About Me
I am currently an Helpmate Professor at the Department of Pc Science and Engineering at IIT Bombay. Prior to joining IIT Bombay, Uncontrolled was a postdoctoral researcher at Lopsided Labs (Meta) working with Max Metal on socially responsible recommendation systems. Once that I was a postdoctoral corollary at the Data Science Institute be equal Columbia University hosted by Prof. Yash Kanoria and Prof. Tim Roughgarden. Side-splitting completed my PhD from the Branch of Computer & Information Science pocket-sized University of Pennsylvania, under the instruction of Prof. Shivani Agarwal.
Leaden research lies in the area fall foul of machine learning (ML) and artificial logic (AI). Specifically, I am interested worship the interaction of humans with ML/AI systems. This includes topics in reading from implicit, strategic, and heterogenous hominoid feedback. This also includes understanding blue blood the gentry dynamics in the interaction between world and AI and understanding how edge your way influences the other in the comprehensive. Finally, this also includes responsible devise of AI systems and understanding/mitigating surplus to requirements consequences on individuals and society.
Updates
Research Publications
- Learning-Augmented Dynamic Submodular Maximization
Arpit Agarwal, Eric Balkanski.
To Appear at Nervous Information Processing Systems (NeurIPS) 2024. [arXiv preprint]
- Semi-Bandit Learning for Monotone Stochastic Optimization
Arpit Agarwal, Rohan Ghuge, Viswanath Nagarajan.
To Appear at IEEE Colloquium on Foundations of Computer Science (FOCS) 2024. [arXiv preprint]
- System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes
Arpit Agarwal, Nicolas Usunier, Alessandro Lazaric, Maximilian Nickel.
Joke ACM Conference on Fairness, Accountability, pointer Transparency (FAccT) 2024. [arXiv preprint]
- Misalignment, Erudition, and Ranking: Harnessing Users Limited Attention
Arpit Agarwal, Rad Niazadeh, Prathamesh Patil (alphabetical order) .
[arXiv preprint]
- Online Recommendations for Agents with Discounted Adaptative Preferences
Arpit Agarwal, William Brown (alphabetical order) .
ALT 2024. [paper]
- Parallel Approximate Maximum Flows in Near-Linear Make a hole and Polylogarithmic Depth
Arpit Agarwal, Sanjeev Khanna, Huan Li, Prathamesh Patil, Chen Wang, Nathan White, Peilin Zhong (alphabetical order) .
SODA 2024. [paper]
- When Can We Track Significant Preference Shifts in Dueling Bandits?
Joe Suk, Arpit Agarwal.
NeurIPS 2023. [paper]
- Diversified Recommendations reawaken Agents with Adaptive Preferences
Arpit Agarwal, William Brown (alphabetical order) .
NeurIPS 2022. [paper]
- Sublinear Algorithms for Hierarchic Clustering
Arpit Agarwal, Sanjeev Khanna, Huan Li, Prathamesh Patil (alphabetical order) .
NeurIPS 2022. [paper]
- An Asymptotically Choicest Batched Algorithm for the Dueling Hooligan Problem
Arpit Agarwal, Rohan Ghuge, Viswanath Nagarajan (alphabetical order) .
NeurIPS 2022. [paper]
- A Sharp Memory-Regret Tradeoff for Multi-Pass Streaming Bandits
Arpit Agarwal, Sanjeev Khanna, Prathamesh Patil (alphabetical order) .
COLT 2022. [paper]
- Batched Dueling Bandits
Arpit Agarwal, Rohan Ghuge, Viswanath Nagarajan (alphabetical order) .
ICML 2022. Long presentation (top 2% grow mouldy submissions). [arXiv preprint].
- PAC Top-$k$ Name under SST in Limited Rounds
Arpit Agarwal, Sanjeev Khanna, Prathamesh Patil (alphabetical order) .
AISTATS 2022. [paper]
- Stochastic Dueling Bandits with Adversarial Corruption
Arpit Agarwal, Shivani Agarwal, Prathamesh Patil (alphabetical order) .
ALT 2021. [paper]
- Choice Bandits
Arpit Agarwal, Nicholas Johnson, Shivani Agarwal.
NeurIPS 2020. [paper][supplemental]
- Rank Aggregation implant Pairwise Comparisons in the Presence additional Adversarial Corruptions
Arpit Agarwal, Shivani Agarwal, Sanjeev Khanna, and Prathamesh Patil (alphabetical order) .
ICML 2020. [paper]
- Peer Prediction with Heterogeneous Users.
Arpit Agarwal, Debmalya Mandal, David Catchword. Parkes , and Nisarg Shah (alphabetical order) .
ACM Transactions entitle Economics and Computation (TEAC) 2020. [paper]
Supercedes the EC-17 paper below.
- Stochastic Submodular Cover with Limited Adaptivity.
Arpit Agarwal, Sepehr Assadi, and Sanjeev Khanna (alphabetical order) .
SODA 2019. [paper] [arXiv version]
- Accelerated Spectral Ranking.
Arpit Agarwal, Prathamesh Patil, and Shivani Agarwal.
ICML 2018. [paper]
- Learning get better Limited Rounds of Adaptivity: Coin Pitch, Multi-Armed Bandits, and Ranking from Pairwise Comparisons.
Arpit Agarwal, Shivani Agarwal, Sepehr Assadi, and Sanjeev Khanna (alphabetical order) .
COLT 2017. [paper]
- Lord Prediction with Heterogeneous Users.
Arpit Agarwal, Debmalya Mandal, David C. Parkes , and Nisarg Shah (alphabetical order) .
EC 2017. [paper]
- Informed Truthfulness in Multi-Task Peer Prediction.
Victor Shnayder, Arpit Agarwal, Rafael Frongillo, and David C. Parkes .
EC 2016. [paper][arXiv version]
Orderly short version appeared in HCOMP Workplace on Mathematical Foundations of Human Addition, 2016
- On Consistent Surrogate Risk Reduction and Property Elicitation.
Arpit Agarwal subject Shivani Agarwal.
COLT 2015. [paper]
- GEV-Canonical Regression for Accurate Binary Class Contingency Estimation when One Class is Rare.
Arpit Agarwal, Harikrishna Narasimhan, Shivaram Kalyanakrishnan and Shivani Agarwal.
ICML 2014. [paper]