Related papers: MCGrad: Multicalibration at Web Scale
In semi-supervised learning (SSL), a technique called consistency regularization (CR) achieves high performance. It has been proved that the diversity of data used in CR is extremely important to obtain a model with high discrimination…
Multimodal information processing has become increasingly important for enhancing image classification performance. However, the intricate and implicit dependencies across different modalities often hinder conventional methods from…
Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to detect mislabeled instances and subject them to special…
Developing generalist robots capable of mastering diverse skills remains a central challenge in embodied AI. While recent progress emphasizes scaling model parameters and offline datasets, such approaches are limited in robotics, where…
Data set composed of categorical features is very common in big data analysis tasks. Since categorical features are usually with a limited number of qualitative possible values, the nested granular cluster effect is prevalent in the…
The advances of sensor technology enable people to monitor air quality through widely distributed low-cost sensors. However, measurements from these sensors usually encounter high biases and require a calibration step to reach an acceptable…
Large Language Models (LLMs) often suffer from hallucinations, which Retrieval-Augmented Generation (RAG) and GraphRAG mitigate by incorporating external knowledge and knowledge graphs (KGs). However, GraphRAG remains text-centric due to…
Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike…
One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers…
Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for labelling large number of images, the amount of available training data is always limited. To produce more data…
Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and…
Probabilistic classifiers output a probability distribution on target classes rather than just a class prediction. Besides providing a clear separation of prediction and decision making, the main advantage of probabilistic models is their…
Multirate time integration methods apply different step sizes to resolve different components of the system based on the local activity levels. This local selection of step sizes allows increased computational efficiency while achieving the…
In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning methods have achieved great success in predictive accuracy,…
Uncertainty quantification in automated image analysis is highly desired in many applications. Typically, machine learning models in classification or segmentation are only developed to provide binary answers; however, quantifying the…
Multi-agent reinforcement learning (MARL) has been gaining extensive attention from academia and industries in the past few decades. One of the fundamental problems in MARL is how to evaluate different approaches comprehensively. Most…
We introduce CLARGA, a general-purpose multimodal fusion architecture for multimodal representation learning that works with any number and type of modalities without changing the underlying framework. Given a supervised dataset, CLARGA can…
Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and…
Amid mounting concern about the reliability and credibility of machine learning research, we present a principled framework for making robust and generalizable claims: the multiverse analysis. Our framework builds upon the multiverse…
Many mechanical engineering applications call for multiscale computational modeling and simulation. However, solving for complex multiscale systems remains computationally onerous due to the high dimensionality of the solution space.…