90 citations · 910 across the 140 of their papers we have counts for
24 papers · 1 filter
Distributionally Robust Schrödinger Bridge
Jinhwan Sul, Panagiotis Theodoropoulos, Vincent Pacelli +2
Schrödinger bridge (SB) learns stochastic transport between prescribed initial and target distributions. When the initial distribution shifts at test time, the learned dynamics can…
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
Panagiotis Theodoropoulos, Nan Jiang, Xintong Duan +4
Power-sharpened sampling is an inference-time alternative to reinforcement-learning (RL) post-training for enhancing reasoning in large language models (LLMs). High-probability seq…
Variational Inference via Entropic Transport Descent
Vincent Pacelli, Akash Ratheesh, Evangelos Theodorou
Particle-based variational inference (ParVI) methods approximate an intractable target distribution by evolving an ensemble of interacting samples. Existing approaches rely predomi…
Generalized Schrödinger Bridge on Graphs
Panagiotis Theodoropoulos, Juno Nam, Evangelos Theodorou +1
Transportation on graphs is a fundamental challenge across many domains, where decisions must respect topological and operational constraints. Despite the need for actionable polic…
Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming
Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou
Optimization of deep neural networks (DNNs) has been a driving force in the advancement of modern machine learning and artificial intelligence. With DNNs characterized by a prolong…
Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
Yuchen Zhu, Tianrong Chen, Lingkai Kong +2
The generative modeling of data on manifolds is an important task, for which diffusion models in flat spaces typically need nontrivial adaptations. This article demonstrates how a…
Augmented Bridge Matching
Valentin De Bortoli, Guan-Horng Liu, Tianrong Chen +2
Flow and bridge matching are a novel class of processes which encompass diffusion models. One of the main aspect of their increased flexibility is that these models can interpolate…
Generative Modeling with Phase Stochastic Bridges
Tianrong Chen, Jiatao Gu, Laurent Dinh +3
Diffusion models (DMs) represent state-of-the-art generative models for continuous inputs. DMs work by constructing a Stochastic Differential Equation (SDE) in the input space (ie,…
Data-driven discovery of non-Newtonian astronomy via learning non-Euclidean Hamiltonian
Oswin So, Gongjie Li, Evangelos A. Theodorou +1
Incorporating the Hamiltonian structure of physical dynamics into deep learning models provides a powerful way to improve the interpretability and prediction accuracy. While previo…
Second-Order Neural ODE Optimizer
Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou
We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs).…
Dynamic Game Theoretic Neural Optimizer
Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou
The connection between training deep neural networks (DNNs) and optimal control theory (OCT) has attracted considerable attention as a principled tool of algorithmic design. Despit…
Robustifying Reinforcement Learning Policies with Adaptive Control
Yikun Cheng, Pan Zhao, Manan Gandhi +3
A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods…
Variational Inference MPC using Tsallis Divergence
Ziyi Wang, Oswin So, Jason Gibson +4
In this paper, we provide a generalized framework for Variational Inference-Stochastic Optimal Control by using thenon-extensive Tsallis divergence. By incorporating the deformed e…
Distributed Algorithms for Linearly-Solvable Optimal Control in Networked Multi-Agent Systems
Neng Wan, Aditya Gahlawat, Naira Hovakimyan +2
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…
A Differential Game Theoretic Neural Optimizer for Training Residual Networks
Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou
Connections between Deep Neural Networks (DNNs) training and optimal control theory has attracted considerable attention as a principled tool of algorithmic design. Differential Dy…
NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control
Ioannis Exarchos, Marcus A. Pereira, Ziyi Wang +1
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. Specific…
DDPNOpt: Differential Dynamic Programming Neural Optimizer
Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou
Interpretation of Deep Neural Networks (DNNs) training as an optimal control problem with nonlinear dynamical systems has received considerable attention recently, yet the algorith…
Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective
Guan-Horng Liu, Evangelos A. Theodorou
Attempts from different disciplines to provide a fundamental understanding of deep learning have advanced rapidly in recent years, yet a unified framework remains relatively limite…
Deep 2FBSDEs For Systems With Control Multiplicative Noise
Marcus A Pereira, Ziyi Wang, Tianrong Chen +2
We present a deep recurrent neural network architecture to solve a class of stochastic optimal control problems described by fully nonlinear Hamilton Jacobi Bellmanpartial differen…
Accelerating Imitation Learning with Predictive Models
Ching-An Cheng, Xinyan Yan, Evangelos A. Theodorou +1
Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has p…
MPC-Inspired Neural Network Policies for Sequential Decision Making
Marcus Pereira, David D. Fan, Gabriel Nakajima An +1
In this paper we investigate the use of MPC-inspired neural network policies for sequential decision making. We introduce an extension to the DAgger algorithm for training such pol…
Safe end-to-end imitation learning for model predictive control
Keuntaek Lee, Kamil Saigol, Evangelos A. Theodorou
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 circumstance…
Safe Learning of Quadrotor Dynamics Using Barrier Certificates
Li Wang, Evangelos A. Theodorou, Magnus Egerstedt
To effectively control complex dynamical systems, accurate nonlinear models are typically needed. However, these models are not always known. In this paper, we present a data-drive…
Variational Policy for Guiding Point Processes
Yichen Wang, Grady Williams, Evangelos Theodorou +1
Temporal point processes have been widely applied to model event sequence data generated by online users. In this paper, we consider the problem of how to design the optimal contro…