45 citations · 49 across the 7 of their papers we have counts for
7 papers
Certificate-Guided Evaluation of Reinforcement Learning Generalization
Vignesh Subramanian, Đorđe Žikelić, Suguman Bansal
This work presents a logic-driven framework to evaluate the performance of reinforcement learning (RL) algorithms in their ability to generalize to unseen tasks. Our framework defi…
Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications
Vignesh Subramanian, Subhajit Roy, Suguman Bansal
Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies. Prior work ca…
Inductive Generalization in Reinforcement Learning from Specifications
Vignesh Subramanian, Rohit Kushwah, Subhajit Roy +1
We present a novel inductive generalization framework for RL from logical specifications. Many interesting tasks in RL environments have a natural inductive structure. These induct…
A note on the Segal conjecture for large objects
Robert Burklund, Vignesh Subramanian
The Segal conjecture for (as proved by Lin and Gunawardena) asserts that the canonical map from the -complete sphere spectrum to the Tate construction for the trivial acti…
Generalization for multiclass classification with overparameterized linear models
Vignesh Subramanian, Rahul Arya, Anant Sahai
Via an overparameterized linear model with Gaussian features, we provide conditions for good generalization for multiclass classification of minimum-norm interpolating solutions in…
Classification vs regression in overparameterized regimes: Does the loss function matter?
Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian +3
We compare classification and regression tasks in an overparameterized linear model with Gaussian features. On the one hand, we show that with sufficient overparameterization all t…
Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
Anant Sahai, Joshua Sanz, Vignesh Subramanian +2
We examine the problem of learning to cooperate in the context of wireless communication. In our setting, two agents must learn modulation schemes that enable them to communicate a…