Travelled to:1 × Germany
4 × USA
Collaborated with:G.J.Gordon M.Likhachev A.Blum D.Golovin M.Young D.Sculley B.Bryan C.M.Schafer J.G.Schneider G.Holt D.Sculley D.Ebner J.Grady L.Nie T.Phillips E.Davydov S.Chikkerur D.Liu M.Wattenberg A.M.Hrafnkelsson T.Boulos J.Kubica
Talks about:bound (2) adversari (1) guarante (1) function (1) program (1) presenc (1) predict (1) perform (1) monoton (1) minimax (1)
Person: H. Brendan McMahan
DBLP: McMahan:H=_Brendan
Contributed to:
2013
2013200720052003Wrote 5 papers:
- ICML-c2-2013-GolovinSMY #learning #ram #scalability
- Large-Scale Learning with Less RAM via Randomization (DG, DS, HBM, MY), pp. 325–333.
- KDD-2013-McMahanHSYEGNPDGCLWHBK #predict
- Ad click prediction: a view from the trenches (HBM, GH, DS, MY, DE, JG, LN, TP, ED, DG, SC, DL, MW, AMH, TB, JK), pp. 1222–1230.
- ICML-2007-BryanMSS
- Efficiently computing minimax expected-size confidence regions (BB, HBM, CMS, JGS), pp. 97–104.
- ICML-2005-McMahanLG #bound #performance #programming #realtime
- Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees (HBM, ML, GJG), pp. 569–576.
- ICML-2003-McMahanGB #cost analysis
- Planning in the Presence of Cost Functions Controlled by an Adversary (HBM, GJG, AB), pp. 536–543.