Eric Vanden-Eijnden

14

Papers

82

Total Citations

Papers (14)

NETS: A Non-equilibrium Transport Sampler

How to build a consistency model: Learning flow maps via self-distillation

Multimarginal Generative Modeling with Stochastic Interpolants

Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy

Multitask Learning with Stochastic Interpolants

Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes

Stochastic Interpolants with Data-Dependent Couplings

Neuron birth-death dynamics accelerates gradient descent and converges asymptotically

Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

A Dynamical Central Limit Theorem for Shallow Neural Networks

Learning sparse features can lead to overfitting in neural networks

Learning Optimal Flows for Non-Equilibrium Importance Sampling

Efficient Training of Energy-Based Models Using Jarzynski Equality