A 2023 law championed by Republicans requires the CDC have a director confirmed by the Senate. For months, though, it's had only acting directors--and the White House won't say when that will change. As the agency rotates through a cast of leaders, it's unclear when--or if--the US Centers for Disease Control and Prevention will get a permanent director under Donald Trump's second term as president. Following Jim O'Neill's departure as acting CDC director last week, National Institutes of Health director Jay Bhattacharya will now lead both agencies temporarily. It's the latest in a series of shakeups at Trump's CDC, which has lost about a quarter of its staff to mass layoffs carried out by Health and Human Services Secretary Robert F. Kennedy, Jr. last year.

Modern machine learning systems are able to learn extremely complicated relations from data.

Temporal Domain Generalization (TDG) addresses the challenge of training predictive models under temporally varying data distributions. Traditional TDG approaches typically focus on domain data collected at fixed, discrete time intervals, which limits their capability to capture the inherent dynamics within continuous-evolving and irregularly-observed temporal domains.

Our analysis operates in a "batched"

We investigate the convergence rates and data sample sizes required for training a machine learning model using a stochastic gradient descent (SGD) algorithm, where data points are sampled based on either their loss value or uncertainty value. These training methods are particularly relevant for active learning and data subset selection problems. For SGD with a constant step size update, we present convergence results for linear classifiers and linearly separable datasets using squared hinge loss and similar training loss functions.