70 citations · 560 across the 53 of their papers we have counts for
4 papers · 1 filter
Beating the Minimax Rate of Active Learning with Prior Knowledge
Lijun Zhang, Mehrdad Mahdavi, Rong Jin
Active learning refers to the learning protocol where the learner is allowed to choose a subset of instances for labeling. Previous studies have shown that, compared with passive l…
Efficient Distance Metric Learning by Adaptive Sampling and Mini-Batch Stochastic Gradient Descent (SGD)
Qi Qian, Rong Jin, Jinfeng Yi +2
Distance metric learning (DML) is an important task that has found applications in many domains. The high computational cost of DML arises from the large number of variables to be…
O(logT) Projections for Stochastic Optimization of Smooth and Strongly Convex Functions
Lijun Zhang, Tianbao Yang, Rong Jin +1
Traditional algorithms for stochastic optimization require projecting the solution at each iteration into a given domain to ensure its feasibility. When facing complex domains, suc…
Optimal Stochastic Strongly Convex Optimization with a Logarithmic Number of Projections
Jianhui Chen, Tianbao Yang, Qihang Lin +2
We consider stochastic strongly convex optimization with a complex inequality constraint. This complex inequality constraint may lead to computationally expensive projections in al…