Related papers: FISTA-Condat-Vu: Automatic Differentiation for Hyp…

This paper proposes a statistically optimal approach for learning a function value using a confidence interval in a wide range of models, including general non-parametric estimation of an expected loss described as a stochastic programming…

In multistage decision problems, it is often the case that an initial strategic decision (such as investment) is followed by many operational ones (operating the investment). Such initial strategic decision can be seen as a parameter…

Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization, which can be considered as hyperparameters. Although such hyperparameters can be optimized using the existing gradient-based…

Recent developments in the unsupervised domain adaptation (UDA) enable the unsupervised machine learning (ML) prediction for target data, thus this will accelerate real world applications with ML models such as image recognition tasks in…

We address the problem of learning an unknown smooth function and its derivatives from noisy pointwise evaluations under the supremum norm. While classical nonparametric regression provides a strong theoretical foundation, traditional…

Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or…

We derive methods to compute higher order differentials (Hessians and Hessian-vector products) of the rendering operator. Our approach is based on importance sampling of a convolution that represents the differentials of rendering…

Quasi-Newton methods are widely used in practise for convex loss minimization problems. These methods exhibit good empirical performance on a wide variety of tasks and enjoy super-linear convergence to the optimal solution. For large-scale…

This paper introduces a coordinate descent version of the V\~u-Condat algorithm. By coordinate descent, we mean that only a subset of the coordinates of the primal and dual iterates is updated at each iteration, the other coordinates being…

Naturalistic fMRI characterizes the brain as a dynamic predictive engine driven by continuous sensory streams. However, modeling the causal forward evolution in realistic neural simulation is impeded by the timescale mismatch between…

This paper presents a new regularization method to train a fully convolutional network for semantic tissue segmentation in histopathological images. This method relies on the benefit of unsupervised learning, in the form of image…

A significant milestone in modern gradient-based optimization was achieved with the development of Nesterov's accelerated gradient descent (NAG) method. This forward-backward technique has been further advanced with the introduction of its…

The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD…

We consider the problem of minimizing the sum of three convex functions: i) a smooth function $f$ in the form of an expectation or a finite average, ii) a non-smooth function $g$ in the form of a finite average of proximable functions…

In computer vision, Single Image Super-Resolution (SISR) is still a difficult problem. We present ViT-SR, a new technique to improve the performance of a Vision Transformer (ViT) employing a two-stage training strategy. In our method, the…

We analyze convergence rates of stochastic optimization procedures for non-smooth convex optimization problems. By combining randomized smoothing techniques with accelerated gradient methods, we obtain convergence rates of stochastic…

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

Most existing federated learning algorithms are based on the vanilla FedAvg scheme. However, with the increase of data complexity and the number of model parameters, the amount of communication traffic and the number of iteration rounds for…

Visual Instruction Finetuning (VIF) is pivotal for post-training Vision-Language Models (VLMs). Unlike unimodal instruction finetuning in plain-text large language models, which mainly requires instruction datasets to enable model…

Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the…