We examine how transformers cope with two challenges: learning basic int...
The theory of statistical learning has focused on variational objectives...
Simulation-free methods for training continuous-time generative models
c...
Let V_* : ℝ^d →ℝ be some (possibly non-convex)
potential function, and c...
Kernel two-sample testing provides a powerful framework for distinguishi...
When solving finite-sum minimization problems, two common alternatives t...
Differential privacy (DP) is the de facto standard for private data rele...
Learning high-dimensional distributions is often done with explicit
like...
Min-max optimization problems arise in several key machine learning setu...
We construct pairs of distributions μ_d, ν_d on ℝ^d such
that the quanti...
A well-known line of work (Barron, 1993; Breiman, 1993; Klusowski Ba...
Energy-based models (EBMs) are generative models that are usually traine...
Several works in implicit and explicit generative modeling empirically
o...
Energy-based models (EBMs) are a simple yet powerful framework for gener...
Advances in generative modeling and adversarial learning have given rise...
Finding Nash equilibria in two-player zero-sum continuous games is a cen...
Data-driven model training is increasingly relying on finding Nash equil...