We consider stochastic unconstrained bilevel optimization problems when only the first-order
gradient oracles are available. While numerous optimization methods have been proposed …

Modern machine learning models deployed in the wild can encounter both covariate and
semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OOD …

In this work, we consider the regret minimization problem for reinforcement learning in latent
Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of …

In this work, we study first-order algorithms for solving Bilevel Optimization (BO) where the
objective functions are smooth but possibly nonconvex in both levels and the variables are …

The Expectation-Maximization algorithm is perhaps the most broadly used algorithm for
inference of latent variable problems. A theoretical understanding of its performance, however, …

We study the convergence rates of the EM algorithm for learning two-component mixed
linear regression under all regimes of signal-to-noise ratio (SNR). We resolve a long-standing …

We consider solving the low-rank matrix sensing problem with the Factorized Gradient Descent
(FGD) method when the specified rank is larger than the true rank. We refer to this as over…

We study the convergence of the Expectation-Maximization (EM) algorithm for mixtures of
linear regressions with an arbitrary number $ k $ of components. We show that as long as …

Learning a near optimal policy in a partially observable system remains an elusive challenge
in contemporary reinforcement learning. In this work, we consider episodic reinforcement …

We consider the problem of spherical Gaussian Mixture models with $ k\geq 3$ components
when the components are well separated. A fundamental previous result established that …