Travelled to:1 × Australia
2 × United Kingdom
4 × USA
Collaborated with:M.Bowling ∅ T.R.Balch N.D.Ratliff J.A.Bagnell J.Langford S.Kakade W.Chu L.Li A.Thomas B.L.Tseng S.Pandey M.Aly A.Bagherjeiran A.O.Hatch P.Ciccolo A.Ratnaparkhi
Talks about:learn (3) target (2) onlin (2) infinitesim (1) tradeoff (1) symmetri (1) gradient (1) competit (1) behavior (1) program (1)
Person: Martin Zinkevich
DBLP: Zinkevich:Martin
Contributed to:
2012
2011
20112006200320022001Wrote 7 papers:
- ICML-2012-BowlingZ #on the
- On Local Regret (MB, MZ), p. 56.
- CIKM-2011-PandeyABHCRZ #behaviour #learning #what
- Learning to target: what works for behavioral targeting (SP, MA, AB, AOH, PC, AR, MZ), pp. 1805–1814.
- KDD-2011-ChuZLTT #data type #learning #online
- Unbiased online active learning in data streams (WC, MZ, LL, AT, BLT), pp. 195–203.
- ICML-2006-RatliffBZ
- Maximum margin planning (NDR, JAB, MZ), pp. 729–736.
- ICML-2003-Zinkevich #online #programming
- Online Convex Programming and Generalized Infinitesimal Gradient Ascent (MZ), pp. 928–936.
- ICML-2002-LangfordZK #analysis #trade-off
- Competitive Analysis of the Explore/Exploit Tradeoff (JL, MZ, SK), pp. 339–346.
- ICML-2001-ZinkevichB #learning #markov #multi #process #symmetry
- Symmetry in Markov Decision Processes and its Implications for Single Agent and Multiagent Learning (MZ, TRB), p. 632–?.