Recent works have shown that diffusion models can learn essentially any distribution
provided one can perform score estimation. Yet it remains poorly understood under what …

Most graph-network-based meta-learning approaches model instance-level relation of
examples. We extend this idea further to explicitly model the distribution-level relation of one …

Spectral methods have emerged as a simple yet surprisingly effective approach for
extracting information from massive, noisy and incomplete data. In a nutshell, spectral …

We study high-dimensional distribution learning in an agnostic setting where an adversary is
allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history …

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 estimating the mean and covariance of a distribution from iid
samples in the presence of a fraction of malicious noise. This is in contrast to much recent …

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 …

The adversarial training procedure proposed by Madry et al.(2018) is one of the most
effective methods to defend against adversarial examples in deep neural networks (DNNs) …

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 …