REVIEW 4 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Empirical Bernstein in smooth Banach spaces
read the original abstract
Existing concentration bounds for bounded vector-valued random variables include extensions of the scalar Hoeffding and Bernstein inequalities. While the latter is typically tighter, it requires knowing a bound on the variance of the random variables. We derive a new vector-valued empirical Bernstein inequality, which makes use of an empirical estimator of the variance instead of the true variance. The bound holds in 2-smooth separable Banach spaces, which include finite dimensional Euclidean spaces and separable Hilbert spaces. The resulting confidence sets are instantiated for both the batch setting (where the sample size is fixed) and the sequential setting (where the sample size is a stopping time). The confidence set width asymptotically exactly matches that achieved by Bernstein in the leading term.
Forward citations
Cited by 4 Pith papers
-
Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
Finite-width shallow networks remain within poly(d) m^{-min(1,c/6)} of their mean-field limit uniformly in time when mean-field excess loss decays as t^{-c} under standard regularity and an integral condition on the loss.
-
Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity
Derives vector-valued self-normalized concentration bounds for light-tailed processes beyond sub-Gaussianity, with applications to online linear regression and linear bandits.
-
Bernstein-type dimension-free concentration for self-normalised martingales
Introduces a dimension-free Bernstein-type concentration inequality for self-normalised martingales and applies it to ellipsoidal confidence sequences in logistic regression with Hilbert-valued covariates and instance...
-
The Power of Power Law: Asymmetry Enables Compositional Reasoning
Power-law data sampling creates beneficial asymmetry in the loss landscape that lets models acquire high-frequency skill compositions first, enabling more efficient learning of rare long-tail skills than uniform distr...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.