Distribution free M-estimation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 9 of its 44 references that are in the map. First posted on arXiv 28 May 2025.
Builds on
9 of 44 references.
References · 9
- 2016Distribution-Free Predictive Inference For Regressioncited by 668
- 2021Adaptive Conformal Inference Under Distribution Shiftcited by 375
- 2019Lower Bounds for Non-Convex Stochastic Optimizationcited by 307
- 2023Conformal PID Control for Time Series Predictioncited by 88
- 2018How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGDcited by 57
- 2022Forecast Hedging and Calibrationcited by 22
- 2025Gradient Equilibrium in Online Learning: Theory and Applicationscited by 13
- 2016Local Minimax Complexity of Stochastic Convex Optimizationcited by 6
- 2020How to trap a gradient flowcited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.