Strong self-concordance and sampling
Strong self-concordance and sampling
复制标题
较强的自一致性和抽样能力
DOI:
10.1145/3357713.3384272
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Vempala, Santosh
中科院分区:
文献类型:
--
作者:
Laddha, Aditi;Lee, Yin Tat;Vempala, Santosh
Motivated by the Dikin walk, we develop aspects of the interior-point theory for sampling in high dimension. Specifically, we introduce the notions of strong self-concordance and symmetry for a barrier. These properties imply that the Dikin walk defined using a strongly self-concordant barrier with symmetry parameter ν mixes in Õ(nν) steps from a warm start for a convex body in ℝn. For many natural barriers, ν is roughly bounded by ν, the standard self-concordance parameter. We also show that these properties hold for the Lee-Sidford barrier. As a consequence, we obtain the first walk that mixes in Õ(n2) steps for an arbitrary polytope in ℝn. Strong self-concordance for other barriers leads to an interesting (and unexpected) connection — for the universal and entropic barriers, it is implied by the KLS conjecture.
登录
查看更多内容
影响因子:
2.7
作者:
Lovász, L
通讯作者:
Lovász, L
DOI:
--
发表时间:
2014
期刊:
Annual Conference Computational Learning Theory
影响因子:
--
作者:
Sébastien Bubeck;Ronen Eldan
通讯作者:
Ronen Eldan
影响因子:
1.2
作者:
Adam Gustafson;Hariharan Narayanan
通讯作者:
Hariharan Narayanan
DOI:
10.1002/(sici)1098-2418(199708)11:1
发表时间:
1997
期刊:
Random Struct. Algorithms
影响因子:
--
作者:
R. Kannan;L. Lovász;M. Simonovits
通讯作者:
R. Kannan;L. Lovász;M. Simonovits
影响因子:
1
作者:
L. Lovász;S. Vempala
通讯作者:
L. Lovász;S. Vempala