Picture for Mladen Kolar

Mladen Kolar

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

Add code
Jul 10, 2024
Viaarxiv icon

Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods

Add code
Jun 20, 2024
Viaarxiv icon

Personalized Binomial DAGs Learning with Network Structured Covariates

Add code
Jun 10, 2024
Viaarxiv icon

AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods

Add code
Feb 17, 2024
Viaarxiv icon

Inconsistency of cross-validation for structure learning in Gaussian graphical models

Add code
Dec 28, 2023
Viaarxiv icon

Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm

Add code
Jun 05, 2023
Figure 1 for Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
Figure 2 for Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
Figure 3 for Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
Figure 4 for Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
Viaarxiv icon

Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching

Add code
May 28, 2023
Figure 1 for Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
Figure 2 for Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
Figure 3 for Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
Figure 4 for Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
Viaarxiv icon

Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems

Add code
Nov 29, 2022
Figure 1 for Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
Figure 2 for Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
Figure 3 for Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
Viaarxiv icon

Latent Multimodal Functional Graphical Model Estimation

Add code
Oct 31, 2022
Figure 1 for Latent Multimodal Functional Graphical Model Estimation
Figure 2 for Latent Multimodal Functional Graphical Model Estimation
Figure 3 for Latent Multimodal Functional Graphical Model Estimation
Figure 4 for Latent Multimodal Functional Graphical Model Estimation
Viaarxiv icon

One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning

Add code
May 31, 2022
Viaarxiv icon