9 citations · 20 across the 10 of their papers we have counts for
9 papers · 1 filter
Diffusion-Based Posterior Sampling: A Feynman-Kac Analysis of Bias and Stability
Matias G. Delgadino, Sebastien Motsch, Advait Parulekar +2
Diffusion-based posterior samplers draw from measurement- or reward-conditioned posteriors using pretrained diffusion priors. Though widely used for inverse problems, their output…
Efficient Approximate Posterior Sampling with Annealed Langevin Monte Carlo
Advait Parulekar, Litu Rout, Karthikeyan Shanmugam +1
We study the problem of posterior sampling in the context of score based generative models. We have a trained score network for a prior , a measurement model , and ar…
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
Liam Collins, Advait Parulekar, Aryan Mokhtari +2
A striking property of transformers is their ability to perform in-context learning (ICL), a machine learning framework in which the learner is presented with a novel context durin…
InfoNCE Loss Provably Learns Cluster-Preserving Representations
Advait Parulekar, Liam Collins, Karthikeyan Shanmugam +2
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 ea…
PAC Generalization via Invariant Representations
Advait Parulekar, Karthikeyan Shanmugam, Sanjay Shakkottai
One method for obtaining generalizable solutions to machine learning tasks when presented with diverse training environments is to find \textit{invariant representations} of the da…
Improved Algorithms for Misspecified Linear Markov Decision Processes
Daniel Vial, Advait Parulekar, Sanjay Shakkottai +1
For the misspecified linear Markov decision process (MLMDP) model of Jin et al. [2020], we propose an algorithm with three desirable properties. (P1) Its regret after episodes…
L1 Regression with Lewis Weights Subsampling
Aditya Parulekar, Advait Parulekar, Eric Price
We consider the problem of finding an approximate solution to regression while only observing a small number of labels. Given an unlabeled data matrix , we…
Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Daniel Vial, Advait Parulekar, Sanjay Shakkottai +1
We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP). Under minimal assumptions, it obtains sublinear regret, is computationally…
Stochastic Linear Bandits with Protected Subspace
Advait Parulekar, Soumya Basu, Aditya Gopalan +2
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…