14 citations · 26 across the 16 of their papers we have counts for
14 papers · 1 filter
Adaptive Bayes exactly tracks information over intrinsic time
Akshay Balsubramani
Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback. We show that the regret of any such update obeys an exact information-acc…
The concentration game: Bayesian updating, regret, and information
Akshay Balsubramani
We give a two-player zero-sum repeated game between a learner and nature whose value identity generates Bayesian updating and an exact accounting of exponential-weights regret at o…
Out-of-Distribution Detection Methods Answer the Wrong Questions
Yucen Lily Li, Daohan Lu, Polina Kirichenko +4
To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained…
Entropy, concentration, and learning: a statistical mechanics primer
Akshay Balsubramani
Artificial intelligence models trained through loss minimization have demonstrated significant success, grounded in principles from fields like information theory and statistical p…
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh, Shiori Sagawa, Henrik Marklund +20
Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the…
Sharp finite-sample concentration of independent variables
Akshay Balsubramani
We show an extension of Sanov's theorem on large deviations, controlling the tail probabilities of i.i.d. random variables with matching concentration and anti-concentration bounds…