10 papers
Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs
Vansh Bansal, Cho Cholyeon, Syamantak Kumar +2
In this paper, we propose using random walks on graphs as a verifiable sandbox to study different parallel sampling strategies in masked diffusion models (MDMs). We train an MDM on…
On the Curse of Dimensionality in Private Sparse Covariance Estimation and PCA
Syamantak Kumar, Shourya Pandey, Purnamrita Sarkar +1
We study high-dimensional differentially private (DP) covariance estimation in the operator norm, and principal component analysis (PCA), under -row-column sparsity (-RCS) of…
Combinatorial Sparse PCA Beyond the Spiked Identity Model
Syamantak Kumar, Purnamrita Sarkar, Kevin Tian +1
Sparse PCA is one of the most well-studied problems in high-dimensional statistics. In this problem, we are given samples from a distribution with covariance , whose top eigenv…
Nonparametric Evaluation of Noisy ICA Solutions
Syamantak Kumar, Purnamrita Sarkar, Peter Bickel +1
Independent Component Analysis (ICA) was introduced in the 1980's as a model for Blind Source Separation (BSS), which refers to the process of recovering the sources underlying a m…
Low-Precision Streaming PCA
Sanjoy Dasgupta, Syamantak Kumar, Shourya Pandey +1
Low-precision streaming PCA estimates the top principal component in a streaming setting under limited precision. We establish an information-theoretic lower bound on the quantizat…
Dimension-free Score Matching and Time Bootstrapping for Diffusion Models
Syamantak Kumar, Dheeraj Nagaraj, Purnamrita Sarkar
Diffusion models generate samples by estimating the score function of the target distribution at various noise levels. The model is trained using samples drawn from the target dist…