b'Brandon Amos'

research

∙ 09/14/2023

Learning to Warm-Start Fixed-Point Optimization Algorithms

We introduce a machine-learning framework to warm-start fixed-point opti...

0 Rajiv Sambharya, et al. ∙

research

∙ 07/18/2023

Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information

Recent works in learning-integrated optimization have shown promise in s...

0 Arman Zharmagambetov, et al. ∙

research

∙ 04/28/2023

Multisample Flow Matching: Straightening Flows with Minibatch Couplings

Simulation-free methods for training continuous-time generative models c...

1 Aram-Alexandre Pooladian, et al. ∙

research

∙ 10/21/2022

On amortizing convex conjugates for optimal transport

This paper focuses on computing the convex conjugate operation that aris...

0 Brandon Amos, et al. ∙

research

∙ 10/12/2022

Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

Natural agents can effectively learn from multiple data sources that dif...

0 Qinqing Zheng, et al. ∙

research

∙ 07/19/2022

Theseus: A Library for Differentiable Nonlinear Optimization

We present Theseus, an efficient application-agnostic open source librar...

24 Luis Pineda, et al. ∙

research

∙ 07/11/2022

Matching Normalizing Flows and Probability Paths on Manifolds

Continuous Normalizing Flows (CNFs) are a class of generative models tha...

12 Heli Ben-Hamu, et al. ∙

research

∙ 06/10/2022

Meta Optimal Transport

We study the use of amortized optimization to predict optimal transport ...

0 Brandon Amos, et al. ∙

research

∙ 03/14/2022

Semi-Discrete Normalizing Flows through Differentiable Tessellation

Mapping between discrete and continuous distributions is a difficult tas...

0 Ricky T. Q. Chen, et al. ∙

research

∙ 02/01/2022

Tutorial on amortized optimization for learning to optimize over continuous domains

Optimization is a ubiquitous modeling tool that is often deployed in set...

0 Brandon Amos, et al. ∙

research

∙ 11/23/2021

Input Convex Gradient Networks

The gradients of convex functions are expressive models of non-trivial v...

1 Jack Richter-Powell, et al. ∙

research

∙ 10/07/2021

Cross-Domain Imitation Learning via Optimal Transport

Cross-domain imitation learning studies how to leverage expert demonstra...

1 Arnaud Fickinger, et al. ∙

research

∙ 09/30/2021

Scalable Online Planning via Reinforcement Learning Fine-Tuning

Lookahead search has been a critical component of recent AI successes, s...

4 Arnaud Fickinger, et al. ∙

research

∙ 07/21/2021

Neural Fixed-Point Acceleration for Convex Optimization

Fixed-point iterations are at the heart of numerical computing and are o...

0 Shobha Venkataraman, et al. ∙

research

∙ 06/18/2021

Riemannian Convex Potential Maps

Modeling distributions on Riemannian manifolds is a crucial component in...

6 Samuel Cohen, et al. ∙

research

∙ 05/05/2021

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints

Bridging logical and algorithmic reasoning with modern machine learning ...

0 Anselm Paulus, et al. ∙

research

∙ 04/20/2021

MBRL-Lib: A Modular Library for Model-based Reinforcement Learning

Model-based reinforcement learning is a compelling framework for data-ef...

0 Luis Pineda, et al. ∙

research

∙ 11/09/2020

Neural Spatio-Temporal Point Processes

We propose a new class of parameterizations for spatio-temporal point pr...

0 Ricky T. Q. Chen, et al. ∙

research

∙ 11/08/2020

Learning Neural Event Functions for Ordinary Differential Equations

The existing Neural ODE formulation relies on an explicit knowledge of t...

0 Ricky T. Q. Chen, et al. ∙

research

∙ 08/28/2020

On the model-based stochastic value gradient for continuous reinforcement learning

Model-based reinforcement learning approaches add explicit domain knowle...

6 Brandon Amos, et al. ∙

research

∙ 06/22/2020

Aligning Time Series on Incomparable Spaces

Dynamic time warping (DTW) is a useful method for aligning, comparing an...

17 Samuel Cohen, et al. ∙

research

∙ 02/11/2020

Objective Mismatch in Model-based Reinforcement Learning

Model-based reinforcement learning (MBRL) has been shown to be a powerfu...

0 Nathan Lambert, et al. ∙

research

∙ 10/28/2019

Differentiable Convex Optimization Layers

Recent work has shown how to embed differentiable optimization problems ...

78 Akshay Agrawal, et al. ∙

research

∙ 10/03/2019

Generalized Inner Loop Meta-Learning

Many (but not all) approaches self-qualifying as "meta-learning" in deep...

12 Edward Grefenstette, et al. ∙

research

∙ 10/02/2019

Improving Sample Efficiency in Model-Free Reinforcement Learning from Images

Training an agent to solve control tasks directly from high-dimensional ...

18 Denis Yarats, et al. ∙

research

∙ 09/27/2019

The Differentiable Cross-Entropy Method

We study the Cross-Entropy Method (CEM) for the non-convex optimization ...

28 Brandon Amos, et al. ∙

research

∙ 06/20/2019

The Limited Multi-Label Projection Layer

We propose the Limited Multi-Label (LML) projection layer as a new primi...

0 Brandon Amos, et al. ∙

research

∙ 10/31/2018

Differentiable MPC for End-to-end Planning and Control

We present foundations for using Model Predictive Control (MPC) as a dif...

0 Brandon Amos, et al. ∙

research

∙ 05/21/2018

Depth-Limited Solving for Imperfect-Information Games

A fundamental challenge in imperfect-information games is that states do...

0 Noam Brown, et al. ∙

research

∙ 04/17/2018

Learning Awareness Models

We consider the setting of an agent with a fixed body interacting with a...

0 Brandon Amos, et al. ∙

research

∙ 03/01/2017

OptNet: Differentiable Optimization as a Layer in Neural Networks

This paper presents OptNet, a network architecture that integrates optim...

0 Brandon Amos, et al. ∙

Brandon Amos

Featured Co-authors