13 citations · 13 across the 4 of their papers we have counts for
5 papers
End-to-End Guarantees for Masked Diffusion Models under Conditional Mixing
Fareed Sheriff
Masked diffusion models train a denoiser on masked cross-entropy and generate by unmasking many positions in parallel. Existing MDM sampling bounds assume an exact denoiser or leav…
SpreadNUTS -- Moderate Dynamic Extension of Paths for No-U-Turn Sampling & Partitioning Visited Regions
Fareed Sheriff
Markov chain Monte Carlo (MCMC) methods have existed for a long time and the field is well-explored. The purpose of MCMC methods is to approximate a distribution through repeated s…
PartitionVAE -- a human-interpretable VAE
Fareed Sheriff, Sameer Pai
VAEs, or variational autoencoders, are autoencoders that explicitly learn the distribution of the input image space rather than assuming no prior information about the distribution…
Online variable-weight scheduling with preempting on jobs with linear and exponential penalties
Frederick Tang, Fareed Sheriff, Andrew Wang
We analyze the problem of job scheduling with preempting on weighted jobs that can have either linear or exponential penalties. We review relevant literature on the problem and cre…
ELMOPP: An Application of Graph Theory and Machine Learning to Traffic Light Coordination
Fareed Sheriff
Traffic light management is a broad subject with various papers published that put forth algorithms to efficiently manage traffic using traffic lights. Two such algorithms are the…