Alert button
Picture for Raman Arora

Raman Arora

Alert button

On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond

Jan 06, 2024
Thanh Nguyen-Tang, Raman Arora

Viaarxiv icon

Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates

Nov 22, 2023
Michael Menart, Enayat Ullah, Raman Arora, Raef Bassily, Cristóbal Guzmán

Viaarxiv icon

From Adaptive Query Release to Machine Unlearning

Jul 20, 2023
Enayat Ullah, Raman Arora

Figure 1 for From Adaptive Query Release to Machine Unlearning
Figure 2 for From Adaptive Query Release to Machine Unlearning
Viaarxiv icon

VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation

Mar 04, 2023
Thanh Nguyen-Tang, Raman Arora

Figure 1 for VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
Figure 2 for VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
Figure 3 for VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
Figure 4 for VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
Viaarxiv icon

Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards

Feb 24, 2023
Thanh Nguyen-Tang, Raman Arora

Figure 1 for Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards
Figure 2 for Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards
Figure 3 for Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards
Figure 4 for Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards
Viaarxiv icon

On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation

Nov 23, 2022
Thanh Nguyen-Tang, Ming Yin, Sunil Gupta, Svetha Venkatesh, Raman Arora

Figure 1 for On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
Figure 2 for On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
Figure 3 for On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
Figure 4 for On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
Viaarxiv icon

A Risk-Sensitive Approach to Policy Optimization

Aug 19, 2022
Jared Markowitz, Ryan W. Gardner, Ashley Llorens, Raman Arora, I-Jeng Wang

Figure 1 for A Risk-Sensitive Approach to Policy Optimization
Figure 2 for A Risk-Sensitive Approach to Policy Optimization
Figure 3 for A Risk-Sensitive Approach to Policy Optimization
Figure 4 for A Risk-Sensitive Approach to Policy Optimization
Viaarxiv icon

Faster Rates of Convergence to Stationary Points in Differentially Private Optimization

Jun 02, 2022
Raman Arora, Raef Bassily, Tomás González, Cristóbal Guzmán, Michael Menart, Enayat Ullah

Figure 1 for Faster Rates of Convergence to Stationary Points in Differentially Private Optimization
Viaarxiv icon

Differentially Private Generalized Linear Models Revisited

May 06, 2022
Raman Arora, Raef Bassily, Cristóbal Guzmán, Michael Menart, Enayat Ullah

Figure 1 for Differentially Private Generalized Linear Models Revisited
Viaarxiv icon

Machine Unlearning via Algorithmic Stability

Feb 25, 2021
Enayat Ullah, Tung Mai, Anup Rao, Ryan Rossi, Raman Arora

Figure 1 for Machine Unlearning via Algorithmic Stability
Figure 2 for Machine Unlearning via Algorithmic Stability
Viaarxiv icon