Search Results for author:
Found 48 papers, 9 papers with code
I$^2$SB: Image-to-Image Schrödinger Bridge
We propose Image-to-Image Schr\"odinger Bridge (I$^2$SB), a new class of conditional diffusion models that directly learn the nonlinear diffusion processes between two given distributions.
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
However, it remains unclear whether the optimization principle of SB relates to the modern training of deep generative models, which often rely on constructing log-likelihood objectives. This raises questions on the suitability of SB models as a principled alternative for generative applications.
Ranked #44 on
Image Generation
on CIFAR-10
Second-Order Neural ODE Optimizer
We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs).
Deep Generalized Schrödinger Bridge
In this work, we aim at solving a challenging class of MFGs in which the differentiability of these interacting preferences may not be available to the solver, and the population is urged to converge exactly to some desired distribution.
Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective
In this article, we provide one possible way to align existing branches of deep learning theory through the lens of dynamical system and optimal control.
Bayesian Learning-Based Adaptive Control for Safety Critical Systems
We propose a framework which satisfies these constraints while allowing the use of deep neural networks for learning model uncertainties.
Mirror Diffusion Models for Constrained and Watermarked Generation
In this work, we propose Mirror Diffusion Models (MDM), a new class of diffusion models that generate data on convex constrained sets without losing any tractability.
Generalized Schrödinger Bridge Matching
Modern distribution matching algorithms for training diffusion or flow models directly prescribe the time evolution of the marginal distributions between two boundary distributions.
Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving
We present an information theoretic approach to stochastic optimal control problems that can be used to derive general sampling based optimization schemes.
Robotics
Accelerating Imitation Learning with Predictive Models
When the model oracle is learned online, these algorithms can provably accelerate the best known convergence rate up to an order.
Safe end-to-end imitation learning for model predictive control
We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set.
Safe Learning of Quadrotor Dynamics Using Barrier Certificates
The barrier certificates establish a non-conservative forward invariant safe region, in which high probability safety guarantees are provided based on the statistics of the Gaussian Process.
Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control
Sparse Spectrum Gaussian Processes (SSGPs) are a powerful tool for scaling Gaussian processes (GPs) to large datasets.
Perceptual Attention-based Predictive Control
The proposed information processing architecture is used to support a perceptual attention-based predictive control algorithm that leverages model predictive control (MPC), convolutional neural networks (CNNs), and uncertainty quantification methods.
Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamics
We consider the problem of online adaptation of a neural network designed to represent vehicle dynamics.
Deep Forward-Backward SDEs for Min-max Control
This paper presents a novel approach to numerically solve stochastic differential games for nonlinear systems.
Deep 2FBSDEs For Systems With Control Multiplicative Noise
We present a deep recurrent neural network architecture to solve a class of stochastic optimal control problems described by fully nonlinear Hamilton Jacobi Bellmanpartial differential equations.
Aggressive Perception-Aware Navigation using Deep Optical Flow Dynamics and PixelMPC
In this work, we couple a model predictive control (MPC) framework to a visual pipeline.
Deep Learning Tubes for Tube MPC
This uncertainty may come from errors in learning (due to a lack of data, for example), or may be inherent to the system.
DDPNOpt: Differential Dynamic Programming Neural Optimizer
Interpretation of Deep Neural Networks (DNNs) training as an optimal control problem with nonlinear dynamical systems has received considerable attention recently, yet the algorithmic development remains relatively limited.
Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning
In this work, we present a method for obtaining an implicit objective function for vision-based navigation.
NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control
In this work we propose the use of adaptive stochastic search as a building block for general, non-convex optimization operations within deep neural network architectures.
A Differential Game Theoretic Neural Optimizer for Training Residual Networks
Connections between Deep Neural Networks (DNNs) training and optimal control theory has attracted considerable attention as a principled tool of algorithmic design.
Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs
This paper introduces a new formulation for stochastic optimal control and stochastic dynamic optimization that ensures safety with respect to state and control constraints.
Compositionality of Linearly Solvable Optimal Control in Networked Multi-Agent Systems
The proposed approach achieves both the compositionality and optimality of control actions simultaneously within the cooperative MAS framework in both discrete- and continuous-time in a sample-efficient manner, which reduces the burden of re-computation of the optimal control solutions for the new task on the MASs.
Cooperative Path Integral Control for Stochastic Multi-Agent Systems
Local control actions that rely only on agents' local observations are designed to optimize the joint cost functions of subsystems.
Large-Scale Multi-Agent Deep FBSDEs
We showcase superior performance of our framework over the state-of-the-art deep fictitious play algorithm on an inter-bank lending/borrowing problem in terms of multiple metrics.
Adaptive Risk Sensitive Model Predictive Control with Stochastic Search
We present a general framework for optimizing the Conditional Value-at-Risk for dynamical systems using stochastic search.
Distributional Reinforcement Learning
Optimization and Control
Robotics
Distributed Algorithms for Linearly-Solvable Optimal Control in Networked Multi-Agent Systems
Distributed algorithms for both discrete-time and continuous-time linearly solvable optimal control (LSOC) problems of networked multi-agent systems (MASs) are investigated in this paper.
Variational Inference MPC using Tsallis Divergence
In this paper, we provide a generalized framework for Variational Inference-Stochastic Optimal Control by using thenon-extensive Tsallis divergence.
Dynamic Game Theoretic Neural Optimizer
The connection between training deep neural networks (DNNs) and optimal control theory (OCT) has attracted considerable attention as a principled tool of algorithmic design.
HJB Based Optimal Safe Control Using Control Barrier Functions
This work proposes an optimal safe controller minimizing an infinite horizon cost functional subject to control barrier functions (CBFs) safety conditions.
Safety Embedded Control of Nonlinear Systems via Barrier States
The development enforces safety by means of barrier functions used in optimization through the construction of barrier states (BaS) which are embedded in the control system's model.
Learning Risk-aware Costmaps for Traversability in Challenging Environments
One of the main challenges in autonomous robotic exploration and navigation in unknown and unstructured environments is determining where the robot can or cannot safely move.
Deep $\mathcal{L}^1$ Stochastic Optimal Control Policies for Planetary Soft-landing
In this paper, we introduce a novel deep learning based solution to the Powered-Descent Guidance (PDG) problem, grounded in principles of nonlinear Stochastic Optimal Control (SOC) and Feynman-Kac theory.
Generalization of Safe Optimal Control Actions on Networked Multi-Agent Systems
The control action composition is achieved by taking a weighted mixture of the existing controllers according to the contribution of each component task.
Barrier States Embedded Iterative Dynamic Game for Robust and Safe Trajectory Optimization
The proposed method leverages a game theoretic differential dynamic programming approach with barrier states to handle parametric and non-parametric uncertainties in safety-critical control systems.
Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learning
It can be difficult to autonomously produce driver behavior so that it appears natural to other traffic participants.
Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMM
In this work, we propose a novel safe and scalable decentralized solution for multi-agent control in the presence of stochastic disturbances.
Deep Graphic FBSDEs for Opinion Dynamics Stochastic Control
Our approach relies on the probabilistic representation of the solution of the Hamilton-Jacobi-Bellman partial differential equation.
Distributed Differential Dynamic Programming Architectures for Large-Scale Multi-Agent Control
The aim of this work is to suggest architectures that inherit the computational efficiency and scalability of Differential Dynamic Programming (DDP) and the distributed nature of the Alternating Direction Method of Multipliers (ADMM).
Data-driven discovery of non-Newtonian astronomy via learning non-Euclidean Hamiltonian
Incorporating the Hamiltonian structure of physical dynamics into deep learning models provides a powerful way to improve the interpretability and prediction accuracy.
Gaussian Process Barrier States for Safe Trajectory Optimization and Control
We derive the barrier state dynamics utilizing the GP posterior, which is used to construct a safety embedded Gaussian process dynamical model (GPDM).
Barrier States Theory for Safety-Critical Multi-Objective Control
The proposition is that the control problem is now transformed to designing a control law for the new, unconstrained, system in which the barrier state is driven to stay bounded while achieving other performance objectives.
Generative Modeling with Phase Stochastic Bridges
In this work, we introduce a novel generative modeling framework grounded in \textbf{phase space dynamics}, where a phase space is defined as {an augmented space encompassing both position and velocity.}
Augmented Bridge Matching
In this paper, we highlight that while flow and bridge matching processes preserve the information of the marginal distributions, they do \emph{not} necessarily preserve the coupling information unless additional, stronger optimality conditions are met.
Quantum State Generation with Structure-Preserving Diffusion Model
This article considers the generative modeling of the states of quantum systems, and an approach based on denoising diffusion model is proposed.
React-OT: Optimal Transport for Generating Transition State in Chemical Reactions
The RMSD and barrier height error is further improved by roughly 25% through pretraining React-OT on a large reaction dataset obtained with a lower level of theory, GFN2-xTB.
