Arun Verma

Research

"Basically, I'm not interested in doing research and I never have been... I'm interested in understanding, which is quite a different thing. And often to understand something you have to work it out yourself because no one else has done it." — David Blackwell

Selected Workshop Papers & Preprints

Neural Dueling Bandits
Arun Verma*, Dai Zhongxiang*, Xiaoqiang Lin, Patrick Jaillet, Bryan Kian Hsiang Low (* denotes equal contribution)
ICML 2024, Workshop on Foundations of Reinforcement Learning and Control - Connections and Perspectives, 2024
Prompt Optimization with Human Feedback
Xiaoqiang Lin, Dai Zhongxiang, Arun Verma, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low
ICML 2024, Workshop on Models of Human Feedback for AI Alignment, 2024 (selected as oral)
Online Fair Division with Contextual Bandits
Arun Verma, Indrajit Saha, Makoto Yokoo, Bryan Kian Hsiang Low
Understanding the Relationship between Prompts and Response Uncertainty in Large Language Models
Ze Yu Zhang*, Arun Verma*, Finale Doshi-Velez, Bryan Kian Hsiang Low (* denotes equal contribution)
Data-Centric AI in the Age of Large Language Models
Xinyi Xu, Zhaoxuan Wu, Rui Qiao, Arun Verma, Yao Shu, Jingtan Wang, Xinyuan Niu, Zhenfeng He, Jiangwei Chen, Zijian Zhou, Gregory Kang Ruey Lau, Hieu Dao, Lucas Agussurja, Rachael Hwee Ling Sim, Xiaoqiang Lin, Wenyang Hu, Dai Zhongxiang, Pang Wei Koh, Bryan Kian Hsiang Low
Censored Semi-Bandits for Resource Allocation
Arun Verma, Manjesh K. Hanawal, Arun Rajkumar, Raman Sankaran

Publications

Application of Clustering Algorithms for Dimensionality Reduction in Infrastructure Resilience Prediction Models
Srijith Balakrishnan, Beatrice Cassottana, Arun Verma
Structure and Infrastructure Engineering, 2024
Exploiting Correlated Auxiliary Feedback in Parameterized Bandits
Arun Verma, Dai Zhongxiang, Yao Shu, Bryan Kian Hsiang Low
NeurIPS, 2023
Quantum Bayesian Optimization
Dai Zhongxiang, Gregory Kang Ruey Lau, Arun Verma, Yao Shu, Bryan Kian Hsiang Low, Patrick Jaillet
NeurIPS, 2023
Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-Linear Function Approximation
Chi Thanh Lam, Arun Verma, Bryan Kian Hsiang Low, Patrick Jaillet
ICLR, 2023
Federated Neural Bandit
Dai Zhongxiang, Yao Shu, Arun Verma, Flint Xiaofeng Fan, Bryan Kian Hsiang Low, Patrick Jaillet
ICLR, 2023
Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation
Yao Shu, Dai Zhongxiang, Weicong Sng, Arun Verma, Patrick Jaillet, Bryan Kian Hsiang Low
ICLR, 2023
FAIR: Fair Collaborative Active Learning with Individual Rationality for Scientific Discovery
Xinyi Xu, Zhaoxuan Wu, Arun Verma, Chuan Sheng Foo, Bryan Kian Hsiang Low
AISTATS, 2023
Bayesian Optimization under Stochastic Delayed Feedback
Arun Verma*, Dai Zhongxiang*, Bryan Kian Hsiang Low (* denotes equal contribution)
ICML, 2022
Stochastic Multi-Armed Bandits with Control Variates
Arun Verma, Manjesh K. Hanawal
NeurIPS, 2021
Online Algorithm for Unsupervised Sequential Selection with Contextual Information
Arun Verma, Manjesh K. Hanawal, Csaba Szepesvári, Venkatesh Saligrama
NeurIPS, 2020
Thompson Sampling for Unsupervised Sequential Selection
Arun Verma, Manjesh K. Hanawal, N. Hemachandra
ACML, 2020
Learning and Fairness in Energy Harvesting: A Maximin Multi-Armed Bandits Approach
Debamita Ghosh Arun Verma, Manjesh K. Hanawal
IEEE SPCOM, 2020
Stochastic Network Utility Maximization with Unknown Utility: Multi-Armed Bandits Approach
Arun Verma, Manjesh K. Hanawal
IEEE INFOCOM, 2020
Unsupervised Online Feature Selection for Cost-Sensitive Medical Diagnosis
Arun Verma, Manjesh K. Hanawal, N. Hemachandra
COMSNETS, 2020
Censored Semi-Bandits: A Framework for Resource Allocation with Censored Feedback
Arun Verma, Manjesh K. Hanawal, Arun Rajkumar, Raman Sankaran
NeurIPS, 2019
Distributed Algorithms for Efficient Learning and Coordination in Ad Hoc Networks
Arun Verma, Manjesh K. Hanawal, Rahul Vaze
WiOPT, 2019
Online Algorithm for Unsupervised Sensor Selection
Arun Verma, Manjesh K. Hanawal, Csaba Szepesvári, Venkatesh Saligrama
AISTATS, 2019
Unsupervised Cost Sensitive Predictions with Side Information
Arun Verma, Manjesh K. Hanawal
CoDS-COMAD, 2018
Benchmarking Fast Data Platforms for the Aadhaar Biometric Database
Yogesh Simmhan, Anshu Shukla, Arun Verma,
WBDB, 2015

Talks

Invited talk on Sequential Decision Problems with Weak Feedback, as part of the Multi-Armed Bandits (CS6046) course at IIT Madras on May 4, 2021.
Virtual seminar on Sequential Decision Problems with Weak Feedback, at RIKEN AIP, Japan on November 27, 2020.
SequeL seminar on Censored Semi- Bandits: A Framework for Resource Allocation withCensored Feedback, at INRIA Lille, France on November 24, 2019.
Talk on Online Algorithm for Cost-Sensitive Unsupervised Learning, at RIKEN AIP, Japan during my visit to Approximate Bayesian Inference (ABI) Team from April 9 — 16, 2019.
Lighting talk on Unsupervised Cost Sensitive Predictions with Contextual Information at IEOR Day 2018, IIT Bombay on March 17, 2018.

Awards

COMSNETS 2022 Best Ph.D. Thesis Award for my Ph.D. thesis.
Naik and Rastogi Excellence in Ph. D. Thesis Award (Best Thesis Award of IIT Bombay) for doctoral research.
Microsoft Travel Grant (not used due to Covid-19 travel restrictions) and COMSNETS Association and LRN Foundation Travel Award for attending IEEE INFOCOM 2020.
Travel Award from LinkedIn for attending FATE-ML workshop 2020 at IISc, Bengaluru, India.
Google Travel Grant and NeurIPS Student Travel Award for attending NeurIPS 2019.
Raman-Charpak Fellowship 2018 for visiting SequeL Team of INRIA Lille, France.
ACM-India/IARCS and Microsoft Travel Grant for attending AISTATS 2019.
Technical Color Award of Hostel-14, IIT Bombay for year 2017-18 and 2018-19.
Sports Color Award (Cricket) of Hostel-14, IIT Bombay for year 2017-18.
Conference Travel Awards from HiPC 2016, CoDS 2017, CoDS-COMAD 2018, AUAPAF 2018.
IITB Research Internship Award 2013-14 from Indian Institute of Technology Bombay.
Academic Excellence Award (Gold Medal) for having the highest CGPA in B.Tech.(CSE).