REVIEW 2 cited by
Distribution free M-estimation
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
Distribution free M-estimation
read the original abstract
The basic question of delineating those statistical problems that are solvable without making any assumptions on the underlying data distribution has long animated statistics and learning theory. This paper characterizes when a convex M-estimation or stochastic optimization problem is solvable in such an assumption-free setting, providing a precise dividing line between solvable and unsolvable problems. The conditions we identify show, perhaps surprisingly, that Lipschitz continuity of the loss being minimized is not necessary for distribution free minimization, and they are also distinct from classical characterizations of learnability in machine learning.
Forward citations
Cited by 2 Pith papers
-
Finding a stationary point of a stochastic convex problem
A randomized proximal-point resampling algorithm achieves dist(0, ∂F_P(x̂_n) + N_X(x̂_n)) → 0 in probability for stochastic convex objectives, using dimension-theoretic graph decomposition to overcome lack of uniform ...
-
Finding a stationary point of a stochastic convex problem
For stochastic convex optimization, a randomized proximal-point algorithm achieves asymptotic ε-stationarity — the subdifferential genuinely contains a small element — without smoothness or Lipschitz-gradient assumptions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.