Universal Barrier Is n-Self-Concordant

References

• [1] Abernethy J , Rakhlin A (2009) Beating the adaptive bandit with high probability. Inform. Theory Appl. Workshop (IEEE, Piscataway, NJ), 280–289.Google Scholar
• [2] Brazitikos S , Giannopoulos A , Valettas P , Vritsiou BH (2014) Geometry of Isotropic Convex Bodies, Mathematical Surveys and Monographs, vol. 196 (American Mathematical Society, Providence, RI).Google Scholar
• [3] Bubeck S , Eldan R (2015) The entropic barrier: A simple and optimal universal self-concordant barrier. Lawrence N, Reid M, eds. Conf. Learn. Theory (Proceedings of Machine Learning Research, Cambridge, MA), 279–279.Google Scholar
• [4] Fox DJ (2015) A Schwarz lemma for Kähler affine metrics and the canonical potential of a proper convex cone. Annali di Matematica Pura ed Applicata (1923-) 194(1):1–42.Google Scholar
• [5] Fradelizi M , Guédon O (2004) The extreme points of subsets of s-concave probabilities and a geometric localization theorem. Discrete Computational Geometry 31(2):327–335.Crossref, Google Scholar
• [6] Güler O (1996) Barrier functions in interior point methods. Math. Oper. Res. 21(4):860–885.Link, Google Scholar
• [7] Hildebrand R (2014) Canonical barriers on convex cones. Math. Oper. Res. 39(3):841–850.Link, Google Scholar
• [8] Lee YT , Sidford A (2014) Path finding methods for linear programming: Solving linear programs in O ˜ ( rank ) iterations and faster algorithms for maximum flow. Bilof R, ed. 2014 IEEE 55th Annual Symp Foundations Comput. Sci. (FOCS) (IEEE, Piscataway, NJ), 424–433.Google Scholar
• [9] Narayanan H , Rakhlin A (2010) Random walk approach to regret minimization. Lafferty J, Williams C, Shawe-Taylor J, Zemel R, Culotta A, eds. Adv. Neural Inform. Processing Systems (NeurIPS Proceedings, Vancouver, BC), 1777–1785.Google Scholar
• [10] Nesterov Y , Nemirovski A (1994) Interior-Point Polynomial Algorithms in Convex Programming , vol. 13 (SIAM, Philadelphia, PA).Crossref, Google Scholar