Picture for Dheeraj Nagaraj

Dheeraj Nagaraj

The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models

Add code
May 27, 2024
Viaarxiv icon

Glauber Generative Model: Discrete Diffusion Models via Binary Classification

Add code
May 27, 2024
Viaarxiv icon

A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health

Add code
Feb 23, 2024
Figure 1 for A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
Figure 2 for A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
Figure 3 for A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
Figure 4 for A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
Viaarxiv icon

Towards Zero Shot Learning in Restless Multi-armed Bandits

Add code
Oct 23, 2023
Figure 1 for Towards Zero Shot Learning in Restless Multi-armed Bandits
Figure 2 for Towards Zero Shot Learning in Restless Multi-armed Bandits
Figure 3 for Towards Zero Shot Learning in Restless Multi-armed Bandits
Figure 4 for Towards Zero Shot Learning in Restless Multi-armed Bandits
Viaarxiv icon

Near Optimal Heteroscedastic Regression with Symbiotic Learning

Add code
Jul 01, 2023
Figure 1 for Near Optimal Heteroscedastic Regression with Symbiotic Learning
Figure 2 for Near Optimal Heteroscedastic Regression with Symbiotic Learning
Viaarxiv icon

Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization

Add code
Jun 15, 2023
Figure 1 for Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization
Figure 2 for Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization
Figure 3 for Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization
Figure 4 for Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization
Viaarxiv icon

Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation

Add code
May 27, 2023
Figure 1 for Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
Figure 2 for Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
Viaarxiv icon

Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits

Add code
Oct 31, 2022
Figure 1 for Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits
Figure 2 for Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits
Figure 3 for Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits
Figure 4 for Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits
Viaarxiv icon

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation

Add code
Oct 12, 2022
Figure 1 for Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
Figure 2 for Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
Figure 3 for Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
Viaarxiv icon

Multi-User Reinforcement Learning with Low Rank Rewards

Add code
Oct 11, 2022
Viaarxiv icon