Picture for Avishek Ghosh

Avishek Ghosh

PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect

Add code
Jun 06, 2024
Viaarxiv icon

Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms

Jun 03, 2024
Viaarxiv icon

Optimal Compression of Unit Norm Vectors in the High Distortion Regime

Jul 16, 2023
Figure 1 for Optimal Compression of Unit Norm Vectors in the High Distortion Regime
Viaarxiv icon

Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference

Jul 23, 2022
Figure 1 for Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Figure 2 for Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Figure 3 for Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Viaarxiv icon

Model Selection in Reinforcement Learning with General Function Approximations

Jul 06, 2022
Viaarxiv icon

Decentralized Competing Bandits in Non-Stationary Matching Markets

May 31, 2022
Figure 1 for Decentralized Competing Bandits in Non-Stationary Matching Markets
Figure 2 for Decentralized Competing Bandits in Non-Stationary Matching Markets
Viaarxiv icon

On Learning Mixture of Linear Regressions in the Non-Realizable Setting

May 26, 2022
Figure 1 for On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Figure 2 for On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Figure 3 for On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Figure 4 for On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Viaarxiv icon

Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits

May 19, 2022
Figure 1 for Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
Figure 2 for Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
Figure 3 for Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
Viaarxiv icon

Model Selection with Near Optimal Rates for Reinforcement Learning with General Model Classes

Jul 13, 2021
Viaarxiv icon

Model Selection for Generic Contextual Bandits

Jul 07, 2021
Figure 1 for Model Selection for Generic Contextual Bandits
Viaarxiv icon