no code implementations • 18 Feb 2024 • Liam Collins, Advait Parulekar, Aryan Mokhtari, Sujay Sanghavi, Sanjay Shakkottai
We show that an attention unit learns a window that it uses to implement a nearest-neighbors predictor adapted to the landscape of the pretraining tasks.
no code implementations • 15 Feb 2023 • Advait Parulekar, Liam Collins, Karthikeyan Shanmugam, Aryan Mokhtari, Sanjay Shakkottai
The goal of contrasting learning is to learn a representation that preserves underlying clusters by keeping samples with similar content, e. g. the ``dogness'' of a dog, close to each other in the space generated by the representation.
no code implementations • 2 Feb 2023 • Litu Rout, Advait Parulekar, Constantine Caramanis, Sanjay Shakkottai
To the best of our knowledge, this is the first linear convergence result for a diffusion based image inpainting algorithm.
no code implementations • 30 May 2022 • Advait Parulekar, Karthikeyan Shanmugam, Sanjay Shakkottai
These are representations of the covariates such that the best model on top of the representation is invariant across training environments.
no code implementations • 12 Sep 2021 • Daniel Vial, Advait Parulekar, Sanjay Shakkottai, R. Srikant
(P1) Its regret after $K$ episodes scales as $K \max \{ \varepsilon_{\text{mis}}, \varepsilon_{\text{tol}} \}$, where $\varepsilon_{\text{mis}}$ is the degree of misspecification and $\varepsilon_{\text{tol}}$ is a user-specified error tolerance.
no code implementations • 19 May 2021 • Aditya Parulekar, Advait Parulekar, Eric Price
We consider the problem of finding an approximate solution to $\ell_1$ regression while only observing a small number of labels.
no code implementations • 4 May 2021 • Daniel Vial, Advait Parulekar, Sanjay Shakkottai, R. Srikant
We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP).
no code implementations • 2 Nov 2020 • Advait Parulekar, Soumya Basu, Aditya Gopalan, Karthikeyan Shanmugam, Sanjay Shakkottai
We study a variant of the stochastic linear bandit problem wherein we optimize a linear objective function but rewards are accrued only orthogonal to an unknown subspace (which we interpret as a \textit{protected space}) given only zero-order stochastic oracle access to both the objective itself and protected subspace.