Statistical Learning
RankAssumptions
Kernel methods augmented with random features give scalable algorithms for learning from big data.
RobustTestinginHigh-DimensionalSparseModels
In the first model, we are givenn i.i.d.
Public-data Assisted Private Stochastic Optimization: Power and Limitations
We study the limits and capability of public-data assisted differentially private (P A-DP) algorithms. Specifically, we focus on the problem of stochastic convex optimization (SCO) with either labeled or unlabeled public data.
We thank the reviewers for the careful comments, questions, and recommendations that surely will improve the quality
As R#1 and R#2 mentioned, there is a strong relation between NPCs and 1-NN.
RandomShufflingBeatsSGDOnlyAfterMany EpochsonIll-ConditionedProblems
However, known lower bounds ignore the problem's geometry,including itscondition number,whereas theupper bounds explicitly depend on it. Perhaps surprisingly, we prove that when the condition number is taken into account, without-replacement SGDdoesnotsignificantly improveon withreplacement SGD in terms of worst-case bounds, unless the number of epochs (passes overthedata) islargerthanthecondition number.
