Forl = 2, i. e., for 3 - cycles, thisrelationship is X ikX kj= X ij. Figure 1: Averagematchingerrorunderthe LBCmodel ( left) and LACmodel ( right).

We propose a new algorithm for the problem of recovering data that adheres to multiple, heterogeneous low-dimensional structures from linear observations.

Tothis end,wepropose adeep latent variable model thatiscapable oflearning rewards from demonstrations of distinct but related tasks in an unsupervised way.

However, the inferred reward function often fails to capture the underlying task objective.

The problem of inverse reinforcement learning (IRL) is relevant to a variety of tasks including valuealignment androbot learning fromdemonstration.

However, since this proof relies on the existence of a convergent subsequence, their proof does not reveal any rate forglobal convergence.

We advance both the theory and practice of robust $\ell_p$-quasinorm regression for $p \in (0,1]$ by using novel variants of iteratively reweighted least-squares (IRLS) to solve the underlying non-smooth problem. In the convex case, $p=1$, we prove that this IRLS variant converges globally at a linear rate under a mild, deterministic condition on the feature matrix called the stable range space property. In the non-convex case, $p\in(0,1)$, we prove that under a similar condition, IRLS converges locally to the global minimizer at a superlinear rate of order $2-p$; the rate becomes quadratic as $p\to 0$. We showcase the proposed methods in three applications: real phase retrieval, regression without correspondences, and robust face restoration. The results show that (1) IRLS can handle a larger number of outliers than other methods, (2) it is faster than competing methods at the same level of accuracy, (3) it restores a sparsely corrupted face image with satisfactory visual quality.

Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert. Many algorithms for IRL have an inherent nested structure: the inner loop finds the optimal policy given parametrized rewards while the outer loop updates the estimates towards optimizing a measure of fit. For high dimensional environments such nested-loop structure entails a significant computational burden. To reduce the computational burden of a nested loop, novel methods such as SQIL \cite{reddy2019sqil} and IQ-Learn \cite{garg2021iq} emphasize policy estimation at the expense of reward estimation accuracy. However, without accurate estimated rewards, it is not possible to do counterfactual analysis such as predicting the optimal policy under different environment dynamics and/or learning new tasks.