4 papers · 1 filter
Instance-optimal stochastic convex optimization: Can we improve upon sample-average and robust stochastic approximation?
Liwei Jiang, Ashwin Pananjady
We study the unconstrained minimization of a smooth and strongly convex population loss function under a stochastic oracle that introduces both additive and multiplicative noise; t…
Multiscale replay: A robust algorithm for stochastic variational inequalities with a Markovian buffer
Milind Nakul, Tianjiao Li, Ashwin Pananjady
We introduce the Multiscale Experience Replay (MER) algorithm for solving a class of stochastic variational inequalities (VIs) in settings where samples are generated from a Markov…
Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization
Kabir Aladin Chandrasekher, Mengqi Lou, Ashwin Pananjady
We consider the problem of estimating the factors of a rank- matrix with i.i.d. Gaussian, rank- measurements that are nonlinearly transformed and corrupted by noise. Consider…
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright +1
We study stochastic approximation procedures for approximately solving a -dimensional linear fixed point equation based on observing a trajectory of length from an ergodic M…