Publications (13)
Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
Rohan Deb, Qiaobo Li, Mayank Shrivastava +1
Uniform bounds on sketched inner products of vectors or matrices underpin several important computational and statistical results in machine learning and randomized algorithms, inc…
KMM-CP: Practical Conformal Prediction under Covariate Shift via Selective Kernel Mean Matching
Siddhartha Laghuvarapu, Rohan Deb, Jimeng Sun
Uncertainty quantification is essential for deploying machine learning models in high-stakes domains such as scientific discovery and healthcare. Conformal Prediction (CP) provides…
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
Rohan Deb, Kiran Thekumparampil, Kousha Kalantari +3
Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting…
Gradient Temporal Difference with Momentum: Stability and Convergence
Rohan Deb, Shalabh Bhatnagar
Gradient temporal difference (Gradient TD) algorithms are a popular class of stochastic approximation (SA) algorithms used for policy evaluation in reinforcement learning. Here, we…
Schedule Based Temporal Difference Algorithms
Rohan Deb, Meet Gandhi, Shalabh Bhatnagar
Learning the value function of a given policy from data samples is an important problem in Reinforcement Learning. TD() is a popular class of algorithms to solve this problem.…
Does Momentum Help? A Sample Complexity Analysis
Swetha Ganesh, Rohan Deb, Gugan Thoppe +1
Stochastic Heavy Ball (SHB) and Nesterov's Accelerated Stochastic Gradient (ASG) are popular momentum methods in stochastic optimization. While benefits of such acceleration ideas…
Replicable Bandits with UCB based Exploration
Rohan Deb, Udaya Ghai, Karan Singh +1
We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration. A bandit algorithm is -replicabl…
Inference Time Policy Optimization for Offline RL with Differentiable World Models
Rohan Deb, Stephen J. Wright, Arindam Banerjee
Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by m…
Plan Before You Trade: Inference-Time Optimization for RL Trading Agents
Eun Go, Rohan Deb, Arindam Banerjee
Reinforcement learning agents for portfolio management are typically trained and deployed as static policies, with no mechanism for using price forecasts at inference time. We prop…
Conservative Contextual Bandits: Beyond Linear Representations
Rohan Deb, Mohammad Ghavamzadeh, Arindam Banerjee
Conservative Contextual Bandits (CCBs) address safety in sequential decision making by requiring that an agent's policy, along with minimizing regret, also satisfies a safety const…
Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources
Rohan Deb, Aadirupa Saha
We consider the problem of reward maximization in the dueling bandit setup along with constraints on resource consumption. As in the classic dueling bandits, at each round the lear…
Contextual Bandits with Online Neural Regression
Rohan Deb, Yikun Ban, Shiliang Zuo +2
Recent works have shown a reduction from contextual bandits to online regression under a realizability assumption [Foster and Rakhlin, 2020, Foster and Krishnamurthy, 2021]. In thi…
Multi Timescale Stochastic Approximation: Stability and Convergence
Rohan Deb, Swetha Ganesh, Shalabh Bhatnagar
This paper presents the first sufficient conditions that guarantee the stability and almost sure convergence of multi-timescale stochastic approximation (SA) iterates. It extends t…