More Like this

1. Faster Kernel Matrix Algebra via Density Estimation

   Backurs, A; Indyk, P; Musco, C; Wagner, T (January 2021, International Conference on Machine Learning)

   null (Ed.)

   We study fast algorithms for computing basic properties of an n x n positive semidefinite kernel matrix K corresponding to n points x_1,...,x_n in R^d. In particular, we consider the estimating the sum of kernel matrix entries, along with its top eigenvalue and eigenvector. These are some of the most basic problems defined over kernel matrices. We show that the sum of matrix entries can be estimated up to a multiplicative factor of 1+epsilon in time sublinear in n and linear in d for many popular kernel functions, including the Gaussian, exponential, and rational quadratic kernels. For these kernels, we also show that the top eigenvalue (and a witnessing approximate eigenvector) can be approximated to a multiplicative factor of 1+epsilon in time sub-quadratic in n and linear in d. Our algorithms represent significant advances in the best known runtimes for these problems. They leverage the positive definiteness of the kernel matrix, along with a recent line of work on efficient kernel density estimation. 

   more » « less
2. Time/Accuracy Tradeoffs for learning a ReLU with respect to Gaussian Marginals

   Goel, Surbhi; Karmalkar, Sushrut; Klivans, Adam (January 2019, Advances in neural information processing systems)

   We consider the problem of computing the best-fitting ReLU with respect to square-loss on a training set when the examples have been drawn according to a spherical Gaussian distribution (the labels can be arbitrary). Let 𝗈𝗉𝗍<1 be the population loss of the best-fitting ReLU. We prove: 1. Finding a ReLU with square-loss 𝗈𝗉𝗍+ϵ is as hard as the problem of learning sparse parities with noise, widely thought to be computationally intractable. This is the first hardness result for learning a ReLU with respect to Gaussian marginals, and our results imply -{\emph unconditionally}- that gradient descent cannot converge to the global minimum in polynomial time. 2. There exists an efficient approximation algorithm for finding the best-fitting ReLU that achieves error O(𝗈𝗉𝗍^{2/3}). The algorithm uses a novel reduction to noisy halfspace learning with respect to 0/1 loss. Prior work due to Soltanolkotabi [Sol17] showed that gradient descent can find the best-fitting ReLU with respect to Gaussian marginals, if the training set is exactly labeled by a ReLU. 

   more » « less
3. Robustly Learning Mixtures of k Arbitrary Gaussians

   https://doi.org/10.1145/3519935.3519953  

   Bakshi, Ainesh; Diakonikolas, Ilias; Jia, He; Kane, Daniel; Kothari, Pravesh; Vempala, Santosh S. (June 2022, Proceedings of the Annual ACM Symposium on Theory of Computing)

   We give a polynomial-time algorithm for the problem of robustly estimating a mixture of k arbitrary Gaussians in $R^d$, for any fixed k, in the presence of a constant fraction of arbitrary corruptions. This resolves the main open problem in several previous works on algorithmic robust statistics, which addressed the special cases of robustly estimating (a) a single Gaussian, (b) a mixture of TV-distance separated Gaussians, and (c) a uniform mixture of two Gaussians. Our main tools are an efficient partial clustering algorithm that relies on the sum-of-squares method, and a novel tensor decomposition algorithm that allows errors in both Frobenius norm and low-rank terms. 

   more » « less
4. Biased Kernel Density Estimators for Chance Constrained Optimal Control Problems

   https://doi.org/10.23919/ACC45564.2020.9148040  

   Keil, Rachel E.; Miller, Alexander; Kumar, Mrinal; Rao, Anil V. (July 2020, 2020 American Control Conference)

   null (Ed.)

   A method is developed for transforming chance constrained optimization problems to a form numerically solvable. The transformation is accomplished by reformulating the chance constraints as nonlinear constraints using a method that combines the previously developed Split-Bernstein approximation and kernel density estimator (KDE) methods. The Split-Bernstein approximation in a particular form is a biased kernel density estimator. The bias of this kernel leads to a nonlinear approximation that does not violate the bounds of the original chance constraint. The method of applying biased KDEs to reformulate chance constraints as nonlinear constraints transforms the chance constrained optimization problem to a deterministic optimization problems that retains key properties of the chance constrained optimization problem and can be solved numerically. This method can be applied to chance constrained optimal control problems. As a result, the Split-Bernstein and Gaussian kernels are applied to a chance constrained optimal control problem and the results are compared. 

   more » « less
5. Faster Kernel Matrix Algebra via Density Estimation.

   Backurs, Arturs; Indyk, Piotr; Musco, Cameron; Wagner, Tal. (January 2021, International Conference on Machine Learning (ICML))

   We study fast algorithms for computing fundamental properties of a positive semidefinite kernel matrix K∈ R^{n*n} corresponding to n points x1,…,xn∈R^d. In particular, we consider estimating the sum of kernel matrix entries, along with its top eigenvalue and eigenvector. We show that the sum of matrix entries can be estimated to 1+ϵ relative error in time sublinear in n and linear in d for many popular kernels, including the Gaussian, exponential, and rational quadratic kernels. For these kernels, we also show that the top eigenvalue (and an approximate eigenvector) can be approximated to 1+ϵ relative error in time subquadratic in n and linear in d. Our algorithms represent significant advances in the best known runtimes for these problems. They leverage the positive definiteness of the kernel matrix, along with a recent line of work on efficient kernel density estimation. 

   more » « less