Recent works have shown that diffusion models can learn essentially any
...
A key problem when modeling signal integrity for passive filters and
int...
We present the first diffusion-based framework that can learn an unknown...
We prove several hardness results for training depth-2 neural networks w...
We consider the problem of distribution-free learning for Boolean functi...
Graphical models are powerful tools for modeling high-dimensional data, ...
We give the first statistical-query lower bounds for agnostically learni...
We prove the first superpolynomial lower bounds for learning one-layer n...
Recent empirical works show that large deep neural networks are often hi...
We consider the problem of computing the best-fitting ReLU with respect ...
We give the first polynomial-time algorithm for robust regression in the...
We give the first polynomial-time algorithm for performing linear or
pol...
We give the first provably efficient algorithm for learning a one hidden...
We give a polynomial-time algorithm for learning neural networks with on...
We give a simple, fast algorithm for hyperparameter optimization inspire...
Given a graphical model, one essential problem is MAP inference, that is...