相关论文: Balanced Sharpness-Aware Minimization for Imbalanc…

Improving the generalization ability of modern deep neural networks (DNNs) is a fundamental challenge in machine learning. Two branches of methods have been proposed to seek flat minima and improve generalization: one led by sharpness-aware…

Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the…

In observational studies, weighting methods that directly optimize the balance between treatment and covariates have received much attention lately; however these have mainly focused on binary treatments. Inspired by domain adaptation, we…

Sharpness-Aware Minimization (SAM) was introduced to improve generalization by seeking flat minima, yet it also exhibits robustness to label noise, a phenomenon that remains only partially understood. Prior work has mainly attributed this…

Class imbalance poses a significant challenge in classification tasks, where traditional approaches often lead to biased models and unreliable predictions. Undersampling and oversampling techniques have been commonly employed to address…

We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization. The key intuition behind our approach is to use at…

Many important computer vision applications are naturally formulated as regression problems. Within medical imaging, accurate regression models have the potential to automate various tasks, helping to lower costs and improve patient…

Weighting procedures are used in observational causal inference to adjust for covariate imbalance within the sample. Common practice for inference is to estimate robust standard errors from a weighted regression of outcome on treatment.…

Sharpness-Aware Minimization (SAM) has recently emerged as a robust technique for improving the accuracy of deep neural networks. However, SAM incurs a high computational cost in practice, requiring up to twice as much computation as…

The generalized linear model (GLM) plays a key role in regression analyses. In high-dimensional data, the sparse GLM has been used but it is not robust against outliers. Recently, the robust methods have been proposed for the specific…

Recent state-of-the-art forecasting methods are trained on collections of time series. These methods, often referred to as global models, can capture common patterns in different time series to improve their generalization performance.…

Data imbalance persists as a pervasive challenge in regression tasks, introducing bias in model performance and undermining predictive reliability. This is particularly detrimental in applications aimed at predicting rare events that fall…

This paper evaluates six strategies for mitigating imbalanced data: oversampling, undersampling, ensemble methods, specialized algorithms, class weight adjustments, and a no-mitigation approach referred to as the baseline. These strategies…

Model-agnostic meta learning (MAML) is currently one of the dominating approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML can be challenging due to the innate bilevel problem structure. Specifically,…

This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets. In contrast to traditional approaches -- which typically assume full knowledge of the forward model or access to paired degraded and…

Sharpness-Aware Minimization (SAM) is an optimizer that takes a descent step based on the gradient at a perturbation $y_t = x_t + \rho \frac{\nabla f(x_t)}{\lVert \nabla f(x_t) \rVert}$ of the current point $x_t$. Existing studies prove…

The allure of superhuman-level capabilities has led to considerable interest in language models like GPT-3 and T5, wherein the research has, by and large, revolved around new model architectures, training tasks, and loss objectives, along…

Medical Image Foundation Models have proven to be powerful tools for mask prediction across various datasets. However, accurately assessing the uncertainty of their predictions remains a significant challenge. To address this, we propose a…

Nonparametric estimation using uniform-width binning is a standard approach for evaluating the calibration performance of machine learning models. However, existing theoretical analyses of the bias induced by binning are limited to binary…

Classification on imbalanced datasets is a challenging task in real-world applications. Training conventional classification algorithms directly by minimizing classification error in this scenario can compromise model performance for…