We study stochastic convex optimization under infinite noise variance. Specifically, when the
stochastic gradient is unbiased and has uniformly bounded $(1+\kappa) $-th moment, for …

We study high-dimensional robust statistics tasks in the streaming model. A recent line of
work obtained computationally efficient algorithms for a range of high-dimensional robust …

Noise-contrastive estimation (NCE) is a statistically consistent method for learning
unnormalized probabilistic models. It has been empirically observed that the choice of the …

We propose SGD-exp, a stochastic gradient descent approach for linear and ReLU
regressions under Massart noise (adversarial semi-random corruption model) for the fully …

We consider the optimization of a smooth and strongly convex objective using constant step-
size stochastic gradient descent (SGD) and study its properties through the prism of Markov …

We study algorithms for online change-point detection (OCPD), where samples that are
potentially heavy-tailed, are presented one at a time and a change in the underlying mean …

The real-time estimation of time-varying parameters from high-dimensional, heavy-tailed
and corrupted data-streams is a common sub-routine in systems ranging from those for …

Statistical inference has a long history of established algorithms with theoretical guarantees,
but modern machine learning applications impose new statistical and computational …