← Search

Shivam Gupta

11 accepted papers

2025

Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics

NeurIPS 2025poster

Given a noisy linear measurement $y = Ax + \xi$ of a distribution $p(x)$, and a good approximation to the prior $p(x)$, when can we sample from the posterior $p(x \mid y)$? Posterior sampling provides an accurate and fair framework for tasks such as inpainting, deblurring, and MRI reconstruction, an…

Cited by 0SourceScholar
2024

Diffusion Posterior Sampling is Computationally Intractable

ICML 2024poster

Diffusion models are a remarkably effective way of learning and sampling from a distribution $p(x)$. In posterior sampling, one is also given a measurement model $p(y \mid x)$ and a measurement $y$, and would like to sample from $p(x \mid y)$. Posterior sampling is useful for tasks such as inpaintin…

Cited by 9SourcePDFScholar
2024

Improved Sample Complexity Bounds for Diffusion Model Training

NeurIPS 2024poster

Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works [CCL+23, CCSW22, BBDD24] have studied the iteration complexity of sampling, assuming acces…

Cited by 2SourcePDFScholar
2023

Get Out of the BAG! Silos in AI Ethics Education: Unsupervised Topic Modeling Analysis of Global AI Curricula (Extended Abstract)

IJCAI 2023poster

This study explores the topics and trends of teaching AI ethics in higher education, using Latent Dirichlet Allocation as the analysis tool. The analyses included 166 courses from 105 universities around the world. Building on the uncovered patterns, we distil a model of current pedagogical practice…

Cited by 34SourcePDFScholar
2023

High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors

ICML 2023poster

In location estimation, we are given $n$ samples from a known distribution $f$ shifted by an unknown translation $\lambda$, and want to estimate $\lambda$ as precisely as possible. Asymptotically, the maximum likelihood estimate achieves the Cramér-Rao bound of error $\mathcal N(0, \frac{1}{n\mathca…

Cited by 7SourcePDFScholar
2022

Finite-Sample Maximum Likelihood Estimation of Location

NeurIPS 2022accept

We consider 1-dimensional location estimation, where we estimate a parameter $\lambda$ from $n$ samples $\lambda + \eta_i$, with each $\eta_i$ drawn i.i.d. from a known distribution $f$. For fixed $f$ the maximum-likelihood estimate (MLE) is well-known to be optimal in the limit as $n \to \infty$: i…

Cited by 9SourcePDFScholar
2022

Outlier-Robust Sparse Estimation via Non-Convex Optimization

NeurIPS 2022accept

We explore the connection between outlier-robust high-dimensional statistics and non-convex optimization in the presence of sparsity constraints, with a focus on the fundamental tasks of robust sparse mean estimation and robust sparse PCA. We develop novel and simple optimization formulations for th…