Search Results for author:
Found 33 papers, 17 papers with code
Optimal Flow Matching: Learning Straight Trajectories in Just One Step
Over the several recent years, there has been a boom in development of flow matching methods for generative modeling.
Estimating Barycenters of Distributions with Neural Optimal Transport
Given a collection of probability measures, a practitioner sometimes needs to find an "average" distribution which adequately aggregates reference distributions.
Light and Optimal Schrödinger Bridge Matching
It exploits the optimal parameterization of the diffusion process and provably recovers the SB process \textbf{(a)} with a single bridge matching step and \textbf{(b)} with arbitrary transport plan as the input.
Light Schrödinger Bridge
Despite the recent advances in the field of computational Schr\"odinger Bridges (SB), most existing SB solvers are still heavy-weighted and require complex optimization of several neural networks.
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Optimal transport (OT) barycenters are a mathematically grounded way of averaging probability distributions while capturing their geometric properties.
Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark
We fill this gap and propose a novel way to create pairs of probability distributions for which the ground truth OT solution is known by the construction.
Energy-guided Entropic Neural Optimal Transport
Energy-based models (EBMs) are known in the Machine Learning community for decades.
Unbalanced and Light Optimal Transport
We address this challenge and propose a novel theoretically-justified and lightweight unbalanced EOT solver.
Neural Gromov-Wasserstein Optimal Transport
To demonstrate the effectiveness of our proposed method, we conduct experiments on the synthetic data and explore the practical applicability of our method to the popular task of the unsupervised alignment of word embeddings.
Entropic Neural Optimal Transport via Diffusion Processes
We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between continuous probability distributions which are accessible by samples.
Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?
Despite the success of WGANs, it is still unclear how well the underlying OT dual solvers approximate the OT cost (Wasserstein-1 distance, $\mathbb{W}_{1}$) and the OT gradient needed to update the generator.
Connecting adversarial attacks and optimal transport for domain adaptation
In domain adaptation, the goal is to adapt a classifier trained on the source domain samples to the target domain.
Neural Optimal Transport with General Cost Functionals
We introduce a novel neural network-based algorithm to compute optimal transport (OT) plans for general cost functionals.
Kernel Neural Optimal Transport
We study the Neural Optimal Transport (NOT) algorithm which uses the general optimal transport formulation and learns stochastic transport plans.
An Optimal Transport Perspective on Unpaired Image Super-Resolution
First, the learned SR map is always an optimal transport (OT) map.
Neural Optimal Transport
We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs.
Wasserstein Iterative Networks for Barycenter Estimation
Wasserstein barycenters have become popular due to their ability to represent the average of probability measures in a geometrically meaningful way.
Generative Modeling with Optimal Transport Maps
In particular, we consider denoising, colorization, and inpainting, where the optimality of the restoration map is a desired attribute, since the output (restored) image is expected to be close to the input (degraded) one.
Cycle monotonicity of adversarial attacks for optimal domain adaptation
In our algorithm, instead of mapping from target to the source domain, optimal transport maps target samples to the set of adversarial examples.
Manifold Topology Divergence: a Framework for Comparing Data Manifolds
We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance.
Large-Scale Wasserstein Gradient Flows
Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gradient descent over entropy functionals in Wasserstein space.
Manifold Topology Divergence: a Framework for Comparing Data Manifolds.
We propose a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization
Wasserstein barycenters provide a geometric notion of the weighted average of probability measures based on optimal transport.
Topological obstructions in neural networks learning
We define the neural network Topological Obstructions score, "TO-score", with the help of robust topological invariants, barcodes of the loss function, that quantify the "badness" of local minima for gradient-based optimization.
Integral Mixability: a Tool for Efficient Online Aggregation of Functional and Probabilistic Forecasts
In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts.
Barcodes as summary of objective function's topology
We apply the canonical forms (barcodes) of gradient Morse complexes to explore topology of loss surfaces.
Wasserstein-2 Generative Networks
We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance).
Barcodes as summary of objective functions' topology
We apply canonical forms of gradient complexes (barcodes) to explore neural networks loss surfaces.
Adaptive Hedging under Delayed Feedback
The article is devoted to investigating the application of hedging strategies to online expert weight allocation under delayed feedback.
Aggregating Strategies for Long-term Forecasting
The first one is theoretically close to an optimal algorithm and is based on replication of independent copies.
Long-Term Online Smoothing Prediction Using Expert Advice
In the first one, at each step $t$ the learner has to combine the point forecasts of the experts issued for the time interval $[t+1, t+d]$ ahead.
Meta-Learning for Resampling Recommendation Systems
One possible approach to tackle the class imbalance in classification tasks is to resample a training dataset, i. e., to drop some of its elements or to synthesize new ones.
