Travelled to:
1 × Australia
1 × Israel
1 × United Kingdom
2 × France
3 × USA
Collaborated with:
R.Jin L.Zhang S.Zhu A.K.Jain Y.Zhou Q.Lin X.He P.Zhao S.C.H.Hoi Y.Chi J.Yi W.Liu J.Wang M.Ji B.Lin J.Han M.Mahdavi W.Tong
Talks about:
learn (3) algorithm (2) supervis (2) stochast (2) general (2) random (2) optim (2) noisi (2) error (2) bound (2)
Person: Tianbao Yang
DBLP: Yang:Tianbao
Contributed to:
Wrote 11 papers:
- ICML-2015-Yang0JZ #bound #fault #set
- An Explicit Sampling Dependent Spectral Error Bound for Column Subset Selection (TY, LZ, RJ, SZ), pp. 135–143.
- ICML-2015-Yang0JZ15a #random #reduction
- Theory of Dual-sparse Regularized Randomized Reduction (TY, LZ, RJ, SZ), pp. 305–314.
- KDD-2015-YangLJ #big data #data analysis #optimisation
- Big Data Analytics: Optimization and Randomization (TY, QL, RJ), p. 2327.
- KDD-2015-Yi0YLW #algorithm #clustering #constraints #performance
- An Efficient Semi-Supervised Clustering Algorithm with Sequential Constraints (JY, LZ, TY, WL, JW), pp. 1405–1414.
- ICML-c3-2013-ZhangYJH #optimisation #probability
- O(logT) Projections for Stochastic Optimization of Smooth and Strongly Convex Functions (LZ, TY, RJ, XH), pp. 1121–1129.
- ICML-2012-JiYLJH #algorithm #bound #fault #learning
- A Simple Algorithm for Semi-supervised Learning with Improved Generalization Error Bound (MJ, TY, BL, RJ, JH), p. 110.
- ICML-2012-YangMJZZ #kernel #learning #multi #probability #programming
- Multiple Kernel Learning from Noisy Labels by Stochastic Programming (TY, MM, RJ, LZ, YZ), p. 21.
- ICML-2011-ZhaoHJY #online
- Online AUC Maximization (PZ, SCHH, RJ, TY), pp. 233–240.
- ICML-2010-YangJJ #learning
- Learning from Noisy Side Information by Generalized Maximum Entropy Model (TY, RJ, AKJ), pp. 1199–1206.
- KDD-2010-YangJJZT #categorisation #classification
- Unsupervised transfer classification: application to text categorization (TY, RJ, AKJ, YZ, WT), pp. 1159–1168.
- KDD-2009-YangJCZ #approach #community #detection
- Combining link and content for community detection: a discriminative approach (TY, RJ, YC, SZ), pp. 927–936.