Related papers: Optimal Transport Kernels for Sequential and Paral…
The term Neural Architecture Search (NAS) refers to the automatic optimization of network architectures for a new, previously unknown task. Since testing an architecture is computationally very expensive, many optimizers need days or even…
Multi-task neural architecture search (NAS) enables transferring architectural knowledge among different tasks. However, ranking disorder between the source task and the target task degrades the architecture performance on the downstream…
Recent advances in adversarial attacks show the vulnerability of deep neural networks searched by Neural Architecture Search (NAS). Although NAS methods can find network architectures with the state-of-the-art performance, the adversarial…
We investigate finding a map $g$ within a function class $G$ that minimises an Optimal Transport (OT) cost between a target measure $\nu$ and the image by $g$ of a source measure $\mu$. This is relevant when an OT map from $\mu$ to $\nu$…
We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of…
In this paper we introduce two algorithms for neural architecture search (NASGD and NASAGD) following the theoretical work by two of the authors [5] which used the geometric structure of optimal transport to introduce the conceptual basis…
Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the former are notoriously expensive, the latter suffer from…
Neural architecture search (NAS) proves to be among the best approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by high computational cost and memory consumption. At the same time,…
In machine learning, Optimal Transport (OT) theory is extensively utilized to compare probability distributions across various applications, such as graph data represented by node distributions and image data represented by pixel…
Solving large scale Optimal Transport (OT) in machine learning typically relies on sampling measures to obtain a tractable discrete problem. While the discrete solver's accuracy is controllable, the rate of convergence of the discretization…
We investigate the problem of sampling from posterior distributions with intractable normalizing constants in Bayesian inference. Our solution is a new generative modeling approach based on optimal transport (OT) that learns a deterministic…
We study unsupervised generative modeling in terms of the optimal transport (OT) problem between true (but unknown) data distribution $P_X$ and the latent variable model distribution $P_G$. We show that the OT problem can be equivalently…
\textbf{Motivation:} Predicting single-cell perturbation responses requires mapping between two unpaired single-cell data distributions. Optimal transport (OT) theory provides a principled framework for constructing such mappings by…
Differentiable architecture search has gradually become the mainstream research topic in the field of Neural Architecture Search (NAS) for its high efficiency compared with the early NAS methods. Recent differentiable NAS also aims at…
Optimal transport (OT) and Gromov-Wasserstein (GW) alignment are powerful frameworks for geometrically driven matching of probability distributions, yet their large-scale usage is hampered by high statistical and computational costs.…
Deploying models across diverse devices demands tradeoffs among multiple objectives due to different resource constraints. Arguably, due to the small model trap problem in multi-objective neural architecture search (MO-NAS) based on a…
The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering. As a consequence, neural architecture search (NAS), which aims at automatically designing neural network architectures in…
The search space of neural architecture search (NAS) for convolutional neural network (CNN) is huge. To reduce searching cost, most NAS algorithms use fixed outer network level structure, and search the repeatable cell structure only. Such…
In this paper, we propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks, aiming to automate the design of SPD neural architectures. To address this problem, we first introduce a…
Despite recent progress on image-based virtual try-on, current methods are constraint by shared warping networks and thus fail to synthesize natural try-on results when faced with clothing categories that require different warping…