Siddartha Devic

According to our database, Siddartha Devic authored at least 21 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Are LLM Decisions Faithful to Verbal Confidence?

Jiawei Wang, Yanfei Zhou, Siddartha Devic, Deqing Fu

CoRR, January, 2026

Auditability and the Landscape of Distance to Multicalibration.

Nathan Derhake, Siddartha Devic, Dutch Hansen, Kuan Liu, Vatsal Sharan

Proceedings of the 17th Innovations in Theoretical Computer Science Conference, 2026

An External Fairness Evaluation of LinkedIn Talent Search.

Tina Behzad, Siddartha Devic, Vatsal Sharan, Aleksandra Korolova, David Kempe

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Trace Length is a Simple Uncertainty Signal in Reasoning Models.

Siddartha Devic, Charlotte Peale, Arwen Bradley, Sinead Williamson, Preetum Nakkiran, Aravind Gollakota

CoRR, October, 2025

From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered.

Siddartha Devic, Tejas Srinivasan, Jesse Thomason, Willie Neiswanger, Vatsal Sharan

CoRR, June, 2025

An Efficient Plugin Method for Metric Optimization of Black-Box Models.

Siddartha Devic, Nurendra Choudhary, Anirudh Srinivasan, Sahika Genc, Branislav Kveton, Gaurush Hiranandani

CoRR, March, 2025

Proper Learnability and the Role of Unlabeled Data.

Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng

Proceedings of the International Conference on Algorithmic Learning Theory, 2025

2024

Learnability is a Compact Property.

Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng

CoRR, 2024

When is Multicalibration Post-Processing Necessary?

Dutch Hansen, Siddartha Devic, Preetum Nakkiran, Vatsal Sharan

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Transductive Learning is Compact.

Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Stability and Multigroup Fairness in Ranking with Uncertain Predictions.

Siddartha Devic, Aleksandra Korolova, David Kempe, Vatsal Sharan

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Open Problem: Can Local Regularization Learn All Multiclass Problems?

Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Regularization and Optimal Multiclass Learning.

Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Fairness in Matching under Uncertainty.

Siddartha Devic, David Kempe, Vatsal Sharan, Aleksandra Korolova

Proceedings of the International Conference on Machine Learning, 2023

2022

Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions.

Zihao Deng, Siddartha Devic, Brendan Juba

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Polynomial Time Reinforcement Learning in Correlated FMDPs with Linear Value Functions.

Siddartha Devic, Zihao Deng, Brendan Juba

CoRR, 2021

Dynamic Bandwidth Allocation for PON Slicing with Performance-Guaranteed Online Convex Optimization.

Genya Ishigaki, Siddartha Devic, Riti Gour, Jason P. Jue

Proceedings of the IEEE Global Communications Conference, 2021

2020

DeepPR: Progressive Recovery for Interdependent VNFs With Deep Reinforcement Learning.

Genya Ishigaki, Siddartha Devic, Riti Gour, Jason P. Jue

IEEE J. Sel. Areas Commun., 2020

Failout: Achieving Failure-Resilient Inference in Distributed Neural Networks.

Ashkan Yousefpour, Brian Q. Nguyen, Siddartha Devic, Guanhua Wang, Aboudy Kreidieh, Hans Lobel, Alexandre M. Bayen, Jason P. Jue

CoRR, 2020

2019

Guardians of the Deep Fog: Failure-Resilient DNN Inference from Edge to Cloud.

Ashkan Yousefpour, Siddartha Devic, Brian Q. Nguyen, Aboudy Kreidieh, Alan Liao, Alexandre M. Bayen, Jason P. Jue

CoRR, 2019

DeepPR: Incremental Recovery for Interdependent VNFs with Deep Reinforcement Learning.

Genya Ishigaki, Siddartha Devic, Riti Gour, Jason P. Jue

Proceedings of the 2019 IEEE Global Communications Conference, 2019