Nidhi Hegde
Research Subjects
Research Interests
Nidhi Hegde has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
S. Borst
Bell Labs., Alcatel-Lucent, Holmdel, NJ
5 shared publicationsA. Proutiere
3 shared publicationsLaurent Massoulie
Microsoft Research - INRIA Joint Centre, France
3 shared publicationsAlexandre Proutiere
Microsoft Research
2 shared publicationsKhosrow Sohraby
Computer Science Telecommunications, University of Missouri-Kansas City, 5100 Rockhill Road, Kansas City, MO
2 shared publications- Laurent Massoulié
Inria Paris, ENS Paris, Paris, France
2 shared publications
Latest Publications
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 3858-3879
RobustDebias: Debiasing Language Models using Distributionally Robust Optimization
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 3858-3879
Open AccessRobustDebias: Debiasing Language Models using Distributionally Robust Optimization
- Open Access
Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering
Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) that helps contextualize questions to the image and supplements them with external world knowledge to generate accurate answers. However, the relative contributions of the vision encoder and the language model in these tasks remain unclear. This is especially interesting given the effectiveness of instruction-tuned LLMs, which exhibit remarkable adaptability to new tasks. To this end, we explore the following aspects in this work: (1) The efficacy of an LLM-only approach on document question answering tasks (2) strategies for serializing textual information within document images and feeding it directly to an instruction-tuned LLM, thus bypassing the need for an explicit vision encoder (3) thorough quantitative analysis on the feasibility of such an approach. Our comprehensive analysis encompasses six diverse benchmark datasets, utilizing LLMs of varying scales. Our findings reveal that a strategy exclusively reliant on the LLM yields results that are on par with or closely approach state-of-the-art performance across a range of datasets. We posit that this evaluation framework will serve as a guiding resource for selecting appropriate datasets for future research endeavors that emphasize the fundamental importance of layout and image content information.
Open AccessAnalyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering
Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) that helps contextualize questions to the image and supplements them with external world knowledge to generate accurate answers. However, the relative contributions of the vision encoder and the language model in these tasks remain unclear. This is especially interesting given the effectiveness of instruction-tuned LLMs, which exhibit remarkable adaptability to new tasks. To this end, we explore the following aspects in this work: (1) The efficacy of an LLM-only approach on document question answering tasks (2) strategies for serializing textual information within document images and feeding it directly to an instruction-tuned LLM, thus bypassing the need for an explicit vision encoder (3) thorough quantitative analysis on the feasibility of such an approach. Our comprehensive analysis encompasses six diverse benchmark datasets, utilizing LLMs of varying scales. Our findings reveal that a strategy exclusively reliant on the LLM yields results that are on par with or closely approach state-of-the-art performance across a range of datasets. We posit that this evaluation framework will serve as a guiding resource for selecting appropriate datasets for future research endeavors that emphasize the fundamental importance of layout and image content information.
- Open Access
Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization
Fairness researchers in machine learning (ML) have coalesced around several fairness criteria which provide formal definitions of what it means for an ML model to be fair. However, these criteria have some serious limitations. We identify four key shortcomings of these formal fairness criteria, and aim to help to address them by extending performative prediction to include a distributionally robust objective.
Open AccessLong Term Fairness for Minority Groups via Performative Distributionally Robust Optimization
Fairness researchers in machine learning (ML) have coalesced around several fairness criteria which provide formal definitions of what it means for an ML model to be fair. However, these criteria have some serious limitations. We identify four key shortcomings of these formal fairness criteria, and aim to help to address them by extending performative prediction to include a distributionally robust objective.
- 18 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 27 (4) , 1657-1668
Asymptotics of Replication and Matching in Large Caching Systems
We consider a generic model of distributed caching systems, where the cache servers are constrained by two main resources: memory size and bandwidth. Content distribution networks (CDNs) providing video contents and peer-to-peer video-on-demand services are a few examples of such systems. The throughput of these systems crucially depends on how these resources are managed, i.e., how contents are replicated across servers and how requests of specific contents are matched to servers storing the contents. In this paper, we formulate the problem of computing the replication policy and the matching policy, which jointly maximizes the throughput of the caching system. It is shown that computing the optimal replication policy for a given finite system is an NP-hard problem. A greedy replication scheme is then proposed and is shown to achieve a constant factor approximation guarantee when combined with the optimal matching policy. We note that the optimal matching policy has the problem of interruption in service of the ongoing requests due to re-assignment or repacking of the existing requests. To avoid this problem, we propose a simple randomized online matching scheme and analyze its performance in conjunction with the proposed replication scheme. We consider a limiting regime, where the number of servers is large and the arrival rates of the contents are scaled proportionally, and show that the proposed policies achieve asymptotic optimality. Extensive simulation results are presented to evaluate the performance of different policies and study the behavior of the caching system under different service time distributions of the requests.
- 18 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 27 (4) , 1657-1668
Asymptotics of Replication and Matching in Large Caching Systems
We consider a generic model of distributed caching systems, where the cache servers are constrained by two main resources: memory size and bandwidth. Content distribution networks (CDNs) providing video contents and peer-to-peer video-on-demand services are a few examples of such systems. The throughput of these systems crucially depends on how these resources are managed, i.e., how contents are replicated across servers and how requests of specific contents are matched to servers storing the contents. In this paper, we formulate the problem of computing the replication policy and the matching policy, which jointly maximizes the throughput of the caching system. It is shown that computing the optimal replication policy for a given finite system is an NP-hard problem. A greedy replication scheme is then proposed and is shown to achieve a constant factor approximation guarantee when combined with the optimal matching policy. We note that the optimal matching policy has the problem of interruption in service of the ongoing requests due to re-assignment or repacking of the existing requests. To avoid this problem, we propose a simple randomized online matching scheme and analyze its performance in conjunction with the proposed replication scheme. We consider a limiting regime, where the number of servers is large and the arrival rates of the contents are scaled proportionally, and show that the proposed policies achieve asymptotic optimality. Extensive simulation results are presented to evaluate the performance of different policies and study the behavior of the caching system under different service time distributions of the requests.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 288-296
Optimal Content Replication and Request Matching in Large Caching Systems
We consider models of content delivery networks in which the servers are constrained by two main resources: memory and bandwidth. In such systems, the throughput crucially depends on how contents are replicated across servers and how the requests of specific contents are matched to servers storing those contents. In this paper, we first formulate the problem of computing the optimal replication policy which if combined with the optimal matching policy maximizes the throughput of the caching system in the stationary regime. It is shown that computing the optimal replication policy for a given system is an NP-hard problem. A greedy replication scheme is proposed and it is shown that the scheme provides a constant factor approximation guarantee. We then propose a simple randomized matching scheme which avoids the problem of interruption in service of the ongoing requests due to re-assignment or repacking of the existing requests in the optimal matching policy. The dynamics of the caching system is analyzed under the combination of proposed replication and matching schemes. We study a limiting regime, where the number of servers and the arrival rates of the contents are scaled proportionally, and show that the proposed policies achieve asymptotic optimality. Extensive simulation results are presented to evaluate the performance of different policies and study the behavior of the caching system under different service time distributions of the requests.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 288-296
Optimal Content Replication and Request Matching in Large Caching Systems
We consider models of content delivery networks in which the servers are constrained by two main resources: memory and bandwidth. In such systems, the throughput crucially depends on how contents are replicated across servers and how the requests of specific contents are matched to servers storing those contents. In this paper, we first formulate the problem of computing the optimal replication policy which if combined with the optimal matching policy maximizes the throughput of the caching system in the stationary regime. It is shown that computing the optimal replication policy for a given system is an NP-hard problem. A greedy replication scheme is proposed and it is shown that the scheme provides a constant factor approximation guarantee. We then propose a simple randomized matching scheme which avoids the problem of interruption in service of the ongoing requests due to re-assignment or repacking of the existing requests in the optimal matching policy. The dynamics of the caching system is analyzed under the combination of proposed replication and matching schemes. We study a limiting regime, where the number of servers and the arrival rates of the contents are scaled proportionally, and show that the proposed policies achieve asymptotic optimality. Extensive simulation results are presented to evaluate the performance of different policies and study the behavior of the caching system under different service time distributions of the requests.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 118-126
Learning Wi-Fi performance
Accurate prediction of wireless network performance is important when performing link adaptation or resource allocation. However, the complexity of interference interactions at MAC and PHY layers, as well as the vast variety of possible wireless configurations make it notoriously hard to design explicit performance models. In this paper, we advocate an approach of “learning by observation” that can remove the need for designing explicit and complex performance models. We use machine learning techniques to learn implicit performance models, from a limited number of real-world measurements. These models do not require to know the internal mechanics of interfering Wi-Fi links. Yet, our results show that they improve accuracy by at least 49% compared to measurement-seeded models based on SINR. To demonstrate that learned models can be useful in practice, we build a new algorithm that uses such a model as an oracle to jointly allocate spectrum and transmit power. Our algorithm is utility-optimal, distributed, and it produces efficient allocations that significantly improve performance and fairness.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 118-126
Learning Wi-Fi performance
Accurate prediction of wireless network performance is important when performing link adaptation or resource allocation. However, the complexity of interference interactions at MAC and PHY layers, as well as the vast variety of possible wireless configurations make it notoriously hard to design explicit performance models. In this paper, we advocate an approach of “learning by observation” that can remove the need for designing explicit and complex performance models. We use machine learning techniques to learn implicit performance models, from a limited number of real-world measurements. These models do not require to know the internal mechanics of interfering Wi-Fi links. Yet, our results show that they improve accuracy by at least 49% compared to measurement-seeded models based on SINR. To demonstrate that learned models can be useful in practice, we build a new algorithm that uses such a model as an oracle to jointly allocate spectrum and transmit power. Our algorithm is utility-optimal, distributed, and it produces efficient allocations that significantly improve performance and fairness.
- 1 June 2015
- Published by Elsevier in Theoretical Computer Science
- Vol. 584, 3-18
Self-organizing flows in social networks
- 1 June 2015
- Published by Elsevier in Theoretical Computer Science
- Vol. 584, 3-18
Self-organizing flows in social networks
- 15 April 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 9 (7) , 1
The Price of Privacy in Untrusted Recommender Systems
Recent increase in online privacy concerns prompts the following question: can a recommender system be accurate if users do not entrust it with their private data? To answer this, we study the problem of learning item-clusters under local differential privacy, a powerful, formal notion of data privacy. We develop bounds on the sample-complexity of learning item-clusters from privatized user inputs. Significantly, our results identify a sample-complexity separation between learning in an information-rich and an information-scarce regime, thereby highlighting the interaction between privacy and the amount of information (ratings) available to each user. In the information-rich regime, where each user rates at least a constant fraction of items, a spectral clustering approach is shown to achieve a sample-complexity lower bound derived from a simple information-theoretic argument based on Fano's inequality. However, the information-scarce regime, where each user rates only a vanishing fraction of items, is found to require a fundamentally different approach both for lower bounds and algorithms. To this end, we develop new techniques for bounding mutual information under a notion of channel-mismatch. These techniques may be of broader interest, and we illustrate this by applying them to (i) learning based on 1-bit sketches, and (ii) adaptive learning. Finally, we propose a new algorithm, MaxSense, and show that it achieves optimal sample-complexity in the information-scarce regime.
- 15 April 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 9 (7) , 1
The Price of Privacy in Untrusted Recommender Systems
Recent increase in online privacy concerns prompts the following question: can a recommender system be accurate if users do not entrust it with their private data? To answer this, we study the problem of learning item-clusters under local differential privacy, a powerful, formal notion of data privacy. We develop bounds on the sample-complexity of learning item-clusters from privatized user inputs. Significantly, our results identify a sample-complexity separation between learning in an information-rich and an information-scarce regime, thereby highlighting the interaction between privacy and the amount of information (ratings) available to each user. In the information-rich regime, where each user rates at least a constant fraction of items, a spectral clustering approach is shown to achieve a sample-complexity lower bound derived from a simple information-theoretic argument based on Fano's inequality. However, the information-scarce regime, where each user rates only a vanishing fraction of items, is found to require a fundamentally different approach both for lower bounds and algorithms. To this end, we develop new techniques for bounding mutual information under a notion of channel-mismatch. These techniques may be of broader interest, and we illustrate this by applying them to (i) learning based on 1-bit sketches, and (ii) adaptive learning. Finally, we propose a new algorithm, MaxSense, and show that it achieves optimal sample-complexity in the information-scarce regime.
- 1 April 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2373-2381
How to Optimally allocate your budget of attention in social networks
We consider the performance of information propagation through social networks in a scenario where each user has a budget of attention, that is, a constraint on the frequency with which he pulls content from neighbors. In this context we ask the question “when users make selfish decisions on how to allocate their limited access frequency among neighbors, does information propagate efficiently?” For the metric of average propagation delay, we provide characterizations of the optimal social cost and the social cost under selfish user optimizations for various topologies of interest. Three situations may arise: well-connected topologies where delay is small even under selfish optimization; tree-like topologies where selfish optimization performs poorly while optimal social cost is low; and “stretched” topologies where even optimal social cost is high. We propose a mechanism for incentivizing users to modify their selfish behaviour, and observe its efficiency in the family of tree-like topologies mentioned above.
- 1 April 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2373-2381
How to Optimally allocate your budget of attention in social networks
We consider the performance of information propagation through social networks in a scenario where each user has a budget of attention, that is, a constraint on the frequency with which he pulls content from neighbors. In this context we ask the question “when users make selfish decisions on how to allocate their limited access frequency among neighbors, does information propagate efficiently?” For the metric of average propagation delay, we provide characterizations of the optimal social cost and the social cost under selfish user optimizations for various topologies of interest. Three situations may arise: well-connected topologies where delay is small even under selfish optimization; tree-like topologies where selfish optimization performs poorly while optimal social cost is low; and “stretched” topologies where even optimal social cost is high. We propose a mechanism for incentivizing users to modify their selfish behaviour, and observe its efficiency in the family of tree-like topologies mentioned above.
- 11 March 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 4 (2) , 789-797
Optimal Control of End-User Energy Storage
An increasing number of retail energy markets show price fluctuations, providing users with the opportunity to buy energy at lower than average prices. We propose to temporarily store this inexpensive energy in a battery, and use it to satisfy demand when energy prices are high, thus allowing users to exploit the price variations without having to shift their demand to the low-price periods. We study the battery control policy that yields the best performance, i.e., minimizes the total discounted costs. The optimal policy is shown to have a threshold structure, and we derive these thresholds in a few special cases. The cost savings obtained from energy storage are demonstrated through extensive numerical experiments, and we offer various directions for future research.
- 11 March 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 4 (2) , 789-797
Optimal Control of End-User Energy Storage
An increasing number of retail energy markets show price fluctuations, providing users with the opportunity to buy energy at lower than average prices. We propose to temporarily store this inexpensive energy in a battery, and use it to satisfy demand when energy prices are high, thus allowing users to exploit the price variations without having to shift their demand to the low-price periods. We study the battery control policy that yields the best performance, i.e., minimizes the total discounted costs. The optimal policy is shown to have a threshold structure, and we derive these thresholds in a few special cases. The cost savings obtained from energy storage are demonstrated through extensive numerical experiments, and we offer various directions for future research.