Search Results for author:
Found 41 papers, 30 papers with code
TaskMet: Task-Driven Metric Learning for Model Learning
We propose take the task loss signal one level deeper than the parameters of the model and use it to learn the parameters of the loss function the model is trained on, which can be done by learning a metric in the prediction space.
Stochastic Optimal Control Matching
Our work introduces Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control that stems from the same philosophy as the conditional score matching loss for diffusion models.
Learning to Warm-Start Fixed-Point Optimization Algorithms
We introduce a machine-learning framework to warm-start fixed-point optimization algorithms.
Multisample Flow Matching: Straightening Flows with Minibatch Couplings
Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples.
On amortizing convex conjugates for optimal transport
I show that combining amortized approximations to the conjugate with a solver for fine-tuning significantly improves the quality of transport maps learned for the Wasserstein-2 benchmark by Korotin et al. (2021a) and is able to model many 2-dimensional couplings and flows considered in the literature.
Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories
For this setting, we develop and study a simple meta-algorithmic pipeline that learns an inverse dynamics model on the labelled data to obtain proxy-labels for the unlabelled data, followed by the use of any offline RL algorithm on the true and proxy-labelled trajectories.
Theseus: A Library for Differentiable Nonlinear Optimization
We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common framework for end-to-end structured learning in robotics and vision.
Matching Normalizing Flows and Probability Paths on Manifolds
Continuous Normalizing Flows (CNFs) are a class of generative models that transform a prior distribution to a model distribution by solving an ordinary differential equation (ODE).
Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world
We introduce Nocturne, a new 2D driving simulator for investigating multi-agent coordination under partial observability.
Meta Optimal Transport
We study the use of amortized optimization to predict optimal transport (OT) maps from the input measures, which we call Meta OT.
Semi-Discrete Normalizing Flows through Differentiable Tessellation
Mapping between discrete and continuous distributions is a difficult task and many have had to resort to heuristical approaches.
Tutorial on amortized optimization
Optimization is a ubiquitous modeling tool and is often deployed in settings which repeatedly solve similar instances of the same problem.
Input Convex Gradient Networks
The gradients of convex functions are expressive models of non-trivial vector fields.
Cross-Domain Imitation Learning via Optimal Transport
Cross-domain imitation learning studies how to leverage expert demonstrations of one agent to train an imitation agent with a different embodiment or morphology.
Scalable Online Planning via Reinforcement Learning Fine-Tuning
Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker.
Learning Complex Geometric Structures from Data with Deep Riemannian Manifolds
We present Deep Riemannian Manifolds, a new class of neural network parameterized Riemannian manifolds that can represent and learn complex geometric structures.
Imitation Learning from Pixel Observations for Continuous Control
In this setting, we explore recipes for imitation learning based on adversarial learning and optimal transport.
Neural Fixed-Point Acceleration for Convex Optimization
Fixed-point iterations are at the heart of numerical computing and are often a computational bottleneck in real-time applications that typically need a fast solution of moderate accuracy.
Riemannian Convex Potential Maps
Modeling distributions on Riemannian manifolds is a crucial component in understanding non-Euclidean data that arises, e. g., in physics and geology.
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact.
MBRL-Lib: A Modular Library for Model-based Reinforcement Learning
MBRL-Lib is designed as a platform for both researchers, to easily develop, debug and compare new algorithms, and non-expert user, to lower the entry-bar of deploying state-of-the-art algorithms.
Model-based Reinforcement Learning
reinforcement-learning
+1
Sliced Multi-Marginal Optimal Transport
To construct this distance, we introduce a characterization of the one-dimensional multi-marginal Kantorovich problem and use it to highlight a number of properties of the sliced multi-marginal Wasserstein distance.
Neural Potts Model
We propose the Neural Potts Model objective as an amortized optimization problem.
Neural Spatio-Temporal Point Processes
We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are localized in continuous time and space.
Learning Neural Event Functions for Ordinary Differential Equations
The existing Neural ODE formulation relies on an explicit knowledge of the termination time.
Fit The Right NP-Hard Problem: End-to-end Learning of Integer Programming Constraints
Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact.
On the model-based stochastic value gradient for continuous reinforcement learning
For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning agents.
Aligning Time Series on Incomparable Spaces
Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in comparable spaces.
Objective Mismatch in Model-based Reinforcement Learning
In our experiments, we study this objective mismatch issue and demonstrate that the likelihood of one-step ahead predictions is not always correlated with control performance.
Model-based Reinforcement Learning
reinforcement-learning
+1
Differentiable Convex Optimization Layers
In this paper, we propose an approach to differentiating through disciplined convex programs, a subclass of convex optimization problems used by domain-specific languages (DSLs) for convex optimization.
Generalized Inner Loop Meta-Learning
Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem.
Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
A promising approach is to learn a latent representation together with the control policy.
The Differentiable Cross-Entropy Method
We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function's parameters.
The Limited Multi-Label Projection Layer
We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems.
Differentiable MPC for End-to-end Planning and Control
We present foundations for using Model Predictive Control (MPC) as a differentiable policy class for reinforcement learning in continuous state and action spaces.
Depth-Limited Solving for Imperfect-Information Games
This paper introduces a principled way to conduct depth-limited solving in imperfect-information games by allowing the opponent to choose among a number of strategies for the remainder of the game at the depth limit.
Learning Awareness Models
We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world.
Task-based End-to-end Model Learning in Stochastic Optimization
With the increasing popularity of machine learning techniques, it has become common to see prediction algorithms operating within some larger process.
OptNet: Differentiable Optimization as a Layer in Neural Networks
This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks.
Input Convex Neural Networks
We show that many existing neural network architectures can be made input-convex with a minor modification, and develop specialized optimization algorithms tailored to this setting.
OpenFace: A general-purpose face recognition library with mobile applications
Cameras are becoming ubiquitous in the Internet of Things (IoT) and can use face recognition technology to improve context.
Ranked #7 on
Face Verification
on Labeled Faces in the Wild
