English
Related papers

Related papers: Augment and Reduce: Stochastic Inference for Large…

200 papers

To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation,…

Machine Learning · Statistics 2019-12-24 Mingzhang Yin , Yuguang Yue , Mingyuan Zhou

Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and…

Computer Vision and Pattern Recognition · Computer Science 2019-11-15 Ekin D. Cubuk , Barret Zoph , Jonathon Shlens , Quoc V. Le

In the regression problem, L1 and L2 are the most commonly used loss functions, which produce mean predictions with different biases. However, the predictions are neither robust nor adequate enough since they only capture a few conditional…

Machine Learning · Computer Science 2019-11-14 Faen Zhang , Xinyu Fan , Hui Xu , Pengcheng Zhou , Yujian He , Junlong Liu

Generative flows and diffusion models have been predominantly trained on ordinal data, for example natural images. This paper introduces two extensions of flows and diffusion for categorical data such as language or image segmentation:…

Machine Learning · Statistics 2021-10-25 Emiel Hoogeboom , Didrik Nielsen , Priyank Jaini , Patrick Forré , Max Welling

This paper studies empirical risk minimization (ERM) problems for large-scale datasets and incorporates the idea of adaptive sample size methods to improve the guaranteed convergence bounds for first-order stochastic and deterministic…

Machine Learning · Computer Science 2017-09-05 Aryan Mokhtari , Alejandro Ribeiro

In large-scale classification problems, the data set always be faced with frequent updates when a part of the data is added to or removed from the original data set. In this case, conventional incremental learning, which updates an existing…

Machine Learning · Computer Science 2021-01-15 Kaichen Zhou , Shiji Song , Gao Huang , Wu Cheng , Quan Zhou

Text augmentation is a technique for constructing synthetic data from an under-resourced corpus to improve predictive performance. Synthetic data generation is common in numerous domains. However, recently text augmentation has emerged in…

Computation and Language · Computer Science 2023-09-12 Mosleh Mahamud , Zed Lee , Isak Samsten

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…

Machine Learning · Computer Science 2022-05-27 Jianhan Wu , Shijing Si , Jianzong Wang , Jing Xiao

Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…

Machine Learning · Computer Science 2023-05-09 Ambar Pal , Jeremias Sulam

Neural networks are capable of learning powerful representations of data, but they are susceptible to overfitting due to the number of parameters. This is particularly challenging in the domain of time series classification, where datasets…

Machine Learning · Computer Science 2022-01-28 Hong Yang , Travis Desell

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods…

Computation and Language · Computer Science 2025-09-25 Shuyu Guo , Shuo Zhang , Zhaochun Ren

Deep learning has achieved remarkable success in medical image classification. However, its clinical application is often hindered by data heterogeneity caused by variations in scanner vendors, imaging protocols, and operators. Approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Yaoyao Zhu , Xiuding Cai , Yingkai Wang , Yu Yao , Xu Luo , Zhongliang Fu

Neural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available. However, as new domains are frequently added, creating sizeable data is expensive.…

Computation and Language · Computer Science 2020-09-09 Samuel Louvan , Bernardo Magnini

It is not an exaggeration to say that the recent progress in artificial intelligence technology depends on large-scale and high-quality data. Simultaneously, a prevalent issue exists everywhere: the budget for data labeling is constrained.…

Machine Learning · Computer Science 2023-08-22 Yujin Hwang , Won Jo , Juyoung Hong , Yukyung Choi

The estimation of categorical distributions under marginal constraints summarizing some sample from a population in the most-generalizable way is key for many machine-learning and data-driven approaches. We provide a parameter-agnostic…

High Energy Physics - Theory · Physics 2023-11-17 Orestis Loukas , Ho Ryun Chung

Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items…

Information Retrieval · Computer Science 2025-03-27 Sichun Luo , Jian Xu , Xiaojie Zhang , Linrong Wang , Sicong Liu , Hanxu Hou , Linqi Song

In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without compromising content integrity. This paper introduces novel auction…

Computer Science and Game Theory · Computer Science 2025-06-16 MohammadTaghi Hajiaghayi , Sébastien Lahaie , Keivan Rezaei , Suho Shin

The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external…

Computation and Language · Computer Science 2025-03-04 Zhenrui Yue , Honglei Zhuang , Aijun Bai , Kai Hui , Rolf Jagerman , Hansi Zeng , Zhen Qin , Dong Wang , Xuanhui Wang , Michael Bendersky

We propose a new scalable multi-class Gaussian process classification approach building on a novel modified softmax likelihood function. The new likelihood has two benefits: it leads to well-calibrated uncertainty estimates and allows for…

Machine Learning · Statistics 2019-05-24 Théo Galy-Fajou , Florian Wenzel , Christian Donner , Manfred Opper

D&R is a statistical approach designed to handle large and complex datasets. It partitions the dataset into several manageable subsets and subsequently applies the analytic method to each subset independently to obtain results. Finally, the…

Methodology · Statistics 2024-12-12 Md. Mahadi Hassan Nayem , Soma Chowdhury Biswas