Travelled to:1 × Australia
1 × France
1 × Israel
3 × USA
Collaborated with:J.Langford A.Beygelzimer M.J.Kearns Y.W.Teh S.T.Roweis M.Zinkevich R.Frostig R.Ge A.Sidford A.Anandkumar D.Hsu A.Javanmard N.Srinivas A.Krause M.W.Seeger
Talks about:approxim (3) explor (2) optim (2) learn (2) experiment (1) markovian (1) algorithm (1) tradeoff (1) stochast (1) reinforc (1)
Person: Sham Kakade
DBLP: Kakade:Sham
Contributed to:
201520132010200620032002Wrote 8 papers:
- ICML-2015-FrostigGKS #algorithm #approximate #empirical #named #performance #probability
- Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization (RF, RG, SK, AS), pp. 2540–2548.
- ICML-c1-2013-AnandkumarHJK #learning #linear #network
- Learning Linear Bayesian Networks with Latent Variables (AA, DH, AJ, SK), pp. 249–257.
- ICML-2010-SrinivasKKS #design #optimisation #process
- Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design (NS, AK, SK, MWS), pp. 1015–1022.
- ICML-2006-BeygelzimerKL #nearest neighbour
- Cover trees for nearest neighbor (AB, SK, JL), pp. 97–104.
- ICML-2003-KakadeKL #metric
- Exploration in Metric State Spaces (SK, MJK, JL), pp. 306–312.
- ICML-2002-KakadeL #approximate #learning
- Approximately Optimal Approximate Reinforcement Learning (SK, JL), pp. 267–274.
- ICML-2002-KakadeTR #markov
- An Alternate Objective Function for Markovian Fields (SK, YWT, STR), pp. 275–282.
- ICML-2002-LangfordZK #analysis #trade-off
- Competitive Analysis of the Explore/Exploit Tradeoff (JL, MZ, SK), pp. 339–346.