Related papers: FISTA-Condat-Vu: Automatic Differentiation for Hyp…
We propose a convolution-FFT method for pricing European options under the Heston model that leverages a continuously differentiable representation of the joint characteristic function. Unlike existing Fourier-based methods that rely on…
Robust feature extraction is an integral part of scientific visualization. In unsteady vector field analysis, researchers recently directed their attention towards the computation of near-steady reference frames for vortex extraction, which…
Fine-Grained Image Retrieval~(FGIR) faces challenges in learning discriminative visual representations to retrieve images with similar fine-grained features. Current leading FGIR solutions typically follow two regimes: enforce pairwise…
In machine unlearning, $(\varepsilon,\delta)-$unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the forget set, from a trained model. For strongly convex…
Learning discriminative features for effectively separating abnormal events from normality is crucial for weakly supervised video anomaly detection (WS-VAD) tasks. Existing approaches, both video and segment-level label oriented, mainly…
We introduce a variant of Multicut Decomposition Algorithms (MuDA), called CuSMuDA (Cut Selection for Multicut Decomposition Algorithms), for solving multistage stochastic linear programs that incorporates strategies to select the most…
FISTA is a popular convex optimisation algorithm which is known to converge at an optimal rate whenever a minimiser is contained in a suitable Hilbert space. We propose a modified algorithm where each iteration is performed in a subset…
Recently, the vision transformer (ViT) has made breakthroughs in image recognition. Its self-attention mechanism (MSA) can extract discriminative labeling information of different pixel blocks to improve image classification accuracy.…
Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source domain (e.g. synthetic data) to the target domain (e.g. real-world data) without requiring further annotations on the target domain. This work focuses on UDA…
In optimization-based image restoration models, the correct selection of hyperparameters is crucial for achieving superior performance. However, current research typically involves manual tuning of these hyperparameters, which is highly…
Predictive models can be used on high-dimensional brain images for diagnosis of a clinical condition. Spatial regularization through structured sparsity offers new perspectives in this context and reduces the risk of overfitting the model…
We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, ``submodels'',…
Graph-based variational methods have recently shown to be highly competitive for various classification problems of high-dimensional data, but are inherently difficult to handle from an optimization perspective. This paper proposes a convex…
In this paper, we describe and establish iteration-complexity of two accelerated composite gradient (ACG) variants to solve a smooth nonconvex composite optimization problem whose objective function is the sum of a nonconvex differentiable…
This paper presents an accelerated proximal gradient method for multiobjective optimization, in which each objective function is the sum of a continuously differentiable, convex function and a closed, proper, convex function. Extending…
Dimension of the encoder output (i.e., the code layer) in an autoencoder is a key hyper-parameter for representing the input data in a proper space. This dimension must be carefully selected in order to guarantee the desired reconstruction…
We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, but instead of the classical approach of proving convergence…
Introduced by Beck and Teboulle, FISTA (for Fast Iterative Shrinkage-Thresholding Algorithm) is a first-order method widely used in convex optimization. Adapted from Nesterov's accelerated gradient method for convex functions, the generated…
How to extract more and useful information for single image super resolution is an imperative and difficult problem. Learning-based method is a representative method for such task. However, the results are not so stable as there may exist…
We study the problem of efficiently computing the derivative of the fixed-point of a parametric nondifferentiable contraction map. This problem has wide applications in machine learning, including hyperparameter optimization, meta-learning…