabandhula
2021 arXiv   pre-print
In this paper, we consider the contextual variant of the MNL-Bandit problem. More specifically, we consider a dynamic set optimization problem, where in every round a decision maker offers a subset (assortment) of products to a consumer, and observes their response. Consumers purchase products so as to maximize their utility. We assume that the products are described by a set of attributes and the mean utility of a product is linear in the values of these attributes. We model consumer choice
more » ... consumer choice behavior by means of the widely used Multinomial Logit (MNL) model, and consider the decision maker's problem of dynamically learning the model parameters, while optimizing cumulative revenue over the selling horizon $T$. Though this problem has attracted considerable attention in recent times, many existing methods often involve solving an intractable non-convex optimization problem and their theoretical performance guarantees depend on a problem dependent parameter which could be prohibitively large. In particular, existing algorithms for this problem have regret bounded by $O(\sqrt{\kappa d T})$, where $\kappa$ is a problem dependent constant that can have exponential dependency on the number of attributes. In this paper, we propose an optimistic algorithm and show that the regret is bounded by $O(\sqrt{dT} + \kappa)$, significantly improving the performance over existing methods. Further, we propose a convex relaxation of the optimization step which allows for tractable decision-making while retaining the favourable regret guarantee.
arXiv:2011.14033v3 fatcat:6f3w7kmd5ff65jzyitspfjatoe

Optimizing Revenue while showing Relevant Assortments at Scale [article]

Theja Tulabandhula and Deeksha Sinha and Saketh Karra
2021 arXiv   pre-print
Scalable real-time assortment optimization has become essential in e-commerce operations due to the need for personalization and the availability of a large variety of items. While this can be done when there are simplistic assortment choices to be made, the optimization process becomes difficult when imposing constraints on the collection of relevant assortments based on insights by store-managers and historically well-performing assortments. We design fast and flexible algorithms based on
more » ... rithms based on variations of binary search that find the (approximately) optimal assortment in this difficult regime. In particular, we revisit the problem of large-scale assortment optimization under the multinomial logit choice model without any assumptions on the structure of the feasible assortments. We speed up the comparison steps using advances in similarity search in the field of information retrieval/machine learning. For an arbitrary collection of assortments, our algorithms can find a solution in time that is sub-linear in the number of assortments, and for the simpler case of cardinality constraints - linear in the number of items (existing methods are quadratic or worse). Empirical validations using a real world dataset (in addition to experiments using semi-synthetic data based on the Billion Prices dataset and several retail transaction datasets) show that our algorithms are competitive even when the number of items is $\sim 10^5$ ($10\times$ larger instances than previously studied).
arXiv:2003.04736v2 fatcat:uvkg7noai5g4bcjell7i2jsp3a

Probabilistic Localization of Insect-Scale Drones on Floating-Gate Inverter Arrays [article]

Priyesh Shukla, Ankith Muralidhar, Nick Iliev, Theja Tulabandhula, Sawyer B. Fuller, Amit Ranjan Trivedi
2021 arXiv   pre-print
We propose a novel compute-in-memory (CIM)-based ultra-low-power framework for probabilistic localization of insect-scale drones. The conventional probabilistic localization approaches rely on the three-dimensional (3D) Gaussian Mixture Model (GMM)-based representation of a 3D map. A GMM model with hundreds of mixture functions is typically needed to adequately learn and represent the intricacies of the map. Meanwhile, localization using complex GMM map models is computationally intensive.
more » ... lly intensive. Since insect-scale drones operate under extremely limited area/power budget, continuous localization using GMM models entails much higher operating energy -- thereby, limiting flying duration and/or size of the drone due to a larger battery. Addressing the computational challenges of localization in an insect-scale drone using a CIM approach, we propose a novel framework of 3D map representation using a harmonic mean of "Gaussian-like" mixture (HMGM) model. The likelihood function useful for drone localization can be efficiently implemented by connecting many multi-input inverters in parallel, each programmed with the parameters of the 3D map model represented as HMGM. When the depth measurements are projected to the input of the implementation, the summed current of the inverters emulates the likelihood of the measurement. We have characterized our approach on an RGB-D indoor localization dataset. The average localization error in our approach is $\sim$0.1125 m which is only slightly degraded than software-based evaluation ($\sim$0.08 m). Meanwhile, our localization framework is ultra-low-power, consuming as little as $\sim$17 $\mu$W power while processing a depth frame in 1.33 ms over hundred pose hypotheses in the particle-filtering (PF) algorithm used to localize the drone.
arXiv:2102.08247v1 fatcat:jbstu2yts5emflhrr3ffsb2g4y

Market Effects of Loyalty and Cost Factors in a Price Discrimination Environment [article]

Theja Tulabandhula, Aris Ouksel
2021 arXiv   pre-print
Product cost heterogeneity across firms and loyalty models of customers are two topics that have garnered limited attention in prior studies on competitive price discrimination. Costs are generally assumed negligible or equal for all firms, and loyalty is modeled as an additive bias in customer valuations. We extend these previous treatments by considering cost asymmetry and a richer class of loyalty models in a game-theoretic model involving two asymmetric firms. Here firms may incur different
more » ... may incur different non-negligible product costs, and customers can have firm-specific loyalty levels. We characterize the effects of loyalty levels and product cost difference on market outcomes such as prices, market share and profits. Our analysis and numerical simulations shed new light on market equilibrium structures arising from the interplay between product cost difference and loyalty levels.
arXiv:2102.09620v1 fatcat:2ubhlok4z5betfwjbxjoyaut6y

Deep Reinforcement Learning for Crowdsourced Urban Delivery: System States Characterization, Heuristics-guided Action Choice, and Rule-Interposing Integration [article]

Tanvir Ahamed, Bo Zou, Nahid Parvez Farazi, Theja Tulabandhula
2020 arXiv   pre-print
This paper investigates the problem of assigning shipping requests to ad hoc couriers in the context of crowdsourced urban delivery. The shipping requests are spatially distributed each with a limited time window between the earliest time for pickup and latest time for delivery. The ad hoc couriers, termed crowdsourcees, also have limited time availability and carrying capacity. We propose a new deep reinforcement learning (DRL)-based approach to tackling this assignment problem. A deep Q
more » ... lem. A deep Q network (DQN) algorithm is trained which entails two salient features of experience replay and target network that enhance the efficiency, convergence, and stability of DRL training. More importantly, this paper makes three methodological contributions: 1) presenting a comprehensive and novel characterization of crowdshipping system states that encompasses spatial-temporal and capacity information of crowdsourcees and requests; 2) embedding heuristics that leverage the information offered by the state representation and are based on intuitive reasoning to guide specific actions to take, to preserve tractability and enhance efficiency of training; and 3) integrating rule-interposing to prevent repeated visiting of the same routes and node sequences during routing improvement, thereby further enhancing the training efficiency by accelerating learning. The effectiveness of the proposed approach is demonstrated through extensive numerical analysis. The results show the benefits brought by the heuristics-guided action choice and rule-interposing in DRL training, and the superiority of the proposed approach over existing heuristics in both solution quality, time, and scalability. Besides the potential to improve the efficiency of crowdshipping operation planning, the proposed approach also provides a new avenue and generic framework for other problems in the vehicle routing context.
arXiv:2011.14430v1 fatcat:rv3owxgycffnlndtohsb23eama

Smart "Predict, then Optimize" [article]

Adam N. Elmachtoub, Paul Grigas
2020 arXiv   pre-print
The approach in Tulabandhula and Rudin (2013) relies on minimizing a loss function that combines the prediction error with the operational cost of the model on an unlabeled dataset.  ...  Tulabandhula, Theja, Cynthia Rudin. 2013. Machine learning with operational costs. Journal of Machine Learning Research 14(1) 1989-2028. Wagner, Harvey M, Thomson M Whitin. 1958.  ... 
arXiv:1710.08005v5 fatcat:a3fbloeyznaovhasvswexbzncq

Virtual Strategy Engineer: Using Artificial Neural Networks for Making Race Strategy Decisions in Circuit Motorsport

Alexander Heilmeier, André Thomaser, Michael Graf, Johannes Betz
2020 Applied Sciences  
In-Event Analysis Motorsport The work done by Tulabandhula et al. [34] comes closest to what is pursued in this paper.  ...  The work of Choo [35] is similar to that of Tulabandhula et al. In recent seasons, Amazon [36] applied ML techniques to provide new insights into F1 races for fans.  ... 
doi:10.3390/app10217805 fatcat:4v4m6adfbnfinnhzk34tvzxer4

A Theory of Statistical Inference for Ensuring the Robustness of Scientific Results [article]

Beau Coker, Cynthia Rudin, Gary King
2020 arXiv   pre-print
This is done by Tulabandhula and Rudin (2014b) for machine learning to determine uncertainty sets for decision making.  ... 
arXiv:1804.08646v2 fatcat:hrwk5tsecbcczl2ppymauwxb6a

Fast, Optimal, and Targeted Predictions using Parametrized Decision Analysis [article]

Daniel R. Kowal
2020 arXiv   pre-print
With similar intentions, Tulabandhula and Rudin (2013) and Semenova and Rudin (2019) define a Rashomon set of predictors for which the in-sample empirical loss is within a margin η of the best predictor  ... 
arXiv:2006.13107v2 fatcat:m6otu7ytgnf4xfk6cpwhmm7x6i

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey [article]

Sanmit Narvekar and Bei Peng and Matteo Leonetti and Jivko Sinapov and Matthew E. Taylor and Peter Stone
2020 arXiv   pre-print
Jain and Tulabandhula (2017) propose 4 different online search methods to sequence tasks into a curriculum.  ... 
arXiv:2003.04960v2 fatcat:iacmqeb7jjeezpo27jsnzuqb7u

Learning Product Rankings Robust to Fake Users [article]

Negin Golrezaei, Vahideh Manshadi, Jon Schneider, Shreyas Sekar
2020 arXiv   pre-print
., see Cao et al. (2019) , Wang and Tulabandhula (2020) ).  ...  settings without fake users, Niazadeh et al. (2020) develop policies for adversarial settings, using Blackwell Approachability (Blackwell 1956), Lattimore et al. (2018) , Cao et al. (2019) , Wang and Tulabandhula  ... 
arXiv:2009.05138v1 fatcat:e5ij4bu2abdedbd2f5gi6w4yuy
« Previous Showing results 1 — 15 out of 67 results