We introduce a machine-learning framework to warm-start fixed-point
opti...
Recent works in learning-integrated optimization have shown promise in
s...
Simulation-free methods for training continuous-time generative models
c...
This paper focuses on computing the convex conjugate operation that aris...
Natural agents can effectively learn from multiple data sources that dif...
We present Theseus, an efficient application-agnostic open source librar...
Continuous Normalizing Flows (CNFs) are a class of generative models tha...
We study the use of amortized optimization to predict optimal transport ...
Mapping between discrete and continuous distributions is a difficult tas...
Optimization is a ubiquitous modeling tool that is often deployed in set...
The gradients of convex functions are expressive models of non-trivial v...
Cross-domain imitation learning studies how to leverage expert demonstra...
Lookahead search has been a critical component of recent AI successes, s...
Fixed-point iterations are at the heart of numerical computing and are o...
Modeling distributions on Riemannian manifolds is a crucial component in...
Bridging logical and algorithmic reasoning with modern machine learning
...
Model-based reinforcement learning is a compelling framework for
data-ef...
We propose a new class of parameterizations for spatio-temporal point
pr...
The existing Neural ODE formulation relies on an explicit knowledge of t...
Model-based reinforcement learning approaches add explicit domain knowle...
Dynamic time warping (DTW) is a useful method for aligning, comparing an...
Model-based reinforcement learning (MBRL) has been shown to be a powerfu...
Recent work has shown how to embed differentiable optimization problems ...
Many (but not all) approaches self-qualifying as "meta-learning" in deep...
Training an agent to solve control tasks directly from high-dimensional
...
We study the Cross-Entropy Method (CEM) for the non-convex optimization ...
We propose the Limited Multi-Label (LML) projection layer as a new primi...
We present foundations for using Model Predictive Control (MPC) as a
dif...
A fundamental challenge in imperfect-information games is that states do...
We consider the setting of an agent with a fixed body interacting with a...
This paper presents OptNet, a network architecture that integrates
optim...