Search Results for author:
Found 43 papers, 10 papers with code
Proximal Oracles for Optimization and Sampling
Finally, we combine this proximal sampling oracle and ASF to obtain a Markov chain Monte Carlo method with non-asymptotic complexity bounds for sampling in semi-smooth and composite settings.
Toward effective protection against diffusion based mimicry through score distillation
In this work, we present novel findings on attacking latent diffusion models (LDM) and propose new plug-and-play strategies for more effective protection.
On the Contraction Coefficient of the Schrödinger Bridge for Stochastic Linear Systems
In this work, we study a priori estimates for the contraction coefficients associated with the convergence of respective Schr\"{o}dinger systems.
Data-Driven Adversarial Online Control for Unknown Linear Systems
We consider the online control problem with an unknown linear dynamical system in the presence of adversarial perturbations and adversarial convex loss functions.
Improved Order Analysis and Design of Exponential Integrator for Diffusion Models Sampling
By reformulating the differential equations in DMs and capitalizing on the theory of exponential integrators, we propose refined EI solvers that fulfill all the order conditions, which we designate as Refined Exponential Solver (RES).
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models.
DiffCollage: Parallel Generation of Large Content with Diffusion Models
We present DiffCollage, a compositional diffusion model that can generate large content by leveraging diffusion models trained on generating pieces of the large content.
ReorientDiff: Diffusion Model based Reorientation for Object Manipulation
While certain goals can be achieved by picking and placing the objects of interest directly, object reorientation is needed for precise placement in most of the tasks.
Improved dimension dependence of a proximal algorithm for sampling
For instance, for strongly log-concave distributions, our method has complexity bound $\tilde\mathcal{O}(\kappa d^{1/2})$ without warm start, better than the minimax bound for MALA.
Data-Driven Convex Approach to Off-road Navigation via Linear Transfer Operators
We provide a convex formulation to the off-road navigation problem by lifting the problem to the density space using the linear Perron-Frobenius (P-F) operator.
Signed Graph Neural Networks: A Frequency Perspective
Graph convolutional networks (GCNs) and its variants are designed for unsigned graphs containing only positive links.
gDDIM: Generalized denoising diffusion implicit models
In the CLD, a diffusion model by augmenting the diffusion process with velocity, our algorithm achieves an FID score of 2. 26, on CIFAR10, with only 50 number of score function evaluations~(NFEs) and an FID score of 2. 86 with only 27 NFEs.
A Proximal Algorithm for Sampling from Non-convex Potentials
This work extends the recent algorithm in \cite{LiaChe21, LiaChe22} for non-smooth/semi-smooth log-concave distribution to the setting with non-convex potentials.
Fast Sampling of Diffusion Models with Exponential Integrator
Our goal is to develop a fast sampling method for DMs with a much less number of steps while retaining high sample quality.
Geometry of finite-time thermodynamic cycles with anisotropic thermal fluctuations
In contrast to the classical concept of a Carnot engine that alternates contact between heat baths of different temperatures, naturally occurring processes usually harvest energy from anisotropy, being exposed simultaneously to chemical and thermal fluctuations of different intensities.
A Proximal Algorithm for Sampling
Departing from the standard smooth setting, the potentials are only assumed to be weakly smooth or non-smooth, or the summation of multiple such functions.
Improved analysis for a proximal algorithm for sampling
We study the proximal sampler of Lee, Shen, and Tian (2021) and obtain new convergence guarantees under weaker assumptions than strong log-concavity: namely, our results hold for (1) weakly log-concave targets, and (2) targets satisfying isoperimetric assumptions which allow for non-log-concavity.
Variational Wasserstein gradient flow
Wasserstein gradient flow has emerged as a promising approach to solve optimization problems over the space of probability distributions.
Path Integral Sampler: a stochastic control approach for sampling
The PIS is built on the Schr\"odinger bridge problem which aims to recover the most likely evolution of a diffusion process given its initial distribution and terminal distribution.
Diffusion Normalizing Flow
Our method is closely related to normalizing flow and diffusion probabilistic models and can be viewed as a combination of the two.
A Proximal Algorithm for Sampling from Non-smooth Potentials
One key contribution of this work is a fast algorithm that realizes the restricted Gaussian oracle for any convex non-smooth potential with bounded Lipschitz constant.
On the complexity of the optimal transport problem with graph-structured cost
Multi-marginal optimal transport (MOT) is a generalization of optimal transport to multiple marginals.
Inference of collective Gaussian hidden Markov models
We consider inference problems for a class of continuous state collective hidden Markov models, where the data is recorded in aggregate (collective) form generated by a large population of individuals following the same dynamics.
Neural Monge Map estimation and its applications
Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another.
Learning High Dimensional Wasserstein Geodesics
We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions.
Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
Specifically, we prove that moving along the geodesic in the direction of functional gradient with respect to the second-order Wasserstein distance is equivalent to applying a pushforward mapping to a probability distribution, which can be approximated accurately by pushing a set of particles.
Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory
Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks.
Learning Hidden Markov Models from Aggregate Observations
This problem arises when only the population level counts of the number of individuals at each time step are available, from which one seeks to learn the individual hidden Markov model.
Filtering for Aggregate Hidden Markov Models with Continuous Observations
We consider a class of filtering problems for large populations where each individual is modeled by the same hidden Markov model (HMM).
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport.
Incremental inference of collective graphical models
We consider incremental inference problems from aggregate data for collective dynamics.
Multi-marginal optimal transport and probabilistic graphical models
We study multi-marginal optimal transport problems from a probabilistic graphical model perspective.
Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory
We aim to answer the following questions: When the function approximator is a neural network, how does the associated feature representation evolve?
Improving Robustness via Risk Averse Distributional Reinforcement Learning
One major obstacle that precludes the success of reinforcement learning in real-world applications is the lack of robustness, either to model uncertainties or external disturbances, of the trained policies.
Distributional Reinforcement Learning
reinforcement-learning
+1
Inference with Aggregate Data: An Optimal Transport Approach
Consequently, the celebrated Sinkhorn/iterative scaling algorithm for multi-marginal optimal transport can be leveraged together with the standard belief propagation algorithm to establish an efficient inference scheme which we call Sinkhorn belief propagation (SBP).
Sample-based Distributional Policy Gradient
It relies on the key idea of replacing the expected return with the return distribution, which captures the intrinsic randomness of the long term rewards.
Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind.
Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games
We study discrete-time mean-field Markov games with infinite numbers of agents where each agent aims to minimize its ergodic cost.
On the Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind.
Understand the dynamics of GANs via Primal-Dual Optimization
By developing new primal-dual optimization tools, we show that, with a proper stepsize choice, the widely used first-order iterative algorithm in training GANs would in fact converge to a stationary solution with a sublinear rate.
Probabilistic Kernel Support Vector Machines
We propose a probabilistic enhancement of standard kernel Support Vector Machines for binary classification, in order to address the case when, along with given data sets, a description of uncertainty (e. g., error bounds) may be available on each datum.
Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
In this work, we consider a block-wise one-sided non-convex min-max problem, in which the minimization problem consists of multiple blocks and is non-convex, while the maximization problem is (strongly) concave.
On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator
We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization.
