6 papers
A spectral least-squares-type method for heavy-tailed corrupted regression with unknown covariance \& heterogeneous noise
Roberto I. Oliveira, Zoraida F. Rico, Philip Thompson
We revisit heavy-tailed corrupted least-squares linear regression assuming to have a corrupted -sized label-feature sample of at most arbitrary outliers. We wish to estimat…
Outlier-robust estimation of a sparse linear model using -penalized Huber's -estimator
Arnak S. Dalalyan, Philip Thompson
We study the problem of estimating a -dimensional -sparse vector in a linear model with Gaussian design and additive noise. In the case where the labels are contaminated by a…
Restricted eigenvalue property for corrupted Gaussian designs
Philip Thompson, Arnak S. Dalalyan
Motivated by the construction of tractable robust estimators via convex relaxations, we present conditions on the sample size which guarantee an augmented notion of Restricted Eige…
On variance reduction for stochastic smooth convex optimization with multiplicative noise
Alejandro Jofré, Philip Thompson
We propose dynamic sampled stochastic approximation (SA) methods for stochastic optimization with a heavy-tailed distribution (with finite 2nd moment). The objective is the sum of…
Incremental constraint projection methods for monotone stochastic variational inequalities
Alfredo Iusem, Alejandro Jofré, Philip Thompson
We consider stochastic variational inequalities with monotone operators defined as the expected value of a random operator. We assume the feasible set is the intersection of a larg…
Extragradient method with variance reduction for stochastic variational inequalities
Alfredo Iusem, Alejandro Jofré, Roberto I. Oliveira +1
We propose an extragradient method with stepsizes bounded away from zero for stochastic variational inequalities requiring only pseudo-monotonicity. We provide convergence and comp…