Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 58 min ago
Peer-reviewedLicence not statedThe Annals of Statistics

Local minima of the empirical risk in high dimension: General theorems and convex examples

  • kiana Asgari1
  • Andrea Montanari A2
  • Basil Saeed3
  1. 1Department of Management Science and Engineering, Stanford University
  2. 2Department of Statistics and Department of Mathematics, Stanford University
  3. 3Department of Electrical Engineering, Stanford University
Open at sourcePDFDOICite

Related

  1. On minima of theta and Epstein zeta functions in dimension four
    Senping Luo, Juncheng Wei
    arXivPreprintCC BY 4.0Full textAlgebra & number theoryAnalysis & PDEsarXiv
  2. Optimal dimension growth rates in the high dimensional Central Limit Theorems
    Mayukh Choudhury, Debraj Das
    arXivPreprintarXiv licenceFull textProbabilityarXiv
  3. Dimension-free Convergence Rate in Sliced Wasserstein Distance for Empirical Measures of Markov Processes
    Feng-Yu Wang
    arXivPreprintCC0Full textProbabilityarXiv
  4. Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators
    Diego Martinez-Taboada, Aaditya Ramdas
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  5. Multi-Level General Fractional Derivatives: Fundamental Theorems and Applications
    Mina Ghasemi, Hashem P. Masiha, Manuel De La De La Sen
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref

Cite

BibTeXRIS
BibTeX
@article{asgari2026local,
  title = {{Local minima of the empirical risk in high dimension: General theorems and convex examples}},
  author = {kiana Asgari and Andrea Montanari A and Basil Saeed},
  journal = {The Annals of Statistics},
  year = {2026},
  month = oct,
  doi = {10.1214/26-aos2652},
  url = {http://arxiv.org/abs/2502.01953},
}
RIS
TY  - JOUR
TI  - Local minima of the empirical risk in high dimension: General theorems and convex examples
AU  - kiana Asgari
AU  - Andrea Montanari A
AU  - Basil Saeed
PY  - 2026
DA  - 2026/10/01
JO  - The Annals of Statistics
DO  - 10.1214/26-aos2652
UR  - http://arxiv.org/abs/2502.01953
SN  - 0090-5364
SN  - 2168-8966
ER  -