FORT

Foundations of Robust and Trustworthy Algorithms for Machine Learning

Publications

  • Differentially Private Algorithms for Efficient Online Matroid Optimization

    Kushagra Chandak, Bingshan Hu, and Nidhi Hegde. “Differentially Private Algorithms for Efficient Online Matroid Optimization”. In: The Conference on Lifelong Learning Agents (CoLLAs). 2023

  • Optimistic Thompson Sampling-based Algorithms for Episodic Reinforcement Learning

    Bingshan Hu, Tianyue Zhang, Nidhi Hegde, and Mark Schmidt. “Optimistic Thompson Sampling-based Algorithms for Episodic Reinforcement Learning”. In: The 39th Conference on Uncertainty in Artificial Intelligence. 2023. URL: https://openreview.net/forum?id=XfpmehHGo2.

  • FineDeb: A Debiasing Framework for Language Models

    Akash Saravanan, Dhruv Mullick, Habib Rahman, and Nidhi Hegde. “FineDeb: A Debiasing Framework for Language Models”. In: The Workshop on Artificial Intelligence for Social Good at AAAI 2023. 2023. URL: https://amulyayadav.github.io/AI4SG2023/images/24.pdf.

  • Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum

    Kirby Banman, Garnet Liam Peet-Pare, Nidhi Hegde, Alona Fyshe, and Martha White. “Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum”. In: International Conference on Learning Representations. 2022. url: https://openreview.net/forum?id=5ECQL05ub0J.

  • Privacy-preserving predictions for large evolving graphs

    Nidhi Hegde and Gaurav Sharma. “Privacy-preserving predictions for large evolving graphs”. In: Theory and Practice of Differential Privacy (TPDP). 2022. URL: https://openreview.net/forum?id=pIalgWjrinC.

  • Optimal Thompson Sampling-based Algorithms for Differentially Private Stochastic Bandits

    Bingshan Hu and Nidhi Hegde. “Optimal Thompson Sampling-based Algorithms for Differentially Private Stochastic Bandits”. In: The 38th Conference on Uncertainty in Artificial Intelligence. 2022. URL: https://openreview.net/forum?id=Bfzg8d8j9x5.

  • Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization

    Garnet Liam Peet-Pare, Nidhi Hegde, and Alona Fyshe. “Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization”. In: Responsible Decision Making in Dynamic Environments, workshop at ICML 2022. 2022. URL: https://responsibledecisionmaking.github.io/assets/pdf/papers/35.pdf.

  • Multi Type Mean Field Reinforcement Learning

    Sriram Ganapathi Subramanian, Pascal Poupart, Matthew E. Taylor, and Nidhi Hegde. “Multi Type Mean Field Reinforcement Learning”. In: (to appear) Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2020. 2020.

  • Asymptotics of Replication and Matching in Large Caching Systems

    Arpan Mukhopadhyay, Nidhi Hegde, and Marc Lelarge. “Asymptotics of Replication and Matching in Large Caching Systems”. In: IEEE/ACM Transactions on Networking 27.4 (2019), pp. 1657–1668. DOI: 10.1109/TNET.2019.2926235. URL: https://doi.org/10.1109/TNET.2019.2926235.

  • Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces

    Baoxiang Wang and Nidhi Hegde. “Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces”. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. 2019, pp. 11323–11333. URL: http://papers.nips.cc/paper/9310-privacy-preserving-q-learning-with-functionalnoise-in-continuous-spaces.

  • ACM Sigmetrics Performance Evaluation Review: A New Series on Diversity, an editorial

    Nidhi Hegde. “ACM Sigmetrics Performance Evaluation Review: A New Series on Diversity, an editorial”. In: Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2018, Irvine, CA, USA, June 18-22, 2018. ACM, 2018, p. 139. doi: 10.1145/3219617.3219675. URL: https://doi.org/10.1145/3219617.3219675.

  • Optimal Content Replication and Request Matching in Large Caching Systems

    Arpan Mukhopadhyay, Nidhi Hegde, and Marc Lelarge. “Optimal Content Replication and Request Matching in Large Caching Systems”. In: IEEE Conference on Computer Communications, INFOCOM 2018, Honolulu, HI, USA, April 16-19, 2018. IEEE, 2018, pp. 288–296. DOI: 10.1109/INFOCOM.2018.8486229. URL: https://doi.org/10.1109/INFOCOM.2018.8486229.

  • Adaptive Active Hypothesis Testing under Limited Information

    Fabio Cecchi and Nidhi Hegde. “Adaptive Active Hypothesis Testing under Limited Information”. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA. 2017, pp. 4035–4043.

  • Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science

    Sara Alouf, Alain Jean-Marie, Nidhi Hegde, and Alexandre Proutière, eds. Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science, Antibes Juan-Les-Pins, France, June 14-18, 2016. ACM, 2016. ISBN: 978-1-4503-4266-7. DOI: 10.1145/2896377. URL: https://doi.org/10.1145/2896377.

  • The Price of Privacy in Untrusted Recommender Systems

    Siddhartha Banerjee, Nidhi Hegde, and Laurent Massoulié. “The Price of Privacy in Untrusted Recommender Systems”. In: Selected Topics in Signal Processing, IEEE Journal of 9.7 (2015). (impact factor: 2.569), pp. 1319–1331. ISSN: 1932-4553. DOI: 10.1109/JSTSP.2015.2423254.

  • Self-Organizing Flows in Social Networks

    Nidhi Hegde, Laurent Massouli´e, and Laurent Viennot. “Self-Organizing Flows in Social Networks”. In: Theoretical Computer Science 584 (Feb. 2015). (impact factor: 0.643), pp. 3–18. DOI: 10.1016/j.tcs.2015.02.018. URL: https://hal.inria.fr/hal-00761046.

  • Learning Wi-Fi performance

    Julien Herzen, Henrik Lundgren, and Nidhi Hegde. “Learning Wi-Fi performance”. In: 12th Annual IEEE International Conference on Sensing, Communication, and Networking, SECON 2015, Seattle, WA, USA, June 22-25, 2015. (acceptance rate: 28%). 2015, pp. 118–126. DOI: 10.1109/SAHCN.2015.7338298. URL: http://dx.doi.org/10.1109/SAHCN.2015.7338298.

  • Stable and scalable universal swarms

    Ji Zhu, Stratis Ioannidis, Nidhi Hegde, and Laurent Massoulié. “Stable and scalable universal swarms”. English. In: Distributed Computing 28.6 (Dec. 2015). (impact factor: 1.263), pp. 391–406. ISSN: 0178-2770. DOI: 10.1007/s00446- 014- 0228- 1. URL: http://dx.doi.org/10.1007/s00446-014-0228-1.

  • Distributed Content Curation on the Web

    Zeinab Abbassi, Nidhi Hegde, and Laurent Massoulié. “Distributed Content Curation on the Web”. In: ACM Transactions Internet Technology 14.(2–3) (Oct. 2014), 9:1–9:15. ISSN: 1533-5399. DOI: 10.1145/2663489. URL: http://doi.acm.org/10.1145/2663489.

  • Distributed Content Curation on the Web

    Zeinab Abbassi, Nidhi Hegde, and Laurent Massoulié. “Distributed Content Curation on the Web”. In: Proc. W-PIN+NetEcon, the joint Workshop on Pricing and Incentives in Networks and Systems. June 2013.