This work considers a computationally and statistically efficient parameter estimation method
for a wide class of latent variable models—including Gaussian mixture models, hidden …

We consider the problem of controlling a possibly unknown linear dynamical system with
adversarial perturbations, adversarially chosen convex loss functions, and partially …

We describe a general technique that yields the first Statistical Query lower bounds for a
range of fundamental high-dimensional learning problems involving Gaussian distributions …

Many real-world problems involve the optimization of multiple, possibly conflicting
objectives. Multi-objective reinforcement learning (MORL) is a generalization of standard …

We use smoothed analysis techniques to provide guarantees on the training loss of
Multilayer Neural Networks (MNNs) at differentiable local minima. Specifically, we examine …

We use the Sum of Squares method to develop new efficient algorithms for learning well-
separated mixtures of Gaussians and robust mean estimation, both in high dimensions, that …

In the classical transformer attention scheme, we are given three $ n\times d $ size matrices
$ Q, K, V $(the query, key, and value tokens), and the goal is to compute a new $ n\times d …

Training neural networks is a challenging non-convex optimization problem, and
backpropagation or gradient descent can get stuck in spurious local optima. We propose a …

We develop efficient algorithms for estimating low-degree moments of unknown distributions
in the presence of adversarial outliers and design a new family of convex relaxations for k …

We study the problem of list-decodable (robust) Gaussian mean estimation and the related
problem of learning mixtures of separated spherical Gaussians. In the former problem, we …