Travelled to:1 × China
1 × Finland
1 × France
4 × USA
Collaborated with:S.Chakrabarti M.J.Wainwright L.Bottou ∅ J.Langford S.Negahban P.D.Ravikumar S.Aggarwal K.Chang A.Krishnamurthy H.D.III S.M.Kakade N.Karampatziakis L.Song G.Valiant D.Hsu S.Kale L.Li R.E.Schapire
Talks about:learn (3) algorithm (2) predict (2) optim (2) graph (2) rank (2) multiclass (1) decomposit (1) structur (1) contextu (1)
Person: Alekh Agarwal
DBLP: Agarwal:Alekh
Contributed to:
201520142013201120082007
2006Wrote 9 papers:
- ICML-2015-AgarwalB #bound #finite #optimisation
- A Lower Bound for the Optimization of Finite Sums (AA, LB), pp. 78–86.
- ICML-2015-ChangKADL #education #learning
- Learning to Search Better than Your Teacher (KWC, AK, AA, HDI, JL), pp. 2058–2066.
- ICML-c2-2014-AgarwalHKLLS #algorithm #performance
- Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits (AA, DH, SK, JL, LL, RES), pp. 1638–1646.
- ICML-c2-2014-AgarwalKKSV #multi #predict #scalability
- Least Squares Revisited: Scalable Approaches for Multi-class Prediction (AA, SMK, NK, LS, GV), pp. 541–549.
- ICML-c3-2013-Agarwal #algorithm #multi #predict
- Selective sampling algorithms for cost-sensitive multiclass prediction (AA), pp. 1220–1228.
- ICML-2011-AgarwalNW #composition #matrix
- Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions (AA, SN, MJW), pp. 1129–1136.
- ICML-2008-RavikumarAW #convergence #linear #message passing #source code
- Message-passing for graph-structured linear programs: proximal projections, convergence and rounding schemes (PDR, AA, MJW), pp. 800–807.
- ICML-2007-AgarwalC #graph #learning #random #rank
- Learning random walks to rank nodes in graphs (AA, SC), pp. 9–16.
- KDD-2006-AgarwalCA #learning #rank
- Learning to rank networked entities (AA, SC, SA), pp. 14–23.