RD
Rohan Deb
cs.LGcs.AIstat.MLcs.SYeess.SYstat.AP
On Valency
published · living versionsW_kb5efy95·v1 · currentpublished
Conservative Dueling Bandits: Preference Learning under Baseline Constraints
with Mohammad Ghavamzadeh, Arindam Banerjee
1 version
Preprints & journals
13 papers in the corpus · 2021–2026Replicable Dueling Bandits2610.20908v1 · Rohan Deb, Aadirupa Saha, Udaya Ghai et al.2026 · 0 citationsarXiv
Plan Before You Trade: Inference-Time Optimization for RL Trading Agents2605.12653v2 · Eun Go, Rohan Deb, Arindam Banerjee2026 · 0 citationsarXiv
Replicable Bandits with UCB based Exploration2604.20024v2 · Rohan Deb, Udaya Ghai, Karan Singh et al.2026 · 0 citationsarXiv
KMM-CP: Practical Conformal Prediction under Covariate Shift via Selective Kernel Mean Matching2603.26415v1 · Siddhartha Laghuvarapu, Rohan Deb, Jimeng Sun2026 · 0 citationsarXiv
Inference Time Policy Optimization for Offline RL with Differentiable World Models2603.22430v2 · Rohan Deb, Stephen J. Wright, Arindam Banerjee2026 · 0 citationsarXiv
Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms2509.21847v1 · Rohan Deb, Qiaobo Li, Mayank Shrivastava et al.2025 · 0 citationsarXiv
Conservative Contextual Bandits: Beyond Linear Representations2412.06165v1 · Rohan Deb, Mohammad Ghavamzadeh, Arindam Banerjee2024 · 0 citationsarXiv
Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources2312.17229v1 · Rohan Deb, Aadirupa Saha2023 · 0 citationsarXiv
Contextual Bandits with Online Neural Regression2312.07145v1 · Rohan Deb, Yikun Ban, Shiliang Zuo et al.2023 · 0 citationsarXiv
Multi Timescale Stochastic Approximation: Stability and Convergence2112.03515v3 · Rohan Deb, Swetha Ganesh, Shalabh Bhatnagar2021 · 2 citationsarXiv
Schedule Based Temporal Difference Algorithms2111.11768v1 · Rohan Deb, Meet Gandhi, Shalabh Bhatnagar2021 · 1 citationarXiv
Gradient Temporal Difference with Momentum: Stability and Convergence2111.11004v1 · Rohan Deb, Shalabh Bhatnagar2021 · 3 citationsarXiv
Does Momentum Help? A Sample Complexity Analysis2110.15547v3 · Swetha Ganesh, Rohan Deb, Gugan Thoppe et al.2021 · 2 citationsarXiv
Career total: 14 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.